Local Phase Congruency Based Blur Detection Scheme in Barcode Images

Abstract- The growing uses of camera-based barcode readers have recently gained a lot attention. This has boosted interest in no-reference objective image quality assessment algorithms. Blur is an undesirable phenomenon which appears as one of the most frequent causes of image degradation. In this paper we present a new no-reference blur detection scheme that is based on the perception that it is not easier to differentiate blurred image with the re-blurred version of it. Local phase congruency is calculated for the original and re-blurred images, respectively. These are differenced and normalized to construct a new blur metric. Simulation results show that the proposed scheme gives robust objective metric when identifying blur distortion of barcode images. Index Terms—Blur detection, Intentional blur detection, Phase congruency I