First EAI International Conference on Computer Science and Engineering

Research Article

Text-zone Detection and Rectification in Document Images Captured by Smartphone

Download566 downloads
  • @INPROCEEDINGS{10.4108/eai.27-2-2017.152342,
        author={Sophea PRUM},
        title={Text-zone Detection and Rectification in Document Images Captured by Smartphone},
        proceedings={First EAI International Conference on Computer Science and Engineering},
        publisher={EAI},
        proceedings_a={COMPSE},
        year={2017},
        month={3},
        keywords={Document image processing text-zone detection binariza-tion skew correction smartphone document capture mobile camera doc-ument capture},
        doi={10.4108/eai.27-2-2017.152342}
    }
    
  • Sophea PRUM
    Year: 2017
    Text-zone Detection and Rectification in Document Images Captured by Smartphone
    COMPSE
    EAI
    DOI: 10.4108/eai.27-2-2017.152342
Sophea PRUM1,*
  • 1: Mimos Berhad, Kuala Lumpur, Malaysia
*Contact email: sophea.prum@mimos.my

Abstract

Detection text-zone in the document images captured by smartphone is one of the main challenges in document image processing research domain. Unlike scanned document images, the document im-ages captured by smartphones, especially under unconstrained condition and environment, have some additional challenges. The document frame may appear on various backgrounds, bent, rotated, light reflection, etc. To deal with these problems, we present a pre-processing method that allows to detect and rectify text-zone in the document images captured by a smartphone. The proposed method consists of three steps: bina-rization, skew angle detection/correction and textzone detection. The experimental results based on the recognition rates given by two endto-end OCR systems have shown a significant improvement when applying the proposed pre-processing methods before applying any OCR system.