Affine invariant fusion feature extraction based on geometry descriptor and BIT for object recognition. Issue 1 (1st January 2019)

• Record Type: Journal Article
• Authors: Yu, Lingli; Xia, Xumei; Zhou, Kiajun; Zhao, Lijun
• Is Part Of: IET image processing. Volume 13:Issue 1(2019)
• Page Start: 57
• Page End: 72
• Publication Date: 2019-01-01
• Subjects: feature extraction -- image recognition -- affine transforms -- object recognition -- face recognition -- edge detection; valuable technology -- image recognition -- bio‐visual mechanism -- object recognition method -- fusion feature framework -- geometry descriptor -- double biologically inspired transformation -- shape feature -- interest detector -- contour features -- area estimation -- affine region detector -- area ratio feature vectors -- orientation edge detector -- local space frequency detector -- DBIT feature vectors -- weighted fusion strategy -- Pearson correlation distance -- geometry feature -- highly stable recognition accuracy -- feature invariance -- selectivity -- affine invariant fusion feature extraction -- affine transformation -- viewing angle -- distance variations -- affine invariant feature extraction; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.5488
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : It is difficult to recognise an image with affine transformation due to viewing angle anddistance variations. Therefore, affine invariant feature extraction is avaluable technology in the field of image recognition. Inspired by bio‐visualmechanism, an affine invariant for object recognition method based on a fusionfeature framework is proposed in this study, which employs geometry descriptorand double biologically inspired transformation (DBIT). First, a shape featureof interest detector is adopted to detect contour features. Then, the areaestimation of affine region detector is utilised to construct area ratio featurevectors. Second, an orientation edge detector is built to highlight the edges ofdifferent directions. On this basis, local space frequency detector is adoptedto measure the spatial frequency at each direction and interval, which convertsthe output map into DBIT feature vectors. A weighted fusion strategy isperformed based on Pearson correlation distance to fuse the geometry feature andDBIT feature. Some tests for Alphanumeric, Coil‐100 MPEG‐7, Mixed NationalInstitute of Standards and Technology (MNIST) and Olivetti Research Laboratoryface images database (ORL) database remain highly stable recognition accuracy, even when the shear factor is between −0.5 and + 0.5. The experiment resultsshow the authors' proposed approach has a nice performance in featureinvariance, selectivity and recognition accuracy.