Bengali Caption Generation for Images Using Deep Learning

Automatic caption generation from images has evolved into an active research topic that requires Natural Language Processing (NLP) and Computer Vision (CV) to comprehend the image input and represent it in text. This can assist visually impaired people by generating text captions of images to understand their surroundings. In this study, we have presented a Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) approach, which can generate natural language for an image. A dataset containing 8,000 images and a total of 37611 captions are utilized for training our model. Besides, VVG16 is employed to extract features from images. Finally, performance is evaluated, which shows an accuracy of 66% and BLEU-1, BLEU-2, BLEU-3, and BLEU-4 scores of 0.40, 0.18, 0.11, and 0.03, respectively.

I. Introduction

Deep learning is an exciting field where human activity can be simulated using a machine. Data is provided to the machine then the machine can learn from the pattern and relation and predict the output similar to the input data. Image caption generation is a problem in deep learning, where a machine can learn from input data and generate captions for images that describe the image the most. This image captioning system can solve many problems, i.e., blind people can benefit from this system, where an image can be described using a deep learning model and then converted to audio data.