An Advanced Image Captioning using combination of CNN and LSTM

Abstract

The Captioning of Image now a days is gaining a lot of interest which generates an automated simple and short sentence describing the image content. Machines indeed are trained in a way that they can understand the Image content and generate captions which are almost accurate at a human level of knowledge is a very tedious and interesting task. There are various solutions used to solve this tedious task and generate simple sentences known as captions using neural network which still comes with problems such as inaccurate captions, generating captions only for the seen images, etc. In this paper, the proposed system model was able to generate more precise captions using a two staged model which consists of a combination of Deep Neural Network algorithms (Convolutional and Long Short-Term Memory). The proposed model was able to overcome the problems arise using Traditional CNN and RNN algorithms. The model is trained and tested using the Flicker8k Data set.