| 1. |
|
|
| 2. |
- Al-Naser, Mohammad, et al.
(författare)
-
Reconstruction of occluded facial images using asymmetrical Principal Component Analysis
- 2012
-
Ingår i: Integrated Computer-Aided Engineering. - 1069-2509 .- 1875-8835. ; 19:3, s. 273-283
-
Tidskriftsartikel (refereegranskat)abstract
- When only non-occluded image parts are available for facial images it is difficult or impossible to correctly recognize the person in the image. The problem addressed in this work is reconstruction of the occluded parts in facial images; e. g. eyes covered with sunglasses. Asymmetrical Principal Component Analysis (aPCA) allows estimation of occluded facial parts based on the content of the facial parts which are visible. aPCA is used to estimate full non-occluded faces from 3 kinds of occlusion with 2 different reconstruction methods in this work and we present the results with both objective and subjective evaluation. The subjective evaluation shows that clear and sharp image regions are preferred even if this results in visible edges in the images. The method also performs well when a different facial expression than the one in the database is used to calculate the reconstruction parameters.
|
|
| 3. |
- Al-Naser, Mohammad, et al.
(författare)
-
Reconstruction of occluded facial images using asymmetrical principal component analysis
- 2011
-
Ingår i: 2011 18th International Conference on Systems, Signals and Image Processing (IWSSIP). - : IEEE. - 9789958996610 ; , s. 276-279
-
Konferensbidrag (refereegranskat)abstract
- When face images are occluded it becomes difficult or impossible to make a correct recognition based on only the non-occluded parts. With asymmetrical Principal Component Analysis (aPCA) it is possible to estimate occluded regions based on the content of the non-occluded pixels. Entire faces can be reconstructed from images where some parts are occluded with the occluded region being estimated based on the relation to the non-occluded region. We show the result with 3 different occlusion cases and compare two reconstruction methods. The results are measured both objectively and subjectively and it is shown that a clear and sharp image part should be used even if the resulting image have edges in it.
|
|
| 4. |
- Andersson, Erik, et al.
(författare)
-
Ambio fit for the 2020s
- 2022
-
Ingår i: Ambio. - : Springer Nature. - 0044-7447 .- 1654-7209. ; 51:5, s. 1091-1093
-
Tidskriftsartikel (refereegranskat)
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Darvish, A. M., et al.
(författare)
-
Super-resolution facial images from single input images based on discrete wavelet transform
- 2014
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 9781479952083 ; , s. 843-848
-
Konferensbidrag (refereegranskat)abstract
- In this work, we are presenting a technique that allows for accurate estimation of frequencies in higher dimensions than the original image content. This technique uses asymmetrical Principal Component Analysis together with Discrete Wavelet Transform (aPCA-DWT). For example, high quality content can be generated from low quality cameras since the necessary frequencies can be estimated through reliable methods. Within our research, we build models for interpreting facial images where super-resolution versions of human faces can be created. We have worked on several different experiments, extracting the frequency content in order to create models with aPCA-DWT. The results are presented along with experiments of deblurring and zooming beyond the original image resolution. For example, when an image is enlarged 16 times in decoding, the proposed technique outperforms interpolation with more than 7 dB on average.
|
|
| 10. |
- Khan, Muhammad Sikandar Lal, 1988-, et al.
(författare)
-
Face-off : A face reconstruction technique for virtual reality (VR) scenarios
- 2016
-
Ingår i: 14th European Conference on Computer Vision, ECCV 2016. - Cham : Springer. - 9783319466033 - 9783319466040 ; , s. 490-503
-
Konferensbidrag (refereegranskat)abstract
- Virtual Reality (VR) headsets occlude a significant portion of human face. The real human face is required in many VR applications, for example, video teleconferencing. This paper proposes a wearable camera setup-based solution to reconstruct the real face of a person wearing VR headset. Our solution lies in the core of asymmetrical principal component analysis (aPCA). A user-specific training model is built using aPCA with full face, lips and eye region information. During testing phase, lower face region and partial eye information is used to reconstruct the wearer face. Online testing session consists of two phases, (i) calibration phase and (ii) reconstruction phase. In former, a small calibration step is performed to align test information with training data, while the later uses half face information to reconstruct the full face using aPCAbased trained-data. The proposed approach is validated with qualitative and quantitative analysis.
|
|
| 11. |
- Kouma, Jean-Paul, et al.
(författare)
-
Wyner-Ziv Video Coding using Hadamard Transform and Deep Learning
- 2016
-
Ingår i: International Journal of Advanced Computer Sciences and Applications. - 2158-107X .- 2156-5570. ; 7:7, s. 582-589
-
Tidskriftsartikel (refereegranskat)abstract
- Predictive schemes are current standards of video coding. Unfortunately they do not apply well for lightweight devices such as mobile phones. The high encoding complexity is the bottleneck of the Quality of Experience (QoE) of a video conversation between mobile phones. A considerable amount of research has been conducted towards tackling that bottleneck. Most of the schemes use the so-called Wyner-Ziv Video Coding Paradigm, with results still not comparable to those of predictive coding. This paper shows a novel approach for Wyner-Ziv video compression. It is based on the Reinforcement Learning and Hadamard Transform. Our Scheme shows very promising results.
|
|
| 12. |
- Li, Bo, 1982-, et al.
