An effective object recognition system by a mobile application

Abstract

Unparalleled growth in the sharing of media via networks has prompted a great deal of research into issues pertaining to image retrieval. The training and verification of image retrieval systems requires a large number of labelled images with ground truth; however, most researchers employ synthetic datasets for their experiments. In this study, we developed a system based on a mobile phone App for the collection of information pertaining to the location of objects in images. The proposed system is simple and easy to use. Experiments demonstrate the excellent performance of the proposed system with regard to accuracy and response time. This study demonstrates the feasibility of collecting image information using mobile phones.