Object Detection for Image Captioning

Abstract

Generation of description of pictures victimization tongue sentences is gaining a lot of quality of late. It's a difficult task, because it needs not solely understanding a picture, however to translate that visual data into sentence description. So as to caption a picture, we tend to 1st have to be compelled to discover the objects within the image. Object detection has become one amongst the international widespread analysis fields. 1st the paper introduced the distinction between deep learning and machine learning for object detection. Second the techniques for object detection are surveyed. Third it mentioned techniques for object classification.