(författare)
-
Distinctive curve features
- 2016
-
Ingår i: Electronics Letters. - : John Wiley & Sons. - 0013-5194 .- 1350-911X. ; 52:3, s. 197-198
-
Tidskriftsartikel (refereegranskat)abstract
- Curves and lines are geometrical, abstract features of an image. Whereas interest points are more limited, curves and lines provide much more information of the image structure. However, the research done in curve and line detection is very fragmented. The concept of scale space is not yet fused very well into curve and line detection. Keypoint (e.g. SIFT, SURF, ORB) is a successful concept which represent features (e.g. blob, corner etc.) in scale space. Stimulated by the keypoint concept, a method which extracts distinctive curves (DICU) in scale space, including lines as a special form of curve features is proposed. A curve feature can be represented by three keypoints (two end points, and one middle point). A good way to test the quality of detected curves is to analyse the repeatability under various image transformations. DICU using the standard Oxford benchmark is evaluated. The overlap error is calculated by averaging the overlap error of three keypoints on the curve. Experiment results show that DICU achieves good repeatability comparing with other state-of-the-art methods. To match curve features, a relatively uncomplicated way is to combine local descriptors of three keypoints on each curve.
|
|
| 13. |
- Li, Bo, 1982-, et al.
(författare)
-
Distinctive curves : unified scale-invariant detection of edges, corners, lines and curves
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- This paper aims to broaden the scope of shape related features including edges, corners, lines and curves: 1) Edges, corners, lines, curves are all shape related features. In the past, the detection of each type of feature is usually solved independently under certain hypotheses. Our proposed distinctive curve detection method (DICU) solves the detection of all these type of features together. 2) Compared to the development in scale-invariant interest point detectors which have adopted more objective robustness measures using repeatability score, the research in line and curve features is still limited to “true/false positive” measures. DICU detection utilizes the scale-space concept and proves that curve features can be as robust as scale-invariant interest points. DICU has three advantages: 1) DICU outputs multi-type features which can benefit future computer vision applications. At the same time, the computational efficiency is unaffected, after detecting edges, only 5% additional computation is needed to detect corners, lines, and curves. 2) It is robust under various image perturbations and transformations and outperforms state-of-the-art interest point detectors and line detectors. At the same time, all types of detected features are robust. 3) Curve features contains more geometric information than points. Our curve matching test shows that curve matching can outperform interest point matching.
|
|
| 14. |
- Li, Bo, 1982-, et al.
(författare)
-
Fast edge detection by center of mass
- 2013
-
Ingår i: The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013). - Kitakyushu, Japan : The Institute of Industrial Applications Engineers. ; , s. 103-110
-
Konferensbidrag (refereegranskat)abstract
- In this paper, a novel edge detection method that computes image gradient using the concept of Center of Mass (COM) is presented. The algorithm runs with a constant number of operations per pixel independently from its scale by using integral image. Compared with the conventional convolutional edge detector such as Sobel edge detector, the proposed method performs faster when region size is larger than 9×9. The proposed method can be used as framework for multi-scale edge detectors when the goal is to achieve fast performance. Experimental results show that edge detection by COM is competent with Canny edge detection.
|
|
| 15. |
- Li, Bo, 1982-, et al.
(författare)
-
Fast edge filter and multi-scale edge detection
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- The first step of efficient edge detection is to use a filter to detect intensity change. The filter size is a parameter which affects the edge detection result. A filter of large size is less sensitive to noise while a filter of small size is more accurate when locating edges. This gives the user a choice of choosing the proper filter size depending on the situation. A more stable edge detection approach is multi-scale edge detection, which detects gradients using several filter sizes. The time consumption of a conventional edge filter is usually or , where w is the width of the filter. Therefore, using filters of large size or multi-scale filters is not very efficient. We propose an efficient edge detection method with time consumption. It uses the center of mass concept and utilizes the power of integral images to achieve this efficiency. The results of our experiments show that the proposed edge detector is very stable and we also propose a simplified multi-scale edge detection scheme which can be used in practical operations.
|
|
| 16. |
- Li, Bo, 1982-, et al.
(författare)
-
Independent Thresholds on Multi-scale Gradient Images
- 2013
-
Ingår i: The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013). - Kitakyushu, Japan : The Institute of Industrial Applications Engineers. ; , s. 124-131
-
Konferensbidrag (refereegranskat)abstract
- In this paper we propose a multi-scale edge detection algorithm based on proportional scale summing. Our analysis shows that proportional scale summing successfully improves edge detection rate by applying independent thresholds on multi-scale gradient images. The proposed method improves edge detection and localization by summing gradient images with a proportional parameter cn (c < 1); which ensures that the detected edges are as close as possible to the fine scale. We employ non-maxima suppression and thinning step similar to Canny edge detection framework on the summed gradient images. The proposed method can detect edges successfully and experimental results show that it leads to better edge detection performance than Canny edge detector and scale multiplication edge detector.
