Towards more discriminative features for texture recognition. (November 2020)

• Record Type: Journal Article
• Authors: Cerkezi, Llukman; Topal, Cihan
• Is Part Of: Pattern recognition. Volume 107(2020:Nov.)
• Publication Date: 2020-11
• Subjects: Local binary patterns -- Texture recognition -- Feature representations -- Feature optimization -- Deep texture features -- Mutual information; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107473
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a novel algorithm for extracting more discriminative 2D LBP features. The method optimizes projections of 2D LBP distribution on to the marginal histograms. Several statistical constraints are considered for optimization. Mutual Information constraint has shown the best performance among others. The method shows better performance up to 2.4% compared to conventional approach. Abstract: Local binary patterns (LBP) are considered to be one of the most computationally efficient descriptor that can also be combined jointly among different variants to increase accuracy. In this study, we propose a method to obtain more discriminative 2D LBP features by optimizing projections of a joint LBP distribution onto the marginal histograms. To find a more efficient representation of the feature vector, we seek the least redundant marginal histograms of a joint LBP distribution via optimizing several constraints. In this way, we aim to have a more compact yet accurate feature vector in contrast to the methods that flatten the joint distribution. Experiments we perform on five popular texture datasets show that the feature vectors optimized with the proposed method provide higher recognition rates with the same size vectors and comparable results even with lower dimensional vectors. We also compare the proposed algorithm to more recent texture recognition methods based on convolutional neural networks and show that it can still provide comparable results even though the resulting feature vectors are smaller by orders of magnitude.