IMAGE CAPTION GENERATOR USING CNN AND LSTM(GUI Application)

Computer Engineering

Image captioning is one of the most needed requirements of today’s world. Moreover, there are some inbuilt applications that generate and provide a caption for a certain image, all these things are done with the help of deep neural network models. The process of generating a description of an image or the process by which we get to know moto of image is called image captioning. Using CNN it detects the important objects, their attributes and also relation among them in respective image. It generates syntactically and semantically correct sentences. In this project, we present a CNN LSTM Model to describe images and generate captions using computer vision and machine translation. This project aims to detect different and important objects found in an image, recognize the relationships between those objects and predicting the sequence of sentence using LSTM. The dataset used is Flickr8k and the programming language used is Python3, and with the help of the Xception model, to demonstrate the caption for image. This project will also elaborate on the functions and structure of the various Neural networks involved. Generating image captions is an important aspect of Computer Vision and Natural language processing.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.