11 May 2018 Pattern recognition system: from classical methods to deep learning techniques
Author Affiliations +
Abstract
Performance of modern automated pattern recognition (PR) systems is heavily influenced by accuracy of their feature extraction algorithm. Many papers have demonstrated uses of deep learning techniques in PR, but there is little evidence on using them as feature extractors. Our goal is to contribute to this field and perform a comparative study between classical used methods in feature extraction and deep learning techniques. For that, a biometric recognition system, which is a PR application, is developed and evaluated using a proposed evaluation metric called expected risk probability. In our study, two deeply learned features, based on PCANet and DCTNet deep learning techniques, are used with two biometric modalities that are palmprint and palm-vein. Subsequently, the efficiency of these techniques is compared with various classical feature extraction methods. From the obtained results, we drew our conclusions on a very positive impact of deep learning techniques on overall recognition rate, and thus these techniques significantly outperform the classical techniques.
© 2018 SPIE and IS&T
Hakim Bendjenna, Hakim Bendjenna, Abdallah Meraoumia, Abdallah Meraoumia, Othaila Chergui, Othaila Chergui, } "Pattern recognition system: from classical methods to deep learning techniques," Journal of Electronic Imaging 27(3), 033008 (11 May 2018). https://doi.org/10.1117/1.JEI.27.3.033008 . Submission: Received: 19 February 2018; Accepted: 24 April 2018
Received: 19 February 2018; Accepted: 24 April 2018; Published: 11 May 2018
JOURNAL ARTICLE
14 PAGES


SHARE
RELATED CONTENT


Back to Top