Recognizing Rotated Faces From Frontal and Side Views: An Approach Toward Effective Use of Mugshot Databases

76 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning to generate chairs with convolutional neural networks (2014, background): “Modeling of viewpoint variation is often considered in the context of pose-invariant face recognition [3, 34].”
A Comprehensive Survey on Pose-Invariant Face Recognition (2015, background): “However, in some special applications, for example, law enforcement, multiview images are available for each subject during enrollment [Zhang et al. 2006, 2008].”
Face recognition across pose: A review (2009, methodology): “No training Template matching [16], LEM [27], DCP [28], LBP [2] , cylindrical 3D pose recovery [26], probabilistic geometry assisted FR [55], automatic texture synthesis [85], ICM [29, 30], stereo matching [18], Composite deformable model [48], pan or mic view [71], MQVM [87].”
Learning to Generate Chairs, Tables and Cars with Convolutional Networks (2014, background): “e downside is, of course, the need for a label that fully describes the appearance of each image. Modeling of viewpoint variation is often considered in the context of pose-invariant face recognition [3,34]. In a recent work Zhu et al. [35] approached this task with a neural network: their network t”
Rotating your face using multi-task deep neural network (2015, unknown): “These studies are largely separated into studies of 3D methods [2, 12, 24, 20] and 2D methods [11].”