Search

This research paper presents an innovative solution for offline handwritten word recognition in Bengali, a prominent Indic language. The complexities of this script, particularly in cursive writing, often lead to overlapping characters and segmentation challenges. Conventional methodologies, reliant on individual character recognition and aggregation, are error-prone. To overcome these limitations, we propose a novel method treating the entire document as a coherent entity and utilizing the efficient you only look once (YOLO) model for word extraction. In our approach, we view individual words as distinct objects and employ the YOLO model for supervised learning, transforming object detection into a regression problematic to predict spatially detached bounding boxes and class possibilities. Rigorous training results in outstanding performance, with remarkable box_loss of 0.014, obj_loss of 0.14, and class_loss of 0.009. Furthermore, the achieved mAP_0.5 score of 0.95 and map_0.5:0.95 score of 0.97 demonstrates the model's exceptional accuracy in detecting and recognizing handwritten words. To evaluate our method comprehensively, we introduce the Omor-Ekush dataset, a meticulously curated collection of 21,300 handwritten words from 150 participants, featuring 141 words per document. Our pioneering YOLO-based approach, combined with the curated Omor-Ekush dataset, represents a significant advancement in handwritten word recognition in Bengali. [ABSTRACT FROM AUTHOR]

Accurately classifying user-independent handwritten Bengali characters and numerals presents a formidable challenge in their recognition. This task becomes more complicated due to the inclusion of numerous complex-shaped compound characters and the fact that different authors employ diverse writing styles. Researchers have recently conducted significant researches using individual approaches to recognize handwritten Bangla digits, alphabets, and slightly compound characters. To address this, we propose a straightforward and lightweight convolutional neural network (CNN) framework to accurately categorize handwritten Bangla simple characters, compound characters, and numerals. The suggested approach exhibits outperformance in terms of performance when compared too many previously developed procedures, with faster execution times and requiring fewer epochs. Furthermore, this model applies to more than three datasets. Our proposed CNN-based model has achieved impressive validation accuracies on three datasets. Specifically, for the BanglaLekha isolated dataset, which includes 84-character classes, the validation accuracy was 92.48%. On the Ekush dataset, which includes 60-character classes, the model achieved a validation accuracy of 97.24%, while on the customized dataset, which includes 50- character classes, the validation accuracy was 97.03%. Our model has demonstrated high accuracy and outperformed several prominent existing frameworks. [ABSTRACT FROM AUTHOR]