Multi-Frame Labeled Faces Database: Towards Face Super-Resolution from Realistic Video Sequences

Abstract

Forensically trained facial reviewers are still considered as one of the most accurate approaches for person identification from video records. The human brain can utilize information, not just from a single image, but also from a sequence of images (i.e., videos), and even in the case of low-quality records or a long distance from a camera, it can accurately identify a given person. Unfortunately, in many cases, a single still image is needed. An example of such a case is a police search that is about to be announced in newspapers. This paper introduces a face database obtained from real environment counting in 17,426 sequences of images. The dataset includes persons of various races and ages and also different environments, different lighting conditions or camera device types. This paper also introduces a new multi-frame face super-resolution method and compares this method with the state-of-the-art single-frame and multi-frame super-resolution methods. We prove that the proposed method increases the quality of face images, even in cases of low-resolution low-quality input images, and provides better results than single-frame approaches that are still considered the best in this area. Quality of face images was evaluated using several objective mathematical methods, and also subjective ones, by several volunteers. The source code and the dataset were released and the experiment is fully reproducible.

Tracking Missing Person in Large Crowd Gathering Using Intelligent Video Surveillance

“…There are various proposals in the literature, which apply face recognition algorithms to large crowd images such as [ 1 , 2 , 3 , 4 ]; however, tracking a person in a large crowd with low-resolution images is rare. Several state-of-the-art deep learning algorithms are used for face recognition but with high-quality images such as [ 5 ]; however, our study of the related work suggested that they do not show good performance on low-resolution images of the unconstrained environment. To the best of our knowledge, dividing the surveillance premises into geofences and estimating set of geofences for probable presence of missing person is used for the first time in such works.Therefore, we believe our proposal in this paper contributes to the existing knowledge.…”

“…As we noticed in Table 1 , the authors in [ 7 ] applied state-of-art deep learning techniques for face detection and recognition using conversion of low resolution images to high-quality images, but the technique is not tested in low-resolution images from large gatherings. Moreover, literature in [ 1 , 2 , 3 , 4 , 5 , 11 ] shows work on recognizing people based on large crowd and low resolution image data, whereas the literature presented in [ 12 ] only depicts exploitation of large crowd data and in [ 13 ] research carried out only on low resolution data. However, emotional expression of human face have been found in [ 4 ] crowded environment showed happy faces are easily by identified.…”

BFRVSR: A Bidirectional Frame Recurrent Method for Video Super-Resolution

“…Video super-resolution, which solves the problem of reconstructing high-resolution images from low-resolution images, is a classic problem in image processing. It is widely used in security, entertainment, video transmission, and other fields [1][2][3]. As compared with single image super-resolution, video super-resolution can use more information to output better high-resolution images, such as the feature information of adjacent frames.…”