Text Spotting for Low-Resolution Price Tag Images.

Text spotting on low-resolution images is a challenging as well as a popular subject for computer vision researchers. Detecting and also recognizing small characters with a singular system has several difficulties. We have devised a system with multiple simplistic neural networks to overcome the text spotting of product prices on the price tag images taken from the market shelf images. We have acquired our own dataset of market shelf images with 40252 price tag crop images with corresponding price tag text labels. We have focused on detecting the price area on the tags instead of detecting the whole tag with product name, barcode, date, etc. This setup lets us design the sub-networks with relatively well-known and simple architectures. Our architecture consists of one feature extractor backbone ResNet-18, one convolutional network for detecting text area, and one convolutional recurrent network for recognizing characters. As a result, we obtained around 0.80 full-text accuracy and 0.91 character similarity.