Search

Abstract: Face recognition has been a long standing problem in computer vision. Recently, Histograms of Oriented Gradients (HOGs) have proven to be an effective descriptor for object recognition in general and face recognition in particular. In this paper, we investigate a simple but powerful approach to make robust use of HOG features for face recognition. The three main contributions of this work are: First, in order to compensate for errors in facial feature detection due to occlusions, pose and illumination changes, we propose to extract HOG descriptors from a regular grid. Second, fusion of HOG descriptors at different scales allows to capture important structure for face recognition. Third, we identify the necessity of performing dimensionality reduction to remove noise and make the classification process less prone to overfitting. This is particularly important if HOG features are extracted from overlapping cells. Finally, experimental results on four databases illustrate the benefits of our approach. [Copyright &y& Elsevier]

Abstract: The present paper considers the problem of partitioning a dataset into a known number of clusters using the sum of squared errors criterion (SSE). A new clustering method, called DE-KM, which combines differential evolution algorithm (DE) with the well known K-means procedure is described. In the method, the K-means algorithm is used to fine-tune each candidate solution obtained by mutation and crossover operators of DE. Additionally, a reordering procedure which allows the evolutionary algorithm to tackle the redundant representation problem is proposed. The performance of the DE-KM clustering method is compared to the performance of differential evolution, global K-means method, genetic K-means algorithm and two variants of the K-means algorithm. The experimental results show that if the number of clusters K is sufficiently large, DE-KM obtains solutions with lower SSE values than the other five algorithms. [Copyright &y& Elsevier]

Abstract: Among the SVM-based methods for multi-category classification, “1-a-r”, pairwise and DAGSVM are most widely used. The deficiency of “1-a-r” is long training time and unclassifiable region; the deficiency of pairwise and DAGSVM is the redundancy of sub-classifiers. We propose an uncertainty sampling-based multi-category SVM in this paper. In the new method, some necessary sub-classifiers instead of all N ×(N −1)/2 sub-classifiers are selected to be trained and the uncertainty sampling strategy is used to decide which samples should be selected in each training round. This uncertainty sampling-based method is proved to be accurate and efficient by experimental results on the benchmark data. [Copyright &y& Elsevier]

Abstract: In this paper a novel method to derive the Medial Axis of a shape is presented. The property that the Medial Axis is a subset of the Symmetry Set is used. The latter allows a formulation in terms of two equations, based on geometrical arguments. From the set that solves the equations, the subset that yields the Medial Axis can be taken. An algorithm is given that performs these tasks. The Medial Axis can easily be labelled with respect to main axis and branches, as this information follows directly from the Symmetry Set. [Copyright &y& Elsevier]

Vector quantization (VQ) is an asymmetric coding method and the winner search in encoding process is extremely time-consuming. This property of VQ constrains its practical applications very much. Based on the sum pyramid data structure of a vector, a fast encoding algorithm with PSNR equivalent to full search is proposed in this paper to improve the results that have been given in [Pattern Recognition Lett. 22(3/4) (2001) 373].Three major modifications are made. Because sum can be computed accurately using integer operation, mismatched winners due to roundoff error of taking the mean can be overcome firstly by using sum instead of the mean. Secondly, since sum is computed by 2-pixel-merging other than 4-pixel-merging way, more levels can be constructed in a sum pyramid so that the rejection to current codeword can be realized easier. Finally, codebook is off-line rearranged by sorted real sums directly, and the lower and upper bound for promising codeword class are updated dynamically to narrow search scope further once a better-matched codeword has been found during winner search process.For the same four 512 × 512, 256-level standard test images, experimental results show that the proposed algorithm outperforms the method used in [Pattern Recognition Lett. 22(3/4) (2001) 373] in the meaning of total equivalent distance computation being reduced obviously. [Copyright &y& Elsevier]