عنوان انگلیسی مقاله:
Joint discriminative feature learning for multimodal finger recognition
ترجمه فارسی عنوان مقاله:
یادگیری ویژگی های تبعیض آمیز مشترک برای تشخیص انگشتان چند حالته
Sciencedirect - Elsevier - Pattern Recognition, 111 (2021) 107704: doi:10:1016/j:patcog:2020:107704
Recently, ﬁnger-based multimodal biometrics, due to its high security and stability, has received considerable attention compared with unimodal biometrics. However, existing multimodal ﬁnger feature ex- traction approaches separately extract the features of different modalities, at the same time ignoring correlations among these different modalities. Furthermore, most of the conventional ﬁnger feature representation approaches are hand-crafted by design, which require strong prior knowledge. It is therefore very important to explore and develop a suitable feature representation and fusion strategy for mul- timodal biometrics recognition. In this paper, we proposed a joint discriminative feature learning (JDFL) framework for multimodal ﬁnger recognition by combining ﬁnger vein (FV) and ﬁnger knuckle print (FKP) patterns. For the FV and FKP images, we ﬁrst established the informative dominant direction vector by convoluting a bank of Gabor ﬁlters and the original ﬁnger image. Then, we developed a simple yet effective feature learning algorithm, which simultaneously maximized the distance of between-class samples and minimized the distance of within-class samples, as well as maximized the correlation among inter- modality samples of the within-class. Finally, we integrated the block-wise histograms of the learned feature maps together for multimodal ﬁnger fusion recognition. Experimental results demonstrated that the proposed approach has a better recognition performance than state-of-the-art ﬁnger recognition methods.© 2020 Elsevier Ltd. All rights reserved.
Keywords: Multimodal biometrics | Feature fusion | Inter-modality | Joint feature learning