| 1. |
- Bacauskiene, Marija, et al.
(författare)
-
A feature selection technique for generation of classification committees and its application to categorization of laryngeal images
- 2009
-
Ingår i: Pattern Recognition. - New York : Pergamon Press. - 0031-3203 .- 1873-5142. ; 42:5, s. 645-654
-
Tidskriftsartikel (refereegranskat)abstract
- This paper is concerned with a two phase procedure to select salient features (variables) for classification committees. Both filter and wrapper approaches to feature selection are combined in this work. In the first phase, definitely redundant features are eliminated based on the paired t-test. The test compares the saliency of the candidate and the noise features. In the second phase, the genetic search is employed. The search integrates the steps of training, aggregation of committee members, selection of hyper-parameters, and selection of salient features into the same learning process. A small number of genetic iterations needed to find a solution is the characteristic feature of the genetic search procedure developed. The experimental tests performed on five real-world problems have shown that significant improvements in Classification accuracy can be obtained in a small number of iterations if compared to the case of using all the features available.
|
|
| 2. |
- Fierrez-Aguilar, Julian, et al.
(författare)
-
Discriminative multimodal biometric authentication based on quality measures
- 2005
-
Ingår i: Pattern Recognition. - Oxford : Pergamon Press. - 0031-3203 .- 1873-5142. ; 38:5, s. 777-779
-
Tidskriftsartikel (refereegranskat)abstract
- A novel score-level fusion strategy based on quality measures for multimodal biometric authentication is presented. In the proposed method, the fusion function is adapted every time an authentication claim is performed based on the estimated quality of the sensed biometric signals at this time. Experimental results combining written signatures and quality-labelled fingerprints are reported. The proposed scheme is shown to outperform significantly the fusion approach without considering quality signals. In particular, a relative improvement of approximately 20% is obtained on the publicly available MCYT bimodal database.
|
|
| 3. |
- Fouard, Céline, et al.
(författare)
-
Weighted distance transforms generalized to modules and their computation on point lattices
- 2007
-
Ingår i: Pattern Recognition. - : Elsevier BV. - 0031-3203 .- 1873-5142. ; 40:9, s. 2453-2474
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents the generalization of weighted distances to modules and their computation through the chamfer algorithm on general point lattices. The first part is dedicated to formalization of definitions and properties (distance, metric, norm) of weighted distances on modules. It resumes tools found in literature to express the weighted distance of any point of a module and to compute optimal weights in the general case to get rotation invariant distances. The second part of this paper proves that, for any point lattice, the sequential two-scan chamfer algorithm produces correct distance maps. Finally, the definitions and computation of weighted distances are applied to the face-centered cubic (FCC) and body-centered cubic (BCC) grids.
|
|
| 4. |
- Gelzinis, Adas, et al.
(författare)
-
Increasing the discrimination power of the co-occurrence matrix-based features
- 2007
-
Ingår i: Pattern Recognition. - Oxford : Pergamon Press. - 0031-3203 .- 1873-5142. ; 40:9, s. 2367-2372
-
Tidskriftsartikel (refereegranskat)abstract
- This paper is concerned with an approach to exploiting information available from the co-occurrence matrices computed for different distance parameter values. A polynomial of degree n is fitted to each of 14 Haralick's coefficients computed from the average co-occurrence matrices evaluated for several distance parameter values. Parameters of the polynomials constitute a set of new features. The experimental investigations performed substantiated the usefulness of the approach.
|
|
| 5. |
- Savas, Berkant, et al.
(författare)
-
Handwritten digit classification using higher order singular value decomposition
- 2007
-
Ingår i: Pattern Recognition. - : Elsevier BV. - 0031-3203 .- 1873-5142. ; 40:3, s. 993-1003
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper we present two algorithms for handwritten digit classification based on the higher order singular value decomposition (HOSVD). The first algorithm uses HOSVD for construction of the class models and achieves classification results with error rate lower than 6%. The second algorithm uses the HOSVD for tensor approximation simultaneously in two modes. Classification results for the second algorithm are almost down at 5% even though the approximation reduces the original training data with more than 98% before the construction of the class models. The actual classification in the test phase for both algorithms is conducted by solving a series least squares problems. Considering computational amount for the test presented the second algorithm is twice as efficient as the first one.
|
|
| 6. |
- Sternby, Jakob, et al.
