Improving Cross-Resolution Face Matching Using Ensemble-Based Co-Transfer Learning

Abstract

Face recognition algorithms are generally trained for matching high-resolution images and they perform well for similar resolution test data. However, the performance of such systems degrades when a low-resolution face image captured in unconstrained settings, such as videos from cameras in a surveillance scenario, are matched with high-resolution gallery images. The primary challenge, here, is to extract discriminating features from limited biometric content in low-resolution images and match it to information rich high-resolution face images. The problem of cross-resolution face matching is further alleviated when there is limited labeled positive data for training face recognition algorithms. In this paper, the problem of cross-resolution face matching is addressed where low-resolution images are matched with high-resolution gallery. A co-transfer learning framework is proposed, which is a cross-pollination of transfer learning and co-training paradigms and is applied for cross-resolution face matching. The transfer learning component transfers the knowledge that is learnt while matching high-resolution face images during training to match low-resolution probe images with high-resolution gallery during testing. On the other hand, co-training component facilitates this transfer of knowledge by assigning pseudolabels to unlabeled probe instances in the target domain. Amalgamation of these two paradigms in the proposed ensemble framework enhances the performance of cross-resolution face recognition. Experiments on multiple face databases show the efficacy of the proposed algorithm and compare with some existing algorithms and a commercial system. In addition, several high profile real-world cases have been used to demonstrate the usefulness of the proposed approach in addressing the tough challenges.

A comprehensive overview of biometric fusion

“…Further, the requirements of an application and the nature of its data may change over time. In the literature, techniques such as online learning or co-training have shown to improve the performance of unibiometric recognition systems by updating them on the fly [201,202]. However, online learning based techniques are yet to be explored for multibiometric systems.…”

Association of Face and Facial Components Based on CNN and Transfer Subspace Learning for Forensics Applications

“…This common information is used to convey knowledge that is gained from the face domain and classify the nose or lip biometric. Use of transfer learning has been made in multiple applications like kinship verification in photo [26], image annotation [27], brain decoding in the medical field [32], face recognition [29,31], cross-domain age estimation [28] and cross-domain association [30]. Transfer learning using dual codebook has been proposed for cross-view action recognition and it shows that it works better compared to stateof-the-art methods [33].…”

“…To tackle this shortcoming, the Bregman divergencebased regularization D Z P S | | | | P T that calculates the probability distribution difference existing between the two domains in the projected subspace Z is used [29]. For every exponential family distribution, there exist corresponding generalized distance measures.…”

A novel training algorithm for convolutional neural network

“…Performance improvement is seen when transfer learning is used in medical image segmentation followed by classifi-cation [42]. Low-resolution face images are matched with the high-resolution gallery images using transfer learning which improved cross-resolution face matching [43]. Transfer learning using Bayesian model was used in [44] for face verification application.…”