WLD: A Robust Local Image Descriptor

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 32; no. 9; pp. 1705 - 1720
• Main Authors: Chen, Jie, Shan, Shiguang, He, Chu, Zhao, Guoying, Pietikäinen, Matti, Chen, Xilin, Gao, Wen
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01-09-2010; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Computer science; control theory; systems; Exact sciences and technology; Excitation; Face detection; Face recognition; Histograms; Human; Humans; Illumination; Image edge detection; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image motion analysis; Image texture analysis; Imaging, Three-Dimensional - methods; local descriptor; Orientation; Pattern recognition; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Perception; Pixel; Pixels; Robustness; Subtraction Technique; Surface layer; Testing; Texture; Weber law; Human; local descriptor; Gabor filter; Histogram; Stimulus; Face recognition; face detection; Weber law; Autoregressive model; Regression analysis; Pattern recognition; Orientation; Texture; Lighting; Facies; Object detection; Database; Frontal; Sensorial perception; Pattern analysis; Artificial intelligence
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/TPAMI.2009.155

Inspired by Weber's Law, this paper proposes a simple, yet very powerful and robust local descriptor, called the Weber Local Descriptor (WLD). It is based on the fact that human perception of a pattern depends not only on the change of a stimulus (such as sound, lighting) but also on the original intensity of the stimulus. Specifically, WLD consists of two components: differential excitation and orientation. The differential excitation component is a function of the ratio between two terms: One is the relative intensity differences of a current pixel against its neighbors, the other is the intensity of the current pixel. The orientation component is the gradient orientation of the current pixel. For a given image, we use the two components to construct a concatenated WLD histogram. Experimental results on the Brodatz and KTH-TIPS2-a texture databases show that WLD impressively outperforms the other widely used descriptors (e.g., Gabor and SIFT). In addition, experimental results on human face detection also show a promising performance comparable to the best known results on the MIT+CMU frontal face test set, the AR face data set, and the CMU profile test set.