Encoder-Decoder Architecture for Image Caption Generation

摘要

Describing the contents of an image without human intervention is a complex task. Computer Vision and Natural Language Processing are widely used for tackling this problem. It requires an approach with two distinct methods, to understand the contents of the image using computer vision, convert the understanding into semantically correct sentences. Convolutional Neural Network (CNN) is a widely used powerful image feature extraction algorithm for object detection and image classification. Gated Recurrent Unit (GRU) is typically used for effective sentence generation. A combined model of CNN and GRU was proposed to achieve accurate image captions. With the proposed model, an experimentation was done with various datasets and compared the results with existing work. BLEU evaluation metrics was used for benchmarking the results; The proposed model results in a BLEU-4 score (the higher the better) on the MS-COCO 2017 dataset as 53.5.