Impact of Automatic Image Classification and Blind Deconvolution in Improving Text Detection Performance of the CRAFT Algorithm

TL;DR

This study enhances the CRAFT text detection algorithm by automatically classifying images as blurry or not and applying blind deconvolution to blurry images, significantly improving detection accuracy on the ICDAR 2013 dataset.

Contribution

The paper introduces an automatic image classification and blind deconvolution pre-processing pipeline that improves CRAFT's text detection performance.

Findings

Detection IoU h-mean improved to 94.47%

Outperformed top-ranked SenseTime method

Significant enhancement over original CRAFT performance

Abstract

Text detection in natural scenes has been a significant and active research subject in computer vision and document analysis because of its wide range of applications as evidenced by the emergence of the Robust Reading Competition. One of the algorithms which has good text detection performance in the said competition is the Character Region Awareness for Text Detection (CRAFT). Employing the ICDAR 2013 dataset, this study investigates the impact of automatic image classification and blind deconvolution as image pre-processing steps to further enhance the text detection performance of CRAFT. The proposed technique automatically classifies the scene images into two categories, blurry and non-blurry, by utilizing of a Laplacian operator with 100 as threshold. Prior to applying the CRAFT algorithm, images that are categorized as blurry are further pre-processed using blind deconvolution to reduce the blur. The results revealed that the proposed method significantly enhanced the detection performance of CRAFT, as demonstrated by its IoU h-mean of 94.47% compared to the original 91.42% h-mean of CRAFT and this even outperformed the top-ranked SenseTime, whose h-mean is 93.62%.