A new methodology for gray-scale character segmentation and recognition

1996 ◽  
Vol 18 (10) ◽  
pp. 1045-1050 ◽  
Author(s):  
Seong-Whan Lee ◽  
Dong-June Lee ◽  
Hee-Seon Park
Keyword(s):  
Character Segmentation ◽  
Gray Scale

Segmentation of Characters in a Handwritten Kannada Document

2020 ◽  
Vol 10 ◽  
Author(s):  
Asha K. ◽  
Krishnappa H.K
Keyword(s):  
Handwriting Recognition ◽  
Research Work ◽  
Recognition System ◽  
Character Segmentation ◽  
Gray Scale ◽  
Skew Detection ◽  
Kannada Language ◽  
Contrast Normalization ◽  
Line Segmentation ◽  
Processing Steps

Purpose: The main purpose of the proposed research work is to perform the segmentation of characters from the handwritten Kannada document. The reason behind segmentation is to support the implementation of handwriting recognition system for Kannada language. Methodology: To perform segmentation of characters, input document has to go through gray scale conversion, denoising, contrast normalization and binarization process. Result: Documents collected from ICDAR-2013 and ICDAR-2015 were considered for experiment and obtained 100% accuracy for line segmentation and 96% accuracy for character segmentation. Conclusion:: To further improve the efficiency with respect to accuracy of character segmentation, other pre-processing steps like skew detection and correction shall be considered.

scholarly journals Flip Extended Visual Cryptography for Gray-Scale and Color Cover Images

Symmetry ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 65
Author(s):  
Lu Wang ◽  
Bin Yan ◽  
Hong-Mei Yang ◽  
Jeng-Shyang Pan
Keyword(s):  
Privacy Protection ◽  
Visual Cryptography ◽  
Color Images ◽  
Cover Image ◽  
Error Diffusion ◽  
Gray Scale ◽  
Secret Image ◽  
Transaction Security

Visual cryptography (VC) has found numerous applications in privacy protection, online transaction security, and voting security, etc. To counteract potential cheating attacks, Lin et al. proposed flip visual cryptography in 2010, where a second secret image can be revealed by stacking one share with a flipped version of another share. The second secret image can be designed as an additional verification mechanism. However, Lin’s scheme produces meaningless shares and is only applicable to binary secret images. It is interesting to explore whether it is possible to extend the flip VC to having cover images (i.e., extended VC) and these cover images are color images. This problem is challenging since too many restricting conditions need to be met. In this paper, we designed a flip VC for gray-scale and color cover images based on constraint error diffusion. We show that it is possible to meet all the constraints simultaneously. Compared with existing schemes, our scheme enjoys the following features: Color cover images, no computation needed for decoding, and no interference from cover image on the recovered secret image.

Sign in / Sign up

Export Citation Format

Share Document