Braille Character Segmentation Algorithm Based on Gaussian Diffusion  

作　　者：Zezheng Meng Zefeng Cai Jie Feng Hanjie Ma Haixiang Zhang Shaohua Li 

机构地区：[1]School of Computer Science and Technology,Zhejiang Sci-Tech University,Hangzhou,310018,China

出　　处：《Computers, Materials & Continua》2024年第4期1481-1496,共16页计算机、材料和连续体（英文）

摘　　要：Optical braille recognition methods typically employ existing target detection models or segmentation modelsfor the direct detection and recognition of braille characters in original braille images. However, these methodsneed improvement in accuracy and generalizability, especially in densely dotted braille image environments. Thispaper presents a two-stage braille recognition framework. The first stage is a braille dot detection algorithmbased on Gaussian diffusion, targeting Gaussian heatmaps generated by the convex dots in braille images. Thisis applied to the detection of convex dots in double-sided braille, achieving high accuracy in determining thecentral coordinates of the braille convex dots. The second stage involves constructing a braille grid using traditionalpost-processing algorithms to recognize braille character information. Experimental results demonstrate that thisframework exhibits strong robustness and effectiveness in detecting braille dots and recognizing braille charactersin complex double-sided braille image datasets. The framework achieved an F1 score of 99.89% for Braille dotdetection and 99.78% for Braille character recognition. Compared to the highest accuracy in existing methods,these represent improvements of 0.08% and 0.02%, respectively.

关 键 词：Computer vision image recognition optical braille recognition 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]