OCR

According to news from October 21, the DeepSeek team has recently released a new study, DeepSeek-OCR, which proposes a "text-based optical compression" approach that provides groundbreaking thinking for long text processing for large models. Research shows that by rendering long text into images and then turning to visual token, it is possible to significantly reduce the calculation costs while maintaining high accuracy. Experimental data show that the OCR decoded accuracy rate is as high as 971 TP3T at a rate of less than 10 times; even at 20 times higher, the accuracy rate remains at..

November 5, Google Research demonstrated a new way to read handwritten content using artificial intelligence, called InkSight, a system that can extract digital text directly from images of handwritten text without any intermediate equipment. Traditional handwriting recognition technology relies on Optical Character Recognition (OCR), but this method tends to perform poorly when dealing with handwritten text on complex backgrounds, in blurred or low-light conditions.InkSight takes a different approach by mimicking the process of how humans learn to read, i.e., by continually...