Limits...
Feature and score fusion based multiple classifier selection for iris recognition.

Islam MR - Comput Intell Neurosci (2014)

Bottom Line: Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result.CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions.Experimental results show the versatility of the proposed system of four different classifiers with various dimensions.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh.

ABSTRACT
The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al.

Show MeSH
Recognition performance of left-right iris feature fusion based multimodal system among different number of hidden states of DHMM.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4120484&req=5

fig8: Recognition performance of left-right iris feature fusion based multimodal system among different number of hidden states of DHMM.

Mentions: In feature level fusion, optimum value of the number of hidden states of DHMM has been chosen and Figure 8 shows the comparison results with ROC curve. Figure 9 shows the performance comparison among unimodal left iris, unimodal right iris, and left-right iris feature fusion based recognition. Since the primary goal of left-right iris feature fusion based multimodal iris recognition system is to achieve the performance which is equal to or better than the performance of any left or right unimodal iris recognition system. When the noise level is high of right iris, the left iris unimodal system performs better than the right iris unimodality; thus the left-right iris recognition performance should be at least as good as that of the right iris unimodal system. When the noise level is high of left iris, the right iris recognition performance is better than the left one and the integrated performance should be at least the same as or better than the performance of the right iris recognition. The system also works very well when left and right iris image do not contain noises. Figure 9 shows the above-mentioned performance of the left-right feature fusion based multimodal iris recognition.


Feature and score fusion based multiple classifier selection for iris recognition.

Islam MR - Comput Intell Neurosci (2014)

Recognition performance of left-right iris feature fusion based multimodal system among different number of hidden states of DHMM.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4120484&req=5

fig8: Recognition performance of left-right iris feature fusion based multimodal system among different number of hidden states of DHMM.
Mentions: In feature level fusion, optimum value of the number of hidden states of DHMM has been chosen and Figure 8 shows the comparison results with ROC curve. Figure 9 shows the performance comparison among unimodal left iris, unimodal right iris, and left-right iris feature fusion based recognition. Since the primary goal of left-right iris feature fusion based multimodal iris recognition system is to achieve the performance which is equal to or better than the performance of any left or right unimodal iris recognition system. When the noise level is high of right iris, the left iris unimodal system performs better than the right iris unimodality; thus the left-right iris recognition performance should be at least as good as that of the right iris unimodal system. When the noise level is high of left iris, the right iris recognition performance is better than the left one and the integrated performance should be at least the same as or better than the performance of the right iris recognition. The system also works very well when left and right iris image do not contain noises. Figure 9 shows the above-mentioned performance of the left-right feature fusion based multimodal iris recognition.

Bottom Line: Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result.CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions.Experimental results show the versatility of the proposed system of four different classifiers with various dimensions.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh.

ABSTRACT
The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al.

Show MeSH