In this paper, we propose a method, called GridFace, to reduce facial geometric variations and improve the recognition performance.
Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods.
Ranked #13 on Pedestrian Detection on Caltech
In present object detection systems, the deep convolutional neural networks (CNNs) are utilized to predict bounding boxes of object candidates, and have gained performance advantages over the traditional region proposal methods.
Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge.
Ranked #6 on Scene Text Detection on COCO-Text
Different from focused texts present in natural images, which are captured with user's intention and intervention, incidental texts usually exhibit much more diversity, variability and complexity, thus posing significant difficulties and challenges for scene text detection and recognition algorithms.
Recently, text detection and recognition in natural scenes are becoming increasing popular in the computer vision community as well as the document analysis community.
Our basic network is capable of achieving high recognition accuracy ($85. 8\%$ on LFW benchmark) with only 8 dimension representation.