Papers › BN-DRISHTI: Bangla Document Recognition through Instance-level Segmentation of...

BN-DRISHTI: Bangla Document Recognition through Instance-level Segmentation of Handwritten Text Images

31 May 2023arXiv:2306.09351archive 2025-07-28

Sheikh Mohammad Jubaer, Nazifa Tabassum, Md. Ataur Rahman, Mohammad Khairul Islam

Handwriting recognition remains challenging for some of the most spoken languages, like Bangla, due to the complexity of line and word segmentation brought by the curvilinear nature of writing and lack of quality datasets. This paper solves the segmentation problem by introducing a state-of-the-art method (BN-DRISHTI) that combines a deep learning-based object detection framework (YOLO) with Hough and Affine transformation for skew correction. However, training deep learning models requires a massive amount of data. Thus, we also present an extended version of the BN-HTRd dataset comprising 786 full-page handwritten Bangla document images, line and word-level annotation for segmentation, and corresponding ground truths for word recognition. Evaluation on the test portion of our dataset resulted in an F-score of 99.97% for line and 98% for word segmentation. For comparative analysis, we used three external Bangla handwritten datasets, namely BanglaWriting, WBSUBNdb_text, and ICDAR 2013, where our system outperformed by a significant margin, further justifying the performance of our approach on completely unseen samples.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

crusnic-corp/BN-DRISHTI officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Handwriting RecognitionHandwritten Line SegmentationHandwritten Text RecognitionHandwritten Word SegmentationObject DetectionSegmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Handwritten Line Segmentation BN-HTRd BN-DRISHTI Line Segmentation F-Score 0.9997 #1 of 2 Archive leaderboard report
Handwritten Word Segmentation BN-HTRd BN-DRISHTI Word Segmentation F-Score 0.98 #1 of 1 Archive leaderboard report
Handwritten Word Segmentation BanglaWriting BN-DRISHTI Word Segmentation F-Score 0.97 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections