Enhance Text Recognition by Image Pre-Processing to Facilitate Library Services by Mobile Devices

摘要

Facing the popularity of web searching, libraries continuously invest in the provision of online searching and refurnish physical facilities to attract users during the past decades. In this study, we conducted a technical feasibility study to facilitate library services by applying a novel image pre-processing technique to enhance performance of OCR via mobile devices. In the binarization stage, a grayscale image is usually assigned a global threshold value to be binary, while this will not be suitable for some scenarios, such as non-uniform lightness and complicated background. Instead of segregating the grayscale image into many regions like other studies, our approach only partitioned an image into three equal-sized horizontal segments to identify the local threshold value of each segment and then restored the three segments back to the original state. The experimental results illustrate that the proposed method efficiently and effectively improves the text recognition. The accuracy rate was raised from 17.7% to 72.05% of all test images. Without counting eight unrecognizable images, the average accuracy rates of our treatment can reach 90.06%. To compare with other studies we conducted another evaluation to examine the validity of our approach. The result showed that our treatment outperforms most of the other studies and the performance achieves 74.6% in precision and 80.2% in the recall. We are confident that this design will not only bring users more convenience in using libraries but help library staff and businessmen to manage the status of books.