Shan Tesseract OCR

Gradio demo for Tesseract-OCR Shan. Tesseract is an open source text recognition (OCR) Engine.

language
72 600
0.5 3
0.5 3
OEM — OCR Engine Mode
PSM — Page Segmentation Mode
Examples
Input language Enable Preprocessing Auto-scale to target DPI Target DPI Grayscale Denoise (Median filter) Contrast Sharpness Binarize (Otsu's threshold) OEM — OCR Engine Mode PSM — Page Segmentation Mode