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

Authors:
Cao Jian-Hai;Lu Chang-Hou;Shi Chun-Yi
Affiliations:
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China and Shenzhen Modern Computer Manufacturer Co. Ltd, Shenzhen 518057, China;School of Mechanical Engineering, Shandong University, Jinan 250061, China;Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Venue:
Image and Vision Computing
Year:
2007

Citing 10
Cited 0

Template location in noisy pictures

Signal Processing
A survey of moment-based techniques for unoccluded object representation and recognition

CVGIP: Graphical Models and Image Processing
A New Methodology for Gray-Scale Character Segmentation and Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multispace KL for Pattern Representation and Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Picture Processing

Digital Picture Processing
Direct Gray-Scale Extraction of Features for Character Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Rotation-invariant pattern matching using wavelet decomposition

Pattern Recognition Letters
36 years on the pattern recognition front lecture given at ICPR'2000 in Barcelona, Spain on the occasion of receiving the K.S. Fu prize

Pattern Recognition Letters
Defect detection in textured surfaces using color ring-projection correlation

Machine Vision and Applications
Sequential Hierarchical Scene Matching

IEEE Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.