(författare)
-
On-line Arabic handwriting recognition with templates
- 2009
-
Ingår i: Pattern Recognition. - : Elsevier BV. - 1873-5142 .- 0031-3203. ; 42:12, s. 3278-3286
-
Konferensbidrag (refereegranskat)abstract
- After a long period of focus on western and East Asian scripts there is now a general trend in the on-line handwriting recognition community to explore recognition of other scripts such as Arabic and various Indic scripts. One difficulty with the Arabic script is the number and position of diacritic marks associated to Arabic characters. This paper explores the application of a template matching scheme to the recognition of Arabic script with a novel algorithm for dynamically treating the diacritical marks. Template based systems are robust to conditions with scarce training data and in experiments the proposed system outperformed a reference system based on the promising state-of-the-art network technique of BLSTM. Experiments have been conducted in an environment similar to that of many handheld devices with promising results both in terms of memory consumption and response time. (C) 2009 Elsevier Ltd. All rights reserved.
|
|
| 7. |
- Uscka-Wehlou, Hanna, 1973-
(författare)
-
Run-hierarchical structure of digital lines with irrational slopes in terms of continued fractions and the Gauss map
- 2009
-
Ingår i: Pattern Recognition. - : Elsevier. - 0031-3203 .- 1873-5142. ; 42:10, s. 2247-2254
-
Tidskriftsartikel (refereegranskat)abstract
- We study relations between digital lines and continued fractions. The main result is a parsimonious description of the construction of the digital line based only on the elements of the continued fraction representing its slope and containing only simple integer computations. The description reflects the hierarchy of digitization runs, which raises the possibility of dividing digital lines into equivalence classes depending on the continued fraction expansions of their slopes. Our work is confined to irrational slopes since, to our knowledge,there exists no such description for these, in contrast to rational slopes which have been extensively examined. The description is exact (it does not use approximations by rationals). Examples of lines with irrational slopes and with very simple digitization patterns are presented. These include both slopes with periodic and non-periodic continued fraction expansions, i.e.\ both quadratic surds and other irrationals. We also derive the connection between the Gauss map and the digitization parameters introduced by the author in 2007.
|
|
| 8. |
- Damaschke, Peter, 1963, et al.
(författare)
-
Fast algorithms for finding disjoint subsequences with extremal densities
- 2006
-
Ingår i: Pattern Recognition. - : Elsevier BV. - 0031-3203. ; 39:12, s. 2281-2292
-
Tidskriftsartikel (refereegranskat)abstract
- We derive fast algorithms for the following problem: Given a set of n points on the real line and two parameters s and p, find s disjoint intervals of maximum total length that contain at most p of the given points. Our main contribution consists of algorithms whose time bounds improve upon a straightforward dynamic programming algorithm, in the relevant case that input size n is much bigger than parameters s and p. These results are achievedby selecting a few candidate intervals that are provably sufficient for building an optimal solution via dynamic programming. As a byproduct of this idea we improve an algorithm for a similar subsequence problem of Chen, Lu andTang (2005). The problems are motivated by the search for significant patterns in biological data. Finally we propose several heuristics that further reduce the time complexity in typical instances. One of them leads to an apparently open subsequence sum problem of independent interest.
|
|
| 9. |
- Yu, Donggang, et al.
(författare)
-
Recognition and analysis of cell nuclear phases for high-content screening based on morphological features
- 2009
-
Ingår i: NOVA. The University of Newcastle’s Digital Repository. - : Elsevier BV. - 0031-3203. ; 42:4, s. 498-508
-
Tidskriftsartikel (refereegranskat)abstract
- Automated analysis of molecular images has increasingly become an important research in computational life science. In this paper some new and efficient algorithms for recognizing and analyzing cell phases of high-content screening are presented. The conceptual frameworks are based on the morphological features of cell nuclei. The useful preprocessing includes: smooth following and linearization; extraction of morphological structural points; shape recognition based morphological structure; issue of touching cells for cell separation and reconstruction. Furthermore, the novel detecting and analyzing strategies of feed-forward and feed-back of cell phases are proposed based on gray feature, cell shape, geometrical features and difference information of corresponding neighbor frames. Experiment results tested the efficiency of the new method.
|
|
