An investigation and implementation of real-time image cropping on mobile computing devices based on saliency and face detection
Lisheng Gao, Deqian Fu, Seong Tae Jhang · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2012
Thumbnail images provide mobile computing users of an easier and smoother image exploring experience. Recognizing the objects in an image is important in many retrieval tasks, but thumbnails generated by shrinking the original image often contain less information. The ability of computer vision systems to identify key components of images is investigated in this research. We evaluate automatic cropping techniques 1) based on a general method that detects salient portions of images, and 2) based on automatic face detection. Both of the two methods have been implemented on the mobile computing platform and a desktop platform as a comparison. The experimental results demonstrate the validness of the proposed approaches.