IDENTIFYING OBJECT IN AN IMAGE AND GENERATING CAPTION FOR GIVEN IMAGE
B.Sai kumar, Arnell Ephraim, Akella Lakshmana Sai Srikar, D.Ganesh teja · Journal of Emerging Technologies and Innovative Research · 2019
Automatically generating the textual description for an image from an artificial system is known as image captioning. It uses each tongue process and computer vision to get the captions. It is a challenging artificial problem since it requires computer vision to understand the content of the image and a language model from the field of natural language processing to turn the understandings of the image into words. Many techniques proposed to solve this problem. Current approaches or techniques mainly focus on generating captions that are general about image contents.Describing images at a human level and applicable in real life environments is a challenging issue. In this paper, we would implement a neural network based method for image captioning and make it generate the captions for images at a human level by using image captioning, well grounded by the elements of images.