Verification system robust to occlusion using low-order Zernike moments of palmprint sub-images

Abstract

This paper proposes a palmprint based verification system which uses low-order Zernike moments of palmprint sub-images. Euclidean distance is used to match the Zernike moments of corresponding sub-images of query and enrolled palmprints. These matching scores of sub-images are fused using a weighted fusion strategy. The proposed system can also classify the sub-image of palmprint into non-occluded or occluded region and verify user with the help of non-occluded regions. So it is robust to occlusion. The palmprint is extracted from the acquired hand image using a low cost flat bed scanner. A palmprint extraction procedure which is robust to hand translation and rotation on the scanner has been proposed. The system is tested on IITK, PolyU and CASIA databases of size 549, 5239 and 7752 hand images respectively. It performs with accuracy of more than 98%, and FAR, FRR less than 2% for all the databases.

Texture based features for robust palmprint recognition: a comparative study

“…The statisticalbased approaches are based on extracting the features that correspond to mean, variance, moments, and energy. There exist various techniques to capture the statistics of the palmprint that includes wavelet transform [9], Fourier transform [10], Cepstrum energy [11], sub-block energy based on Gabor transform [12,13], micro-scale invariant Gabor [14], Zernike moments [15]. However, the use of the statistics-based approaches are not robust against the sensor noise.…”

Occlusion Invariant Palmprint Recognition with ULBP Histograms

“…These methods are invariant to illumination but do not perform well even for a small rotation and shift. Image moments, such as Zernike, Legendre and Hu, have also been extracted from sub-images of palmprint ROI and used for palmprint recognition 4,13,14 .…”

“…Further, fisher linear discrimination is applied for dimension reduction 15 . Recent researches are focused on improving the quality of palmprint features against variations in position, rotation, scale, noise, translation, occlusion, and illumination 4,15,19,20 . To make a robust palmprint recognition system, two or more feature extraction techniques are essentially combined 15 .…”

“…Capturing a palmprint image in an unconstrained environment makes it difficult to align in the same precise position, and hence brings forth the problems of occlusion, rotation, and translation (shift) 3 . Also, some portion of the palm may be suffered by occlusion due to misplacement or misalignment of the palmprint 4 . In the real life situations, it might be desirable to recognize a palm which may be partially occluded due to reasons like injury, tattoo, dust, or grease marks.…”

Palmprint Based Recognition System Using Local Structure Tensor and Force Field Transformation

“…Palmprint has been extracted from the acquired image using the method proposed in [1]. The extracted palmprint is divided into 12 × 12 sub-blocks and mean for each sub-block is computed.…”