Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters
This work addresses noise susceptibility in character classification for handwritten Bangla, which is an incremental improvement for domain-specific applications.
The paper tackles the problem of classifying noisy handwritten Bangla characters by using a pixel-level denoiser based on a deep belief network to reconstruct characters and remove noise, achieving improved classification effectiveness on noisy versions of Bangla numeral and basic character datasets.
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.