Bionic RSTN invariant feature extraction method for image recognition and its application. Issue 4 (1st April 2017)

• Record Type: Journal Article
• Authors: Yu, Lingli; Zhou, Kaijun; Yang, Yongliang; Chen, Haichu
• Is Part Of: IET image processing. Volume 11:Issue 4(2017)
• Page Start: 227
• Page End: 236
• Publication Date: 2017-04-01
• Subjects: edge detection -- feature extraction -- Gabor filters; image recognition -- bionic RSTN invariant feature extraction -- rotation‐scaling‐translation‐noise -- biological vision -- orientation edge detection -- filter‐to‐filter scheme -- Gabor filters -- bottom filter -- bipolar filters -- top filter -- horizontal direction orientation edge -- vertical direction orientation edge -- vision cortex response -- interval detector -- spatial frequency -- interval detection -- traffic sign recognition -- orientation‐interval feature map; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2016.0326
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : It is significant to extract rotation, scaling, translation, and noise (RSTN) invariant features inspired by biological vision for image recognition. A bionic RSTN‐invariant feature extraction are proposed. This extraction process comprises two stages. In the first stage, a novel orientation edge detection is designed based on a filter‐to‐filter scheme. Gabor filters, a bottom filter, smoothen an image by simulating biological vision. Bipolar filters, a top filter, detect the horizontal and vertical direction orientation edge by simulating vision cortex response. After obtaining the orientation edge of the image, an interval detector is executed by a spatial frequency of different direction and distance. Then, the interval detection results are transformed into pixels of the orientation‐interval feature map. RSTN invariant features are generated through the repetition of orientation edge detection and interval detection. Several experimental results demonstrate that RSTN‐invariant features have striking robustness, and capable to classify RSTN images. Finally, bionic invariant features are practiced in traffic sign recognition.