CP-GAN: A Cross-Pose Profile Face Frontalization Boosting Pose-Invariant Face Recognition

Abstract

Pose variant or self-occlusion is one of the open issues which severely degrades the performance of pose-invariant face recognition (PIFR). Existing solutions to PIFR either have undesirable generalization based on challenging pose normalization or are complicated for implement on account of deep neural network. To relieve the impact of ill-pose on PIFR, we have proposed Cross-Pose Generative Adversarial Networks(CP-GAN) to frontalize the profile face with unaltered identity by learning the mapping between the profile and frontal faces in image space. The generator is an encoder-decoder U-net, and generate frontal face image by fusing multiple profile images to achieve a better performance in PIFR. The siamese discriminative network attends to extract the deep representations of the generated frontal face and the ground truth without introducing extra networks in verification and recognition. Besides the implementable architecture, this problem is well alleviated by introducing a combination of adversarial loss for both the generator and the discriminator, symmetry loss, patch-wise loss, and identity loss guiding an identity reserving property of the generated frontal view. Quantitative and qualitative evaluation on both controlled and in-the-wild datasets attest that the solution we proposed to PIFR presents satisfactory perceptual results and transcends state-of-the-art methods on ill-pose face recognition.

Combination of Adaptive Neuro Fuzzy Inference System and Machine Learning Algorithm for Recognition of Human Facial Expressions

“…The outputs of feature extraction methods for colour, texture, and form were fed into the ANFIS. The ANFIS machine learning method, which combines fuzzy logic and neural network methods, is supervised [27]. We are using feed-forward neural networks as a neural network methodology and the Takagi-Sugeno fuzzy logic method as a fuzzy logic method.…”

Few-Shot Learning for Multi-POSE Face Recognition via Hypergraph De-Deflection and Multi-Task Collaborative Optimization

“…However, the diversity of attitude changes considered by this method is limited during model training, so the learned model is invalid when processing images involving other pose changes. Liu et al [38] use multiple profile images to generate frontal images and use the Siamese network to learn the depth representation of the generated frontal images. The depth representation of the images is more easily recognized by the classifier, which helps to improve the recognition rate of the algorithm.…”

Computational Intelligence and Soft Computing Paradigm for Cheating Detection in Online Examinations

“…Detection for Online Examinations. Articles from the literature by Ren et al [17], Liu et al [18], and Yuankai et al [19] have explored the usage of deep neural networks for the extraction of facial features for image recognition (Table 2). For instance, Ren et al [17] have used the Chinese whisper algorithm for extraction of facial features and double triplet NN for classifcation of the images.…”

“…For instance, Ren et al [17] have used the Chinese whisper algorithm for extraction of facial features and double triplet NN for classifcation of the images. Gan and C. P. [18] have been able to overcome the problem of a person writing an exam in various poses by developing a pose invariant face recognition (PIFR) algorithm. Tis would be of great help for students who have diverse postures while writing the exam as various profles of their faces would be registered and facial feature matching would be done.…”