Abstract
Abstract: The process of generating text from images is called Image Captioning. It not only requires the recognition of the object and the scene but the ability to analyze the state and identify the relationship among these objects. Therefore image captioning integrates the field of computer vision and natural language processing. Thus we introduces a novel image captioning model which is capable of recognizing human faces in an given image using transformer model. The proposed Faster R-CNN-Transformer model architecture comprises of feature extraction from images, extraction of semantic keywords from captions, and encoder-decoder transformers. Faster-RCNN is implemented for face recognition and features are extracted from images using InceptionV3 . The model aims to identify and recognizes the known faces in the images. The Faster R-CNN module creates the bounding box across the face which helps in better interpretation of an image and caption. The dataset used in this model has images with celebrity faces and caption with celebrity names included within itself, respectively has in total 232 celebrities. Due to small size of dataset, we have augmented images and added 100 images with their corresponding captions to increase the size of vocabulary for our model. The BLEU and METEOR scores were generated to evaluate the accuracy/quality of generated captions. Keywords: Image Captioning, Faster R-CNN , Transformers, Bleu score, Meteor score.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have