• Improving Tesseract 4's OCR Accuracy through Image Preprocessing

    Improving Tesseract 4's OCR Accuracy through Image Preprocessing

    In this work I took a look at Tesseract 4’s performance at recognizing characters from a challenging dataset and proposed a minimalistic convolution-based approach for input image preprocessing that can boost the character-level accuracy from 13.4% to 61.6% (+359% relative...

    Jun 7, 2020

  • Evaluating the Robustness of OCR Systems

    Evaluating the Robustness of OCR Systems

    In this article, I’m going to discuss about my Bachelor’s degree final project, which is about evaluating the robustness of OCR systems (such as Tesseract or Google’s Cloud Vision) when adversarial samples are presented as inputs. It’s somewhere in-between fuzzing...

    Sep 7, 2019