Papers › Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters

Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters

21 Jun 2018arXiv:1806.08037archive 2025-07-28

Manohar Karki, Qun Liu, Robert DiBiano, Saikat Basu, Supratik Mukhopadhyay

Classification techniques for images of handwritten characters are susceptible to noise. Quadtrees can be an efficient representation for learning from sparse features. In this paper, we improve the effectiveness of probabilistic quadtrees by using a pixel level classifier to extract the character pixels and remove noise from handwritten character images. The pixel level denoiser (a deep belief network) uses the map responses obtained from a pretrained CNN as features for reconstructing the characters eliminating noise. We experimentally demonstrate the effectiveness of our approach by reconstructing and classifying a noisy version of handwritten Bangla Numeral and Basic Character datasets.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Classification Document Image Classification General Classification Image Classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Document Image Classification	Noisy Bangla Characters	Pixel-level RC	Accuracy	77.22	#2 of 2	Archive leaderboard	report
Document Image Classification	Noisy Bangla Numeral	Pixel-level RC	Accuracy	95.46	#2 of 2	Archive leaderboard	report
Document Image Classification	n-MNIST	Pixel-level RC	Accuracy	97.62	#1 of 1	Archive leaderboard	report
Image Classification	Noisy MNIST (AWGN)	Pixel-level RC	Accuracy	97.62	#2 of 2	Archive leaderboard	report
Image Classification	Noisy MNIST (Contrast)	Pixel-level RC	Accuracy	95.04	#2 of 2	Archive leaderboard	report
Image Classification	Noisy MNIST (Motion)	Pixel-level RC	Accuracy	97.20	#2 of 2	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