Image Caption Generation Using Attention Model

The process of generating a caption for a given image using the techniques of computer vision and natural language processing is called image caption generation. During recent times, many deep learning models have been used to increase the performance of the caption generating models. But the drawback of these models is that they lack proper focus on the pertinent part of the image while generating the caption which leads to a vague caption generation. To get the better of these drawbacks, we are proposing a model, which gives a caption by selecting pertinent objects in a particular image and providing a perceivable explanation using them.