Closed ccouzens closed 3 years ago
HOCR presumably stands for HTML OCR. It generates HTML of the image, with attributes describing where each word appears in the image.
https://github.com/houqp/leptess/issues/27
Example output (from different project): https://github.com/antimatter15/tesseract-rs/blob/3edc4e7658a63aeefe371091e3133bcc24ec02f6/img.html
HOCR presumably stands for HTML OCR. It generates HTML of the image, with attributes describing where each word appears in the image.
https://github.com/houqp/leptess/issues/27
Example output (from different project): https://github.com/antimatter15/tesseract-rs/blob/3edc4e7658a63aeefe371091e3133bcc24ec02f6/img.html