Distortion Detection for Multi Class Barcode using Fine Localization with Image Recognize
Basil. N. Alhamadani, Almanthor Motaz.M
Abstract
Standardized identification, including one dimensional scanner tag and two dimensional scanner tag, In numerous standardized tag-based portable frameworks, distinctive scanner tags will show up all the while with various points, shapes, and picture quality. Standardized tag restriction is a huge essential for scanner tag deciphering in these applications, we propose a district based start to finish system to finely confine and group one dimensional scanner tag and Quick Response code in complex situations. Two unique layers are planned in our system. One is a quadrilateral relapse layer to restrict self-assertive quadrilateral bounding boxes, and another is a Multi scale Spatial Pyramid Pooling layer, to improve the discovery precision of little scope standardized tags, Broad investigations on existing open datasets and our dataset have confirmed the viability of proposed layers. We additionally exhibit that our strategy can oppose a few bends by mimicking scanner tag pictures of various picture characteristics. Besides, a human deciphering test is additionally performed to demonstrate the viability of our technique for Quick Response code unraveling.