|
|
| 17. |
- Li, Bo, 1982-
(författare)
-
Interest Curves : Concept, Evaluation, Implementation and Applications
- 2015
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Image features play important roles in a wide range of computer vision applications, such as image registration, 3D reconstruction, object detection and video understanding. These image features include edges, contours, corners, regions, lines, curves, interest points, etc. However, the research is fragmented in these areas, especially when it comes to line and curve detection. In this thesis, we aim to discover, integrate, evaluate and summarize past research as well as our contributions in the area of image features. This thesis provides a comprehensive framework of concept, evaluation, implementation, and applications for image features.Firstly, this thesis proposes a novel concept of interest curves. Interest curves is a concept derived and extended from interest points. Interest curves are significant lines and arcs in an image that are repeatable under various image transformations. Interest curves bring clear guidelines and structures for future curve and line detection algorithms and related applications.Secondly, this thesis presents an evaluation framework for detecting and describing interest curves. The evaluation framework provides a new paradigm for comparing the performance of state-of-the-art line and curve detectors under image perturbations and transformations.Thirdly, this thesis proposes an interest curve detector (Distinctive Curves, DICU), which unifies the detection of edges, corners, lines and curves. DICU represents our state-of-the-art contribution in the areas concerning the detection of edges, corners, curves and lines. Our research efforts cover the most important attributes required by these features with respect to robustness and efficiency.Interest curves preserve richer geometric information than interest points. This advantage gives new ways of solving computer vision problems. We propose a simple description method for curve matching applications. We have found that our proposed interest curve descriptor outperforms all state-of-the-art interest point descriptors (SIFT, SURF, BRISK, ORB, FREAK). Furthermore, in our research we design a novel object detection algorithm that only utilizes DICU geometries without using local feature appearance. We organize image objects as curve chains and to detect an object, we search this curve chain in the target image using dynamic programming. The curve chain matching is scale and rotation-invariant as well as robust to image deformations. These properties have given us the possibility of resolving the rotation-variance problem in object detection applications. In our face detection experiments, the curve chain matching method proves to be scale and rotation-invariant and very computational efficient.
|
|
| 18. |
- Li, Bo, 1982-, et al.
(författare)
-
Restricted Hysteresis Reduce Redundancy in Edge Detection
- 2013
-
Ingår i: Journal of Signal and Information Processing. - 2159-4465 .- 2159-4481. ; 4:3B, s. 158-163
-
Tidskriftsartikel (refereegranskat)abstract
- In edge detection algorithms, there is a common redundancy problem, especially when the gradient direction is close to -135°, -45°, 45°, and 135°. Double edge effect appears on the edges around these directions. This is caused by the discrete calculation of non-maximum suppression. Many algorithms use edge points as feature for further task such as line extraction, curve detection, matching and recognition. Redundancy is a very important factor of algorithm speed and accuracy. We find that most edge detection algorithms have redundancy of 50% in the worst case and 0% in the best case depending on the edge direction distribution. The common redundancy rate on natural images is approximately between 15% and 20%. Based on Canny’s framework, we propose a restriction in the hysteresis step. Our experiment shows that proposed restricted hysteresis reduce the redundancy successfully.
|
|
| 19. |
- Li, Bo, 1982-, et al.
(författare)
-
Scale-invariant corner keypoints
- 2014
-
Ingår i: 2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP). - : IEEE conference proceedings. - 9781479957514 ; , s. 5741-5745
-
Konferensbidrag (refereegranskat)abstract
- Effective and efficient generation of keypoints from images is the first step of many computer vision applications, such as object matching. The last decade presented us with an arms race toward faster and more robust keypoint detection, feature description and matching. This resulted in several new algorithms, for example Scale Invariant Features Transform (SIFT), Speed-up Robust Feature (SURF), Oriented FAST and Rotated BRIEF (ORB) and Binary Robust Invariant Scalable Keypoints (BRISK). The keypoint detection has been improved using various techniques in most of these algorithms. However, in the search for faster computing, the accuracy of the algorithms is decreasing. In this paper, we present SICK (Scale-Invariant Corner Keypoints), which is a novel method for fast keypoint detection. Our experiment results show that SICK is faster to compute and more robust than recent state-of-the-art methods.
|
|
| 20. |
- Li, Bo, 1982-, et al.
(författare)
-
Scale-invariant corner keypoints
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Effective and efficient generation of keypoints from images is the first step of many computer vision applications, such as object matching. The last decade presented us with an arms race toward faster and more robust keypoint detection, feature description and matching. This resulted in several new algorithms, for example Scale Invariant Features Transform (SIFT), Speed-up Robust Feature (SURF), Oriented FAST and Rotated BRIEF (ORB) and Binary Robust Invariant Scalable Keypoints (BRISK). The keypoint detection has been improved using various techniques in most of these algorithms. However, in the search for faster computing, the accuracy of the algorithms is decreasing. In this paper, we present SICK (Scale-Invariant Corner Keypoints), which is a novel method for fast keypoint detection. Our experiment results show that SICK is faster to compute and more robust than recent state-of-the-art methods.
|
|
| 21. |
- Li, Bo, 1982-, et al.
(författare)
-
Scale & rotation-invariant matching with curve chain
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a new methodology that matches image geometry using a curve chain. A curve chain is defined as a 1-dimensional arrangement of curves. The idea is to match images without using local descriptors and apply this concept into applications. This paper have two contributions. First, we present a novel curve feature which is scale & rotation – invariant. Secondly, we present an efficient scale & rotational-invariant matching method which matches curve chains in the scene. The efficacy is benefited by three factors. Firstly, matching a 1-dimensional curve chain can achieve quadratic operations when dynamic programming is used. Secondly, curves are salient features that naturally reduce the dimensionality compared with scanning all possible locations. Thirdly, curves provide stable relational cues between neighbouring curves. Such stable relational cues reduce the computation to linear operations by avoiding searching all combinations of curves in dynamic programming. The advantages of the method has good potential to benefit application including point correspondence matching, object detection, etc. In point correspondence experiments our method yields a good total matching score on various image transformations. At the same time, the proposed method shows good potential of matching non-rigid object such as faces with scale & rotation invariance.
|
|
| 22. |
- Malhotra, Aman, et al.
