Image Synopsis Generating System Built using Deep Learning

When we saw an image, the human brain can easily understand the context of image, whereas can a computer know the context/content it representing? No, we make this possible in our project. Our work is to generate a sentence/description about the image automatically when it is given as a input. Our project model will take an image as an input and generate an english sentence as output, describing the contents of the image. The methods involved in the process of generating a caption are, one understands the content of the image done with deep learning algorithm like CNN-LSTM and to turn the understanding image into words. For this purpose, we use computer vision[6] and natural language processing. But, some people may not be able to understand the language displayed on the output screen and some may not be able to see. Hence, we convert this caption into the user’s preferred language using a language translator (i.e. Google Translator) by importing gTTS and playSound libraries for text to speech conversion.