Angled local directional pattern for texture analysis with an application to facial expression recognition. Issue 5 (26th February 2018)

• Record Type: Journal Article
• Authors: Shabat, Abuobayda M.M.; Tapamo, Jules‐Raymond
• Is Part Of: IET computer vision. Volume 12:Issue 5(2018)
• Page Start: 603
• Page End: 608
• Publication Date: 2018-02-26
• Subjects: face recognition -- image texture -- feature extraction -- support vector machines -- perceptrons -- decision trees -- emotion recognition; angled local directional pattern -- texture analysis -- facial expression recognition -- local binary pattern -- LBP -- feature extraction method -- random noise -- image intensity -- gradient space -- pixel intensity -- edge response value -- LDP method -- Kirsch Masks -- centre pixel value -- ALDP -- texture data set -- Kylberg -- KTHTIPS2b -- K-nearest neighbour algorithm -- support vector machine -- random forest -- perceptron -- Naive-Bayes -- decision tree -- Cohn-Kanade database -- facial expression emotion; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2017.0340
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Local binary pattern (LBP) is currently one of the most common feature extraction methods used for texture analysis. However, LBP suffers from random noise, because it depends on image intensity. Recently, a more stable feature method was introduced, local directional pattern (LDP) uses the gradient space instead of the pixel intensity. Typically, LDP generates a code based on the edge response values using Kirsch masks. Yet, despite the great achievement of LDP, it has two drawbacks. The first is the static choice of the number of most significant bits used for LDP code generation. Second, the original LDP method uses the 8‐neighborhood to compute the LDP code, and the value of the centre pixel is ignored. This study presents angled local directional pattern (ALDP), which is an improved version of LDP, for texture analysis. Experimental results on two different texture data sets, using six different classifiers, show that ALDP substantially outperforms both LDP and LBP methods. The ALDP has been evaluated to recognise the facial expressions emotion. Results indicate a very high recognition rate for the proposed method. An added advantage is that ALDP has an adaptive approach for the selection of the number significant bits as opposed to LDP.