High-resolution Gallery Research Articles

Multi-Scale Identity-Preserving Image-to-Image Translation Network for Low-Resolution Face Recognition

State-of-the-art deep neural network models have reached near perfect face recognition accuracy rates on controlled high-resolution face images (especially Caucasian faces). However, their performance is drastically degraded when they are tested with very low-resolution face images. This is particularly critical in surveillance systems, where a low-resolution probe image is to be matched with high-resolution gallery images. Super-resolution techniques aim at producing high-resolution face images from low-resolution counterparts. While they are capable of reconstructing images that arevisually appealing, the identity-related information is not preserved. Here, we propose an identity-preserving end-to-end image-to-image translation deep neural network which is capable of super-resolving very low-resolution faces to their high-resolution counterparts while preserving identity-related information. We achieved this by training a very deep convolutional encoder-decoder network with a symmetric contracting path between corresponding layers. This network was trained with a combination of a reconstruction andan identity-preserving loss, on multi-scale low-resolution conditions. Extensive quantitative evaluations of our proposed model demonstrated that it outperforms competing super-resolution and low-resolution face recognition methods on natural and artificial low-resolution face data sets and even unseen identities.

Adaptive super-resolution for person re-identification with low-resolution images

Person re-identification is challenging with low-resolution query and high-resolution gallery images. To address the resolution mismatch, many methods perform super-resolution (SR) on low-resolution queries with specifying a single scale factor. However, using a single SR module, whichever scale factor is specified, always brings both advantages and drawbacks in recovering and identifying identity information. A larger scale factor recovers more details but produces excessive artifacts, while a smaller one is on the contrary. To exploit their complementary property for more robust recovery and identification, we propose the Adaptive Person Super-Resolution (APSR) model. APSR jointly trains and fuses multiple SR modules based on their generated visual contents, to fully compensate and learn the complementary identity features in an end-to-end manner. To improve the robustness to artifacts during fusion, our model further learns informative features by online dividing and integrating the generated body regions. Extensive experiments verify the effectiveness of our method with state-of-the-art performances.

Unsupervised Face Domain Transfer for Low-Resolution Face Recognition

Low-resolution face recognition suffers from domain shift due to the different resolution between a high-resolution gallery and a low-resolution probe set. Conventional methods use the pairwise correlation between high-resolution and low-resolution for the same subject, which requires label information for both gallery and probe sets. However, explicitly labeled low-resolution probe images are seldom available, and labeling them is labor-intensive. In this paper, we propose a novel unsupervised face domain transfer for robust low-resolution face recognition. By leveraging the attention mechanism, the proposed generative face augmentation reduces the domain shift at image-level, while spatial resolution adaptation generates domain-invariant and discriminant feature distributions. On public datasets, we demonstrate the complementarity between generative face augmentation at image-level and spatial resolution adaptation at feature-level. The proposed method outperforms the state-of-the-art supervised methods even though we do not use any label information of low-resolution probe set.

Low-resolution and open-set face recognition via recursive label propagation based on statistical classification

In video surveillance, the captured face images are usually suffered from low-resolution (LR), besides, not all the probe images have mates in the gallery under the premise that only a single frontal high-resolution (HR) face image per subject. To address this problem, a novel face recognition framework called recursive label propagation based on statistical classification (ReLPBSC) has been proposed in this paper. Firstly, we employ VGG to extract robust discriminative feature vectors to represent each face. Then we select the corresponding LR face in the probe for each HR gallery face by similarity. Based on the picked HR–LR pairs, ReLPBSC is implemented for recognition. The main contributions of the proposed approach are as follows: (i) Inspired by substantial achievements of deep learning methods, VGG is adopted to achieve discriminative representation for LR faces to avoid the super-resolution steps; (ii) the accepted and rejected threshold parameters, which are not fixed in face recognition, can be achieved with ReLPBSC adaptively; (iii) the unreliable subjects never enrolled in the gallery can be rejected automatically with designed methods. Experimental results in [Formula: see text] pixels resolution show that the proposed method can achieve 86.64% recall rate while keeping 100% precision.

Robust low-resolution face recognition via low-rank representation and locality-constrained regression

Recognizing face images in low-resolution (LR) scenarios have bigger challenges than recognizing those in high-resolution (HR) scenarios due to that LR images usually lack discriminative details. Previous methods ignore the existence of occlusions in the LR probe images. To alleviate this problem, we propose a low-rank representation and locality-constrained regression (LLRLCR) based method in this paper to learn occlusion-robust representations features for final face recognition tasks. For HR gallery set, LLRLCR uses double low-rank representation to reveal the underlying holistic data structures; for LR probe, LLRLCR uses locality-constrained matrix regression to keep regression error's structural information and to learn robust and discriminative representation features. The proposed method allows us to fully exploit the structure information in gallery and probe data simultaneously. Finally, after getting the occlusion-robust features, the face labels can be predicted via a simple yet powerful sparse representation based classifier engine. Experiments on some standard face databases have indicated that the proposed method can obtain promising recognition performance than some state-of-the-art LR face recognition approaches.

Improving cross-resolution face matching using ensemble-based co-transfer learning.

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.

Multidimensional Scaling for Matching Low-Resolution Face Images

Face recognition performance degrades considerably when the input images are of Low Resolution (LR), as is often the case for images taken by surveillance cameras or from a large distance. In this paper, we propose a novel approach for matching low-resolution probe images with higher resolution gallery images, which are often available during enrollment, using Multidimensional Scaling (MDS). The ideal scenario is when both the probe and gallery images are of high enough resolution to discriminate across different subjects. The proposed method simultaneously embeds the low-resolution probe images and the high-resolution gallery images in a common space such that the distance between them in the transformed space approximates the distance had both the images been of high resolution. The two mappings are learned simultaneously from high-resolution training images using an iterative majorization algorithm. Extensive evaluation of the proposed approach on the Multi-PIE data set with probe image resolution as low as 8 6 pixels illustrates the usefulness of the method. We show that the proposed approach improves the matching performance significantly as compared to performing matching in the low-resolution domain or using super-resolution techniques to obtain a higher resolution test image prior to recognition. Experiments on low-resolution surveillance images from the Surveillance Cameras Face Database further highlight the effectiveness of the approach.