13 February 2025 in PLOS ONE
Automatically generating image captions poses one of the most challenging applications within artificial intelligence due to its integration of computer vision and natural language processing algorithms. This task becomes notably more formidable when dealing with a language as intricate as Bengali and the overall scarcity of Bengali-captioned image databases. In this investigation, a meticulously human-annotated dataset of Bengali captions has been curated specifically for the encompassing collection of pictures. Simultaneously, an innovative end-to-end architecture has been introduced to craft pertinent image descriptions in the Bengali language, leveraging an attention-driven decoder. Initially, the amalgamation of images’ spatial and temporal attributes is facilitated by Gated Recurrent Units, constituting the input features. These features are subsequently fed into the attention layer alongside embedded caption features. The attention mechanism scrutinizes the interrelation between visual and linguistic representations, encompassing both categories of representations. Later, a comprehensive recursive unit comprising two layers employs the amalgamated attention traits to construct coherent sentences. Utilizing our furnished dataset, this model undergoes training, culminating in achievements of a 43% BLEU-4 score, a 39% METEOR score, and a 47% ROUGE score. Compared to all preceding endeavors in Bengali image captioning, these outcomes signify the pinnacle of current attainable standards.
1 October 2025 in IAES International Journal of Artificial Intelligence (IJ-AI)
The bangla alphabet includes vowels, consonants, and compound symbols. The compound nature of bangla is a product of combining two or more root bangla characters into one graph. They are difficult to differentiate because they have a sophisticated geometric shape and an immense variety of scripts used by different places and individuals. This is one of the greatest challenges in creating effective optical character recognition (OCR) systems for bangla. In this paper, a deep convolutional neural network (DCNN)-based system is presented to identify bangla compound characters with high precision. The model was trained using the AIBangla dataset. It has about 171 classes of bangla compound characters. A DCNN system, BonoNet, was designed to classify compound characters. BonoNet outperformed all other state-of-the-art architecture on the test set and improved over current state-of-the-art architecture methods. BonoNet will greatly improve the automation and analysis of the bangla language by accurately identifying these compound complex characters.