Image Captioning Using Deep Learning

Image Captioning Using Deep Learning

Author Name : Firtosh Kumar, Gaurav Sahu, Mrs. Vimal Gaur

ABSTRACT

Image Captioning has been garnered concept of Natural Language Processing (NLP) and Computer Vision (CV). Generation of descriptive sentences for input images is basically a combination of encoder and decoder architecture which uses feature vector of image to develop an encoder. In this work we used multi-layered Convolution Neural Networks (CNNs) for getting features of images and Long Short Term Memory (LSTM) which is a type of Recurrent Neural Networks (RNNs) used to create descriptive combinations of words with extracted features by using trained images. Our model is trained using Flickr8k dataset which has 5 different descriptions for each image.