Professional Documents
Culture Documents
Abstract
This paper proposes an efficient indexing scheme for palmprint-based identification system. The proposed system uses geometric hashing of SURF key-points to index the palmprint into hash table and makes score level fusion of voting strategy based on geometric hashing and SURF score to identify the live palmprint. All ordered pairs of SURF key-points of the palmprint are scaled and mapped to a predefined coordinate system and all other points are similarity transformed. The new location after transformation serves as the index of the hash table. During identification, all ordered pairs of key-points of live palmprint are scaled and mapped to the coordinate system while remaining points are similarity transformed. A vote is casted to all images in the corresponding bins. Images having votes more than certain threshold are considered as candidate images of the live palmprint. SURF features of the live palmprint and the candidate images are compared for matching. Matching scores which are based on SURF key-points and vote of the corresponding candidate image are fused using weighted sum rule. The candidate image with the highest fused score is considered as the best match. The system is tested on IITK, CASIA and PolyU datasets. It has been observed that penetration rate of the proposed system is less than 30% for 0% bin miss rate (BMR) and has the identification accuracy of more than 97% for all three datasets. Further, the system is evaluated for robustness on downscaled and rotated. It has been found that the identification accuracy of the system for top best match is more than 90% for images downscaled up to 49% and accuracy is more than 85% when images are rotated at any angle.
On Discriminant Orientation Extraction Using GridLDA of Line Orientation Maps for Palmprint Identification
Abstract
In this paper, we propose a novel Discriminant Orientation Representation, called DORIR, for palmprint identification. To extract DORIR feature, we proposed the algorithm which includes two main steps: (1) Palm line orientation map computation and (2) Discriminant feature extraction of the orientation field. In the first step, positive orientation and negative orientation maps are proposed as the input of two dimensional linear discriminant analysis (2D-LDA) for computing the class-
separability features. In the second step, the grid-sampling based 2DLDA, called Grid-LDA, is used to remove redundant information of orientation maps and form a discriminant representation more suitable for palmprint identification. The experimental results on the two public databases of Hong Kong Polytechnic University (PolyU) show that proposed technique provides a very robust orientation representation for recognition and gets the best performance in comparison with other approaches in literature.
Likelihood scores are used for matching. Fusion at the matching score level is used before decision making. A comparative study between the two systems is then developed. The experimental results are demonstrated using the PolyU multispectral database and the results show that the two proposed systems are more effective when using multispectral images than their monospectral counterpart images.
Palmprint Recognition Based on TwoDimensional Gabor Wavelet Transform and Two-Dimensional Principal Component Analysis
Abstract
A method of palmprint recognition based on Two-Dimensional Gabor(2DGabor ) Wavelet Transform and Two-Dimensional Principal Component Analysis(2DPCA) is proposed. This method firstly carries out 2DGabor wavelet transform for the palmprint image, so that the amplitude of the filtered image can be used as the eigenvector for the palmprint image. And the 2DPCA is used to decrease the dimension of the eigenvector, and the nearest neighbor classifier is employed for palmprint classification.Finally, simulation experiment to compare the method of palmprint recognition based on 2DGabor wavelet and 2DPCA with the method based on Gabor wavelet and PCA is conducted with the assistance of the palmprint image database provided by Hongkong Polytechnic University. The experiment shows that the palmprint recognition method based on 2DGabor wavelet transform and 2DPCA is more effective.
Palmprint Recognition Based on Translation Invariant Zernike Moments and Modular Neural Network
Abstract
This paper introduces a new approach, TIZMs & MNN, for palmprint recognition. It uses translation invariant Zernike moments (TIZMs) as palm features, and a modular neural network (MNN) as classifier. Translation invariance is added to the general Zernike moments which have very good property of rotation invariance. A fast algorithm for computing the TIZMs is adopted to improve the computation speed. The pattern set is set up by eight-order TIZMs. Because palmprint recognition is a large-scale multi-class task, it is quite difficult for a single multilayer perceptrons to be competent. A modular neural network is presented to act the classifier, which can decompose the palmprint recognition task into a series of smaller and simpler two-class sub-problems. Simulations have been done on the Polyu_PalmprintDB database. Experimental results demonstrate that higher identification rate and recognition rate are achieved by the proposed method in contrast with the straight-line segments (SLS) based method [2].