(författare)
-
Fixed camera drone based photogrammetry for indoor mapping
- 2022
-
Ingår i: 9th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering, UPCON 2022. - : Institute of Electrical and Electronics Engineers (IEEE). - 9798350332506
-
Konferensbidrag (refereegranskat)abstract
- Point cloud data is a way of implementing and recreating the surrounding with the help of 3D imaging and rendering. These point clouds can be further converted into mesh and then 3d models that can be used for localisation and mapping. LIDAR (Light Detection and Ranging) is a common device that is used when we want to reconstruct a space(room or building) in a software 3D Mesh however LIDAR based systems are expensive and can be tricky to stitch and reconstruct, the proposed system uses a single camera, this single camera is going to capture the frame in a continuous manner. This frame capturing will be followed by feature extraction which is essentially going to help in comparing the motion of the camera by comparing the transformation of the frames relative to the previous frame. This process when implemented over a continuous frame path is going to help us build a 3D Space with the help of a process called photogrammetry. This can then be used in spatial planning or areas where the possibility of using lidar is not possible or the cost is too high for implementation. The estimated size from the sensor usually only differs a few centimeters from manually measured sizes. From 24 images the drone can generate more than 12000 feature points for photogrammetry and a point cloud with almost 10000 points for a room with a lot of features.
|
|
| 23. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
Cookies and Trust : Trust in organizations and the design of cookie consent prompts
- 2023
-
Ingår i: ECCE '23. - New York, NY : ACM Digital Library. - 9798400708756
-
Konferensbidrag (refereegranskat)abstract
- The General Data Protection Regulation (GDPR) was passed in 2016 to regulate companies’ use and storage of personal data, such as cookies, which are a common feature of the modern internet used to track user’s activity and preferences. This paper aims to examine people’s perspectives on cookie consent prompts and the effects of using deceptive design in cookie consent prompts.The results suggest that the design, rather than trust in the website’s organization, is crucial for users’ decisions to accept, decline, or manage cookies. Honest design is emphasized, and the dangers of deceptive design in cookie consent prompts are highlighted. Prompts that require full attention from the user and cover the content of the page are more likely to result in reflective and active decisions, but design friction that forces users to make a reflective choice causes irritation. The study also reveals a discrepancy between self-reported and observed behavior regarding cookie acceptance, as users tend to accept more cookies than they say they do.
|
|
| 24. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
Creative Capabilities of Machine Learning : Evaluating music created by algorithms
- 2021
-
Ingår i: ACM International Conference Proceeding Series. - New York, NY, USA : Association for Computing Machinery (ACM). - 9781450387576
-
Konferensbidrag (refereegranskat)abstract
- The concept of creativity is an important part of human society and the continuous evolution of artificial minds has raised questions on creativity among machines. This aim of the this study is to explore machine learning algorithms' ability to be creative. The study reported in this paper uses short samples of music generated by IBM Watson beats that are evaluated using expert assessment of 51 music teachers together with samples generated by humans as control samples. The results show that one of the machine learning generated samples showed the same level of creativity as the human generated samples. Hence, there are indications that today machine learning algorithms can create music that is hard to distinguish from human created music and can be considered creative.
|
|
| 25. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
Deceptive design : cookie consent and manipulative patterns
- 2021
-
Ingår i: 34th Bled eConference: Digital Support from Crisis to Progressive Change. - Maribor, Slovenia : University of Maribor Press. - 9789612864859 ; , s. 397-408
-
Konferensbidrag (refereegranskat)abstract
- As a larger proportion of our lives moves onto the web, so does important and valuable information. This has led to an increase in different kinds of manipulative patterns (dark patterns) in web design with the sole purpose of being deceptive and tricking users. This paper discusses the comprehensive suite of deceptive design patterns on Internet services where the users are expected to comply with the use of cookies. This was done by analyzing 50 different home cooking recipe websites, regarding their appliance to GDPR and how they use different dark patterns in their design. Even though legislation tries tomove the choices from the website to the user, it is clear that by using deceptive design patterns it is possible to "bypass" the legislation and trick the user into making a favorable choice for the owners behind the website. The results show that out of the websites that were GDPR approved, a majority still use two types of deceptive design patterns - misdirection and sneak into basket.
|
|
| 26. |
- Mejtoft, Thomas, Universitetslektor, et al.
(författare)
-
Design Friction : How intentionally added friction affect users level of satisfaction
- 2019
-
Ingår i: ECCE 2019. - New York, NY : ACM Press. - 9781450371667 ; , s. 41-44
-
Konferensbidrag (refereegranskat)abstract
- This study evaluates if intentionally added design friction affects users level of satisfaction when using a mobile application. Today most applications are designed to have as little friction as possible. An interesting question is if a more mindful interaction will lead to more satisfied users. In this study two prototypes inspired by the Headspace application where tested. One prototype had added design friction and the other had none. The participants were asked to rate their experience and to choose which prototype they preferred. The result shows that most participants of the test would choose the mobile application with added design friction and that they felt more satisfied when they had a clear understanding of the goal of the task.
