Dynamic Feature Matching for Partial Face Recognition

Locality-Aware Channel-Wise Dropout for Occluded Face Recognition

Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions has been proved as a useful approach. However, these artificial occlusions are commonly generated by adding a black rectangle or several object templates including sunglasses, scarfs and phones, which cannot well simulate the realistic occlusions. In this paper, based on the argument that the occlusion essentially damages a group of neurons, we propose a novel and elegant occlusion-simulation method via dropping the activations of a group of neurons in some elaborately selected channel. Specifically, we first employ a spatial regularization to encourage each feature channel to respond to local and different face regions. Then, the locality-aware channel-wise dropout (LCD) is designed to simulate occlusions by dropping out a few feature channels. The proposed LCD can encourage its succeeding layers to minimize the intra-class feature variance caused by occlusions, thus leading to improved robustness against occlusion. In addition, we design an auxiliary spatial attention module by learning a channel-wise attention vector to reweight the feature channels, which improves the contributions of non-occluded regions. Extensive experiments on various benchmarks show that the proposed method outperforms state-of-the-art methods with a remarkable improvement.

A novel DeepMaskNet model for face mask detection and masked facial recognition

Coronavirus disease (COVID-19) has significantly affected the daily life activities of people globally. To prevent the spread of COVID-19, the World Health Organization has recommended the people to wear face mask in public places. Manual inspection of people for wearing face masks in public places is a challenging task. Moreover, the use of face masks makes the traditional face recognition techniques ineffective, which are typically designed for unveiled faces. Thus, introduces an urgent need to develop a robust system capable of detecting the people not wearing the face masks and recognizing different persons while wearing the face mask. In this paper, we propose a novel DeepMasknet framework capable of both the face mask detection and masked facial recognition. Moreover, presently there is an absence of a unified and diverse dataset that can be used to evaluate both the face mask detection and masked facial recognition. For this purpose, we also developed a largescale and diverse unified mask detection and masked facial recognition (MDMFR) dataset to measure the performance of both the face mask detection and masked facial recognition methods. Experimental results on multiple datasets including the cross-dataset setting show the superiority of our DeepMasknet framework over the contemporary models.

Savitzky-Golay filter energy features-based approach to face recognition using symbolic modeling

Face recognition is a well-researched domain however many issues for instance expression changes, illumination variations, and presence of occlusion in the face images seriously affect the performance of such systems. A recent survey shows that COVID-19 will also have a considerable and long-term impact on biometric face recognition systems. The work has presented two novel Savitzky-Golay differentiator (SGD) and gradient-based Savitzky-Golay differentiator (GSGD) feature extraction techniques to elevate issues related to face recognition systems. The SGD and GSGD feature descriptors are able to extract discriminative information present in different parts of the face image. In this paper, an efficient and robust person identification using symbolic data modeling approach and similarity analysis measure is devised and employed for feature representation and classification tasks to address the aforementioned issues of face recognition. Extensive experiments and comparisons of the proposed descriptors experimental results indicated that the proposed approaches can achieve optimal performance of 96-97, 92-96, 100, 84-93, and 87-96% on LFW, ORL, AR, IJB-A datasets, and newly devised VISA database, respectively.

Giant Panda Identification

The lack of automatic tools to identify giant panda makes it hard to keep track of and manage giant pandas in wildlife conservation missions. In this paper, we introduce a new Giant Panda Identification (GPID) task, which aims to identify each individual panda based on an image. Though related to the human re-identification and animal classification problem, GPID is extraordinarily challenging due to subtle visual differences between pandas and cluttered global information. In this paper, we propose a new benchmark dataset iPanda-50 for GPID. The iPanda-50 consists of 6, 874 images from 50 giant panda individuals, and is collected from panda streaming videos. We also introduce a new Feature-Fusion Network with Patch Detector (FFN-PD) for GPID. The proposed FFN-PD exploits the patch detector to detect discriminative local patches without using any part annotations or extra location sub-networks, and builds a hierarchical representation by fusing both global and local features to enhance the inter-layer patch feature interactions. Specifically, an attentional cross-channel pooling is embedded in the proposed FFN-PD to improve the identify-specific patch detectors. Experiments performed on the iPanda-50 datasets demonstrate the proposed FFN-PD significantly outperforms competing methods. Besides, experiments on other fine-grained recognition datasets (i.e., CUB-200-2011, Stanford Cars, and FGVC-Aircraft) demonstrate that the proposed FFN-PD outperforms existing state-of-the-art methods.

Learning Aligned Image-Text Representations Using Graph Attentive Relational Network

Image-text matching aims to measure the similarities between images and textual descriptions, which has made great progress recently. The key to this cross-modal matching task is to build the latent semantic alignment between visual objects and words. Due to the widespread variations of sentence structures, it is very difficult to learn the latent semantic alignment using only global cross-modal features. Many previous methods attempt to learn the aligned image-text representations by the attention mechanism but generally ignore the relationships within textual descriptions which determine whether the words belong to the same visual object. In this paper, we propose a graph attentive relational network (GARN) to learn the aligned image-text representations by modeling the relationships between noun phrases in a text for the identity-aware image-text matching. In the GARN, we first decompose images and texts into regions and noun phrases, respectively. Then a skip graph neural network (skip-GNN) is proposed to learn effective textual representations which are a mixture of textual features and relational features. Finally, a graph attention network is further proposed to obtain the probabilities that the noun phrases belong to the image regions by modeling the relationships between noun phrases. We perform extensive experiments on the CUHK Person Description dataset (CUHK-PEDES), Caltech-UCSD Birds dataset (CUB), Oxford-102 Flowers dataset and Flickr30K dataset to verify the effectiveness of each component in our model. Experimental results show that our approach achieves the state-of-the-art results on these four benchmark datasets.

System for Face Recognition under Different Facial Expressions Using a New Associative Hybrid Model Amαβ-KNN for People with Visual Impairment or Prosopagnosia

Face recognition is a natural skill that a child performs from the first days of life; unfortunately, there are people with visual or neurological problems that prevent the individual from performing the process visually. This work describes a system that integrates Artificial Intelligence which learns the face of the people with whom the user interacts daily. During the study we propose a new hybrid model of Alpha-Beta Associative memories (Amαβ) with Correlation Matrix (CM) and K-Nearest Neighbors (KNN), where the Amαβ-CMKNN was trained with characteristic biometric vectors generated from images of faces from people who present different facial expressions such as happiness, surprise, anger and sadness. To test the performance of the hybrid model, two experiments that differ in the selection of parameters that characterize the face are conducted. The performance of the proposed model was tested in the databases CK+, CAS-PEAL-R1 and Face-MECS (own), which test the Amαβ-CMKNN with faces of subjects of both sexes, different races, facial expressions, poses and environmental conditions. The hybrid model was able to remember 100% of all the faces learned during their training, while in the test in which faces are presented that have variations with respect to those learned the results range from 95.05% in controlled environments and 86.48% in real environments using the proposed integrated system.