Transformer architecture for image capturing using deep learning approach

Computer Engineering

Image Captioning is a tremendous job in both Natural Language Processing and Computer Vision. Most image captioning systems operate an encoder-decoder framework, where an input image is encoded into an intermediate representation of the information in the image, and then decoded into a descriptive text sequence. This paper bedrock a new deep learning approach based on transformer architecture method for Image Captioning purpose. A transformer is a deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input data. It is used primarily in the fields of natural language processing (NLP) and computer vision (CV).Here we are using two folders as dataset one contain the images and another contain the data. Here we are using EfficientNets which is a most powerful convolutional neural network. It uses Compound coefficient to scale up models in a very efficient manner. Compound Model Scaling helps to improve model performance, balancing the scale in all the three dimensions — width, depth, and image resolution , considering the variable available resources best improve the overall model performance.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.