|
|
| 27. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
Design friction and digital nudging : impact on the human decision-making process
- 2023
-
Ingår i: IVSP '23. - New York : Association for Computing Machinery (ACM). - 9781450398381 ; , s. 183-190
-
Konferensbidrag (refereegranskat)abstract
- People make a vast number of decisions every day and these decisions invoke either a reflective or automatic behavior. Using e.g., nudging to influence a person’s behavior in a positive direction can have beneficial sustainable effects. This study aims to illustrate how digital nudging and design friction can be used to induce a reflective behavior in users of digital services during their decision-making. The field of study is the user’s reflection regarding sustainable choices when ordering meals online. The results provided from this initial case study showed that the participants preferred prototypes with implemented design approaches of digital nudging and design friction over a neutral prototype. Nudging had great impact on the decision-making process and provided feelings such as guilt if the participants did not select the option with the lowest carbon footprint. The design approach also induced a reflective behavior among the participants. Introducing so-called design friction provided a reflective behavior but had no impact on the participants decisions. Results also showed that even detailed information in the neutral prototype provided an informative and reflective behavior, which in some of the cases had an impact on the participants’ decisions.
|
|
| 28. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
Designing call to action : users' perception of different characteristics
- 2021
-
Ingår i: 34th Bled econference: digital support from crisis to progressive change. - Maribor : University of Maribor University Press. - 9789612864859 ; , s. 405-416
-
Konferensbidrag (refereegranskat)abstract
- This paper aims to provide guidance when designing acall to action in a digital system with the purpose to create anintended feeling and user engagement. The paper is based on a test of four different simple call to action constructions. The users clearly prefer constructions that have a high explainability and feels intuitive. Hence, the design should have a high level of transparency and show the user straight away what it demands from the user and what the result of the action is. Furthermore, the design should have a high usability to make it clear how touse the call to action.
|
|
| 29. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
Enhancing digital social interaction using augmented reality in mobile fitness applications
- 2023
-
Ingår i: IVSP '23. - : ACM Digital Library. - 9781450398381 ; , s. 95-100
-
Konferensbidrag (refereegranskat)abstract
- The recent global pandemic has had great impact on our society, were restricted physical social interaction created changes that will have long-lasting effects on how certain activities are performed. One example is how the restrictive use of training facilities has impacted people's motivation of working out. Training online, through e.g., social media, increased during this time and many new apps for this purpose were launched. One way of differentiating in this landscape is the use of augmented reality. This paper investigates how augmented reality can be used in mobile fitness apps to improve the digital social interaction when working out. The study is based on prototyping and testing of a conceptual app and the results show the potential of augmented reality to improve social interaction in this context.
|
|
| 30. |
- Mejtoft, Thomas, 1976-, et al.
(författare)
-
Feedback in commercial educational applications : Guidelines and conceptual framework
- 2017
-
Ingår i: Proceedings of the European Conference on Cognitive Ergonomics 2017 (ECCE 2017). - New York, NY, USA : ACM Digital Library. - 9781450352567 ; , s. 113-120
-
Konferensbidrag (refereegranskat)abstract
- In recent years, schools made large investments to increase the integration and use of contemporary technologies in teaching and learning.Today iPads and educational applications are growing in popularity and are commonly used. These technologies have a potential beneficial effect on the learning, but studies show that some applications have flaws that hinder these positive effects, for example regarding the feedback provided to the user. This study has determined a number of guidelines for effective feedback in a learning situation and has further shown how well these guidelines can be reached in an educational application today. The study shows that there are both advantages and disadvantages of feedback in an application compared to giving feedback in a more traditional learning situation. Many of the guidelines for effective feedback were found to be possible to reach in an application, and the greatest advantage found in applications is that they can provide feedback timely on each action taken by the pupils.
|
|
| 31. |
- Mejtoft, Thomas, 1976-, et al.
(författare)
-
Intressentfokuserade oberoende longitudinella utvärderingar
- 2018
-
Ingår i: Proceedings från 6:e Utvecklingskonferensen för Sveriges ingenjörsutbildningar. - Göteborg : Chalmers tekniska högskola. - 9789188041111 ; , s. 94-96
-
Konferensbidrag (refereegranskat)abstract
- Utbildningskvalité är en mycket viktig fråga som diskuteras frekvent inom universitetsvärlden. Såväl kontroll som förbättring av utbildningskvalité är i många lägen starkt kopplat till olika former av utvärderingar. Denna artikel syftar till att illustrera och analysera en utvärderingsmodell som har använts på ett civilingenjörsprogram vid Umeå universitet. Målsättningen med utvärderingsmodellen är att skapa mer holistiska utvärderingar med ett starkare fokus på de intressenter som finns för kvalitetsutveckling - studenter och lärare.
|
|
| 32. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
Reclaiming control over personal data with blockchain technology : An exploratory study
- 2019
-
Ingår i: 32nd Bled eConference: Humanizing Technology for a Sustainable Society. - Maribor, Slovenia : University of Maribor Press. - 9789612862800 ; , s. 411-425
-
Konferensbidrag (refereegranskat)abstract
- With the digitalization and increasing number of Internet users,more and more personal data breaches occur. Many people are not awareof their personal data rights and have not received any instructions on howto act in situations such as when their personal data is abused. This issomething that illustrates the flaws of the Internet. A technology thatprovides solutions to some of these problems, such as trust andtransparency, is the blockchain technology. Hence, the objective of thispaper is to investigate knowledge about personal data rights and to explorethe design of a prototype of a blockchain application for increased securityand transparency. User tests were conducted, highlighting the greatestneeds for users to feel secure and in control over their personal data. Thisknowledge provide the foundation for a prototype based on blockchaintechnology that gives the users increased security and forces those whostore personal data to be more transparent with the usage.
