GridFace: Face Rectification via Learning Local Homography Transformations

Zhou, Erjin; Cao, Zhimin; Sun, Jian

doi:10.1007/978-3-030-01270-0_1

Cited by 36 publications

(28 citation statements)

References 40 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, differences in lamination conditions and various types of plates make the problem complex. The rectification is also studied in face recognition work [20] in which they tried to rectify faces by local homography transformation through a deep learning network. Faces have a common shape of an ellipse and contain peculiar features such as eyes, noses, and mouse.…”

Section: Related Workmentioning

confidence: 99%

Deep corner prediction to rectify tilted license plate images

Yoo

Jun

2020

Multimedia Systems

View full text Add to dashboard Cite

Skewness and obliqueness of vehicle plate images influence license plate recognition. The more tilted plate images are, the harder the recognition task is. To this end, if plate images are preprocessed to be aligned and rectified, the recognition performance would improve. We propose deep neural network models that can locate four corner plate positions, which can then be used to perform the perspective transformation that can be used to rectify plates. Such a transformation is called homography. The models consist of two sequential parts: a feature extraction part having convolution and a regression part with fully connected layers. The models are open in the sense that the feature extraction part can host other well-known models such as Mobilenet as long as they have the feature capture capability. We devise a loss function as the sum of Euclidean distance between predicted coordinates and ground truth and discuss image augmentation schemes. The experiment results show that the models with well-known object detection models are able to predict corner positions with relatively high precision.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep corner prediction to rectify tilted license plate images

Yoo

Jun

2020

Multimedia Systems

View full text Add to dashboard Cite

show abstract

“…MTCNN [7] is one of the most effective CNN-based face-detector/landmark detectors and its recent implementation in Keras [29] increased its popularity. Research on multi-pose LD opened the way to 3D alignment: however, even if the most powerful methods (GAN [30] and symmetrization [31]) are optimal for restoration or entertainment purposes, 3D alignment did not show to provide significant advantages in terms of recognition accuracy over its 2D version [32].…”

Section: Alignment Procedures and Spatial Transformer Networkmentioning

confidence: 99%

Distillation of an End-to-End Oracle for Face Verification and Recognition Sensors

Guzzi

Bortoli

Molina

et al. 2020

Sensors

View full text Add to dashboard Cite

Face recognition functions are today exploited through biometric sensors in many applications, from extended security systems to inclusion devices; deep neural network methods are reaching in this field stunning performances. The main limitation of the deep learning approach is an inconvenient relation between the accuracy of the results and the needed computing power. When a personal device is employed, in particular, many algorithms require a cloud computing approach to achieve the expected performances; other algorithms adopt models that are simple by design. A third viable option consists of model (oracle) distillation. This is the most intriguing among the compression techniques since it permits to devise of the minimal structure that will enforce the same I/O relation as the original model. In this paper, a distillation technique is applied to a complex model, enabling the introduction of fast state-of-the-art recognition capabilities on a low-end hardware face recognition sensor module. Two distilled models are presented in this contribution: the former can be directly used in place of the original oracle, while the latter incarnates better the end-to-end approach, removing the need for a separate alignment procedure. The presented biometric systems are examined on the two problems of face verification and face recognition in an open set by using well-agreed training/testing methodologies and datasets.

show abstract

“…Zhong et al [35] also propose an end-to-end trainable framework in which the face alignment and the facial feature extraction can be jointly trained only using the personal identities as the supervising signal. The recent work [22] propose a GridFace to reduce facial geometric variations.…”

Section: Related Workmentioning

confidence: 99%

APA: Adaptive Pose Alignment for Pose-Invariant Face Recognition

Deng

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Face alignment is a crucial step in face recognition. Through making the position of face consistent, face alignment reduces intra-class variability due to factors such as lighting, background, pose, and perspective transformation, and further facilitating the recognition tasks. In this paper, we propose a new face alignment method for pose-invariant face recognition, called adaptive pose alignment (APA), which can greatly reduce the intra-class difference and correct the noise caused by the traditional method in the alignment process, especially in unconstrained settings. Instead of aligning all faces to the predefined, uniform frontal shape, we adaptively learn the alignment templates according to the facial poses and then align each face of training or testing sets to its related template. To further improve face recognition performance, we propose a simple, yet effective feature normalization method which can generate more discriminative feature representation of a face or a set of faces (template) combined with the APA method. Furthermore, we introduce a pose-invariant face recognition pipeline that sequentially applies APA-based alignment, deep representation by softmax or ArcFace loss function, and the effective feature normalization procedure. We empirically show that APA-based images can accelerate the training of deep face recognition model by aligning all the images to the optimal templates. Moreover, experimental results show that the proposed method achieves the state-of-the-art performance on popular challenging face datasets including IJB-A, IJB-C, and CPLFW datasets. INDEX TERMS Face alignment, APA, intra-class variability, pose-invariant face recognition.

show abstract

GridFace: Face Rectification via Learning Local Homography Transformations

Cited by 36 publications

References 40 publications

Deep corner prediction to rectify tilted license plate images

Deep corner prediction to rectify tilted license plate images

Distillation of an End-to-End Oracle for Face Verification and Recognition Sensors

APA: Adaptive Pose Alignment for Pose-Invariant Face Recognition

Contact Info

Product

Resources

About