Practical Recognition System for Text Printed on Clear Reflected Material

Abstract

Text embedded in an image contains useful information for applications in the medical, industrial, commercial, and research fields. While many systems have been designed to correctly identify text in images, no work addressing the recognition of degraded text on clear plastic has been found. This paper posits novel methods and an apparatus for extracting text from an image with the practical assumption: (a) poor background contrast, (b) white, curved, and/or differing fonts or character width between sets of images, (c) dotted text printed on curved reflective material, and/or (d) touching characters. Methods were evaluated using a total of 100 unique test images containing a variety of texts captured from water bottles. These tests averaged a processing time of ~10 seconds (using MATLAB R2008A on an HP 8510 W with 4 G of RAM and 2.3 GHz of processor speed), and experimental results yielded an average recognition rate of 90 to 93% using customized systems generated by the proposed development.

Recognition of Expiration Dates Written on Food Packages with Open Source OCR

“…These methods are also classified into two groups: preprocessing-and training-based methods. The first group utilizes several conventional preprocessing methods such as blob-connection and slant/rotation correction [15]. However, dot matrix characters in actual use vary significantly in terms of printing quality due to factors such as font pattern and dot size, which makes it very difficult to use the same process for every dot matrix font.…”

Printed Arabic optical character segmentation

“…This is due to the complicated Arabic text characteristics, and the structure of letters which differs according to its position in the word; at beginning, middle, or end, many difficulties arise through the development process especially in the segmentation stage from which most of errors come and affects negatively the recognition rate. One of the major and important factors that enhances the information retrieval systems is the efficiency of the data entry operation from different sources of documents like invoices, receipts, bank statement, passport document and other systems as mentioned in [14,15,16].…”