|
|
| 33. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
The effect of skeleton screens : Users’ perception of speed and ease of navigation
- 2018
-
Ingår i: Proceedings of the 36th European Conference on Cognitive Ergonomics. - New York, NY : ACM Press. - 9781450364492
-
Konferensbidrag (refereegranskat)abstract
- Progression bars and spinners have long been the norm when providing feedback during wait times on the web. However, a more recent trend is the use of skeleton screens. This paper aims to evaluate the usefulness of skeleton screens as an alternative to spinners. This is done user testing a fictional news site with two variations, one showing skeleton screens before content is loaded, and another utilizing spinners. Both a questionnaire and measuring timing while finding a specified article when entering a website for the first time was used. The results show that the page using skeleton screens, scored higher on average on both perceived speed and ease of navigation. However, people using the page with spinners were faster at finding the article when entering the site for the first time. The results of this paper cannot show any significant differences in any of the comparisons between the web pages.
|
|
| 34. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
The user experience of personalized content
- 2020
-
Ingår i: 33rd Bled eConference - Enabling Technology for a Sustainable Society. - Maribor, Slovenia : University of Maribor University Press. - 9789612863623 ; , s. 147-158
-
Konferensbidrag (refereegranskat)abstract
- Content in digital services is often filtered for users based on individual preferences with the possible consequence of creating a state referred to as a “filter bubble”. The objective of this paper is to examine which of a user’s inherent needs that are important to satisfy when a user is consuming personalized content in a digital service. The paper uses a survey to measure the need for autonomy, competence and relatedness of the Self-Determination Theory when users are consuming filtered content in digital services. The results show that the investigated services fail to satisfy all needs. A satisfactory user experience should include the opportunity for the user to satisfy the need for autonomy, competence and relatedness. For autonomy, transparency of filtering and choice about filtering should be offered. For competence, it is essential to offer content that the user can learn from, and also provide the right amount of choice throughout the service. The danger of filter bubbles is not personalization, but to remove choice about personalization.
|
|
| 35. |
- Mejtoft, Thomas, 1976-, et al.
(författare)
-
Use of Image Recognition of Social Media
- 2017
-
Ingår i: ANZMAC 2017: Marketing for Impact. - Melbourne : RMIT University. ; , s. 271-278
-
Konferensbidrag (refereegranskat)abstract
- Images are central to firms in their use of social media platforms as part of their marketing strategy. Images are a powerful online marketing tool as they allow for engagement and personalisation of marketing content for individual customers. However, images can be a double edge sword in the web 2.0 world, where consumers are able to post content to branded social media sites. This study evaluates the benefits of integrating image recognition into social media from the users perspective. The pilot study undertaken found the majority of the participants thought the possibilities presented for image recognition technology are useful, however they showed concern in relation to their privacy if this technology were to be in social media networks. The results also showed that prior familiarity with this technology does not have any significant impact in how social media users feel about having this technology in social media.
|
|
| 36. |
- Mejtoft, Thomas, Universitetslektor, 1976-, et al.
(författare)
-
User experience design and digital nudging in a decision making process
- 2019
-
Ingår i: 32nd Bled eConference: Humanizing Technology for a Sustainable Societ. - Maribor, Slovenia : University of Maribor Press. - 9789612862800 ; , s. 427-442
-
Konferensbidrag (refereegranskat)abstract
- When using online nudges to steer people in the right directionwhile they are making a decision, there is usually one preferable outcome.What might happen if the user experience is inadequate, will the nudgesstill work or might they be undermined? In this paper we investigate thecorrelation between user experience and digital nudges in a decisionmaking process. A user A/B test was conducted to investigate theproblem. The test participants visited one of two websites that includedthe same nudges where they were nudged to choose option (a) instead of(b). The only difference in the websites was the quality of the userexperience, one website design had a good user experience while the otherone offered an inadequate user experience. The results showed thateveryone who was assigned the good user experience chose (a), while twoof the inadequate experience participants chose (b). The results indicatethat user experience design can be used for digital nudging.
|
|
| 37. |
- Mårell-Olsson, Eva, 1966-, et al.
(författare)
-
Opportunities and challenges of using socially intelligent agents : increasing interaction and school participation for children suffering from a long-term illness
- 2021
-
Ingår i: The international journal of information and learning technology. - : Emerald Group Publishing Limited. - 2056-4880 .- 2056-4899. ; 38:4, s. 393-411
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose – Children suffering from cancer or cardiovascular disease, who need extended periods of treatment in hospitals, are subjected to multiple hardships apart from the physical implications, for example, experienced isolation and disrupted social and academic development. This has negative effects long after the child’s recovery from the illness. The purpose of this paper is to examine the non-medical needs of children suffering from a long-term illness, as well as research the field of artificial intelligence (AI) – more specifically, the use of socially intelligent agents (SIAs) – in order to study how technology can enhance children’s interaction, participation and quality of life. Design/methodology/approach – Interviews were performed with experts in three fields: housing manager for hospitalized children, a professor in computing science and researcher in AI, and an engineer and developer at a tech company.Findings – It is important for children to be able to take control of the narrative by using an SIA to support the documentation of their period of illness, for example. This could serve as a way of processing emotions, documenting educational development or keeping a reference for later in life. The findings also show that the societal benefits of AI include automating mundane tasks and recognizing patterns. Originality/value – The originality of this study concerns the holistic approach of increasing the knowledge and understanding of these children’s specific needs and challenges, particularly regarding their participation and interaction with teachers and friends at school, using an SIA.
