Abstract | ||
---|---|---|
The recent on-line palmprint recognition algorithms are time-consuming, and not suitable for being implemented with hardware. This paper describes a novel on-line fast palmprint identification approach. In order to reduce the computational cost of extracting palmprint features from a palmprint image and make it easy to be implemented with hardware, we construct an adaptive lifting wavelet scheme to decompose a palmprint image into several subbands, and then the pulse-coupled neural network is employed to decompose each subband into a series of binary images. The entropies of these binary images are calculated and regarded as features. Then, in the classification step, a support vector machine-based classifier is utilized. Experimental results show that the proposed approach yields a better performance in terms of the correct classification percentages compared with the recent on-line palmprint recognition algorithms. It is also shown that the proposed approach yields observably low computational cost and can be easily implemented with hardware. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1016/j.knosys.2013.01.013 | Knowl.-Based Syst. |
Keywords | Field | DocType |
palmprint identification,proposed approach yield,classification step,correct classification percentage,binary image,palmprint image,adaptive lifting wavelet scheme,computational cost,novel on-line fast palmprint,identification approach,recent on-line palmprint recognition,palmprint feature,entropy,support vector machine | Computer vision,Pattern recognition,Computer science,Binary image,Support vector machine,Artificial intelligence,Recognition algorithm,Artificial neural network,Classifier (linguistics),Machine learning,Wavelet | Journal |
Volume | ISSN | Citations |
42, | 0950-7051 | 12 |
PageRank | References | Authors |
0.55 | 26 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xuan Wang | 1 | 50 | 3.16 |
Junhua Liang | 2 | 13 | 0.89 |
Mingzhe Wang | 3 | 34 | 1.29 |