Loading…

Product quality on-line inspecting for the pressed protuberant character on a metal tag

The pressed protuberant character is a reflectorized character based on the difference of reflectance. The quality of its image is lower than the image of the generally character based on the chromatic difference between background and foreground. So, the general quality inspecting method based on t...

Full description

Saved in:
Bibliographic Details
Published in:Image and vision computing 2007-08, Vol.25 (8), p.1255-1262
Main Authors: Jian-Hai, Cao, Chang-Hou, Lu, Chun-Yi, Shi
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The pressed protuberant character is a reflectorized character based on the difference of reflectance. The quality of its image is lower than the image of the generally character based on the chromatic difference between background and foreground. So, the general quality inspecting method based on the binary-scale character cannot adapt for the protuberant character. To solve this problem, a new method of direct gray-scale feature extraction based on the ring projection algorithm and the vector sum for inspecting the quality of the pressed character is presented. The new method keeps integrity feature of the protuberant character information dramatically, and can overcome the main shortages of the traditional method on binary-scale image, such as depending on a binarization algorithm extremely, lower performance of anti-jamming. A limited set of the tag pressed protuberant characters is extracted feature and inspected by the new method. The results show that the proposed method adapts to the variant gray-scale, location and orientation of the character, can yield an excellent performance on the condition of noise and deformity, and its accuracy is 97.27%. It is easy to control the pressed character quality using to adjust the inspecting threshold value. It has highly worth applying to correlated fields.
ISSN:0262-8856
1872-8138
DOI:10.1016/j.imavis.2006.07.025