|
|
| 38. |
- Pordel, Mostafa, 1982-
(författare)
-
Object Classification and Image Labeling using RGB-Depth Information
- 2013
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis is part of research for the vision systems of four robots in the EU funded project, CROPS[l], where the robots should harvest apples, sweet peppers and grapes, and explore forests. The whole process of designing such a system, including the software architecture, creation of the image database, image labeling and object detection, is presented.The software architecture chapter of this thesis provides a review of some of the latest frameworks for robotics. It describes the structure of robetics components and the communication systems between them. The vision system is a subsystem of the robetics architecture studied in conjunction with other components of the robetics system. To build a vision system, three main steps should be taken. First a collection of images that are similar to what the robots are expected to meet should be created. Second, all the images should be labeled manually or automatically. Finally, learning systems should use the labeled images to build object medels. Details about these steps make up the majority of the content in this thesis. With new widely available low-cost sensors such as Microsoft Kinect, it is possible to use depth imagesalong with RGB images to increase the performance of vision systems. We particularly focus on various methods that integrate depth information in the three steps that are mentioned for building a vision system. More specifically, the image labeling tools help to extract objects in images to be used as ground truth for learning and testing processes in object detection. The inputs for such tools are usually RGB images. Despite the existence of many powerful tools for image labeling, there is still a need for RGB-Depth adapted tools. We present a new interactive labeling tool that partially automates image labeling, with two major contributions. First, the method extends the concept of image segmentatian from RGB to RGB-Depth. Second, it minimizes the interadion time needed for object extraction by using a highly efficient segmentatian method in RGB-Depth space. The ent~re procedure requires very few elieks campared to other already existing tools. In fact, when the desired object is the dosest object to the camera, as is the case in our forestry application, no click is required to extract the object. Finally, while we present state of the art in object detection with 2D environments, object detection using RGB-depth information is mainly addressed for future work.
|
|
| 39. |
-
Proceedings of the 16th Student Conference in Interaction Technology and Design and the 5th Student Conference in Electronics and Mechatronics
- 2019
-
Proceedings (redaktörskap) (refereegranskat)abstract
- The joint Student Conference in Interaction Technology and Design and Student Conference in Electronics and Mechatronics is the annual grand finale of the courses Current Topic in Interaction Technology and Design and Student Conference in Electronics and Mechatronics at the Department of Applied Physics and Electronics, Umeå University. The idea and objective of the two courses are to give the students a forum where they can actively participate in scientific research and development through their own ideas and interests. The course introduces students to independently researching an interesting topic, using a foreign language orally and in writing, writing a scientific article, peer-review and presenting their work at a conference. The conference format was chosen to provide a realistic environment for the presentation of the results. The work has been reviewed both by other participant on the course and members of the department. If the reviews are favorable, the paper is accepted as a full paper at the conference and included in the proceedings. Research that has an interesting topic and potential for future publication is presented as work-in-progress at the conference and the abstract is included in the conference proceedings. This year 10 full papers and 2 work-in-progress papers were accepted at the conference and all included in this proceedings as full papers and extended abstracts, respectively.
|
|
| 40. |
-
Proceedings of the 18th Student Conference in Interaction Technology and Design and the 6th Student Conference in Electronics and Mechatronics
- 2020
-
Proceedings (redaktörskap) (övrigt vetenskapligt/konstnärligt)abstract
- The joint Student Conference in Interaction Technology and Design and Student Conference in Electronics and Mechatronics is the annual grand finale of the courses Current Topic in Interaction Technology and Design and Student Conference in Electronics and Mechatronics at the Department of Applied Physics and Electronics, Umeå University. The idea and objective of the two courses are to give the students a forum, where they can actively participate in scientific research and development through their own ideas and interests. The course introduces students to independently finding and researching a topic of interest for them, using a foreign language orally and in writing, writing a scientific article, peer-reviewing and presenting their work at a conference. The conference format was chosen to provide a realistic environment for the presentation of the results. The work has been reviewed both by other participant on the course and members of the department. If the reviews are favorable, the paper is accepted as a full paper at the conference and included in the proceedings.
|
|
| 41. |
-
Proceedings of the 19th Student Conference in Interaction Technology and Design
- 2020
-
Proceedings (redaktörskap) (övrigt vetenskapligt/konstnärligt)abstract
- The Student Conference in Interaction Technology and Design is the annual grand finale of the course Current Topic in Interaction Technology and Design at the Department of Applied Physics and Electronics, Umeå University. The idea and objective of the course are to give the students a forum, where they can actively participate in scientific research and development through their own ideas and interests. The course introduces students to independently finding and researching a topic of interest for them, writing a scientific article, peer-reviewing, and presenting their work at a conference. The course is conducted in English both in writing and orally, and it is a foreign language for most of the students. The conference format is chosen to provide a realistic environment for the presentation of the results. The work of each student has been reviewed both by other participants on the course and members of the department. If the reviews are favorable, the paper is accepted as a full paper at the conference and included in the proceedings.
|
|
| 42. |
-
Proceedings of the 21st Student Conference in Interaction Technology and Design
- 2021
-
Proceedings (redaktörskap) (refereegranskat)abstract
- The Student Conference in Interaction Technology and Design is the annual grand finale of the course Current Topic in Interaction Technology and Design at the Department of Applied Physics and Electronics, Umeå University, Sweden. The main objective of the course is to give the participants a forum, where they can actively discuss scientific research and development through the implementation of their own ideas and interests. The course introduces students to independently finding and researching a topic of interest for them, finding related sources of information and related research publications, writing a scientific article, peer-reviewing, and presenting their work at a conference. The course is conducted in English which is a foreign language for most of the students. The final examination format is chosen as a conference to provide a realistic environment for the presentation of the results. The work of each student has been reviewed by other participants on the course and members of the department acting not only as teachers and consultants but also as program committee members. If the reviews are favorable, the paper is accepted as a full paper at the conference and included in the proceedings.
|
|
| 43. |
- Rosenlind, Emma, et al.
(författare)
-
Young adults' attitude towards digital payment methods and financial responsibility
- 2023
-
Ingår i: 36th Bled eConference – digital economy and society. - Maribor : University of Maribor, University Press. - 9789612867515 ; , s. 393-405
-
Konferensbidrag (refereegranskat)abstract
- There are numerous online payment methods when shopping online. This paper presents the evolution of payment methods through the years and investigates which payment methods young adults prefer and investigates if and how modern payment methods affect financial responsibility among young adults. The study was conducted through a survey and follow-up interviews with Swedish young adults. 75% claimed they make online purchases 1-3 times a week or more, of which 35% always check their bank account before paying. The study suggests that direct payment using their smart device (Swish) is the most preferred payment method. The research suggests that it is the combination of the different payment methods available that is impacting financial responsibility among young adults rather than the payment method itself.
|
|
| 44. |
|
|
| 45. |
- Söderström, Ulrik, 1978-, et al.
(författare)
-
Anonymous video processing for live street view
- 2011
-
Ingår i: 2011 IEEE International Conferences on Internet of Things, and Cyber, Physical and Social Computing. - Los Alamitos : IEEE Computer Society. - 9781457719769 ; , s. 109-113
-
Konferensbidrag (refereegranskat)abstract
- We propose a method for hiding the identity of persons and objects in video sequences. This type of video sequence will be used in applications where the scene is important but the identity of persons should be unrecognizable, e.g., street view applications. Other parts, such as company logos, names on house doors or license plates on parked cars should not be recognizable as well. This is today solved in street view by blurring out parts of images that are compressed with standard encoding techniques. We propose a method that automatically will blur out parts that are moving but still show the motion. Our technique requires very low bitrates for video transmission; almost as low as for a still image. The low bitrate and the low computational complexity will enable video views of streets at the same costs as for still images.
|
|
| 46. |
|
|
| 47. |
- Söderström, Ulrik, 1978-, et al.
(författare)
-
Asymmetrical principal component analysis for video coding
- 2008
-
Ingår i: Electronics Letters. - : Institution of Engineering and Technology (IET). - 0013-5194 .- 1350-911X. ; 44:4, s. 276-277
-
Tidskriftsartikel (refereegranskat)abstract
- Principal component analysis (PCA) can be used to encode video sequences at extremely low bit rates, e.g. 34.6 dB (PSNR) at 4.2 kbit/s. The same eigenvectors are used for encoding and decoding for this coding. Introduced is a coding scheme where eigenvectors for only part of the video frames are used for encoding but the eigenvectors for the entire frame are used for decoding. This is called asymmetric PCA coding. This reduces the complexity of encoding by ap5 times and at the same time increases the reconstruction quality for the facial part of the video with 0.4 dB (PSNR).
|
|
| 48. |
- Söderström, Ulrik, 1978-, et al.
(författare)
-
Comparing millennials view on minimalism and maximalism in web design
- 2019
-
Ingår i: Proceedings of the 31st European Conference on Cognitive Ergonomics. - New York, NY : ACM Press. - 9781450371667 ; , s. 92-95
-
Konferensbidrag (refereegranskat)abstract
- This study evaluates how Generation Y, also known as millennials, perceive different web design approaches. Two web design approaches were compared, using methods in User Experience design. The first approach is minimalism and the second one is maximalism. Minimalism has been a recurring web design trend ever since the end of the twentieth century. Maximalism is claimed to be the most important web design trend of 2018. The interesting question is if millennials who have grown up with minimalism in web design are interested in a new approach – the maximal approach. This study probe the opinions, thoughts and emotions of millennials after they have browsed two websites, one developed with minimalism and one developed with maximalism. The results show that the participants in this study were more exited by the maximal design. However, combining quantitative and qualitative data, the conclusion is that the different design approaches are more or less suitable to use depending on the message that the website is supposed to convey.
|
|
| 49. |
- Söderström, Ulrik, 1978-, et al.
(författare)
-
Customizing Lip Video into Animation for Wireless Emotional Communication
- 2004
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Universal Multimedia Access (UMA) engines are used to adapt the media content to suite different environments.The adaptation decision for content used over wireless networks is heavily dependent on the bandwidth needs since the transmission cost over wireless networks is high. We customize lip video into lip animations and through tests we challenge the assumption that the quality is reduced when the transmission cost is reduced. We show that animations are comparable with video when considering human emotion understanding and comparable with audio only when considering transmission cost. We argue that it is important to consider human cognitive and perceptive factors in the decision stage of a UMA engine. This can both improve the user’s perceived quality and lower the transmission cost.
|
|
| 50. |
|
|
