Research of the SMT Product Character Segmentation Based on Contour Feature

2011 ◽  
Vol 201-203 ◽  
pp. 2019-2022
Author(s):  
Hui Huang Zhao ◽  
De Jian Zhou ◽  
Yu Ming Xu
Keyword(s):  
Image Processing ◽  
Segmentation Algorithm ◽  
Character Segmentation ◽  
Surface Mount Technology ◽  
Binary Images ◽  
Image Sampling ◽  
The Third ◽  
Single Character ◽  
Contour Feature ◽  
Test Result

The principles of the Surface Mount Technology (SMT) product character segmentation and its technology could be described as following: SMT product character image is obtained by image sampling equipment and its ideal binary images is got after image processing. In order to segment the SMT product character effectively, a novel character segmentation algorithm is proposed based on contour feature. Three kinds of information are extracted, one is the up contour feature, another is the under contour feature, the third is the width and the height of the image. Then the position of character segmentation is determined according to the width and height of single character, and character segmentation can be accomplish according to its up contour feature and under contour feature. By analyzing the test result, the proposed approach has excellent properties in character segmentation.

Research on Character Segmentation Method in Image Text Recognition

2012 ◽  
Vol 546-547 ◽  
pp. 1345-1350
Author(s):  
Lian Huan Li
Keyword(s):  
Real Time ◽  
Projection Method ◽  
Segmentation Algorithm ◽  
Character Segmentation ◽  
Text Recognition ◽  
Segmentation Method ◽  
Correction Algorithm ◽  
Vertical Projection ◽  
Tilt Correction ◽  
Single Character

Character Segmentation is the key step for image text recognition. This paper presents a text tilt correction algorithm using tracked characteristics rectangle contour to extract angle, using line scan method based on the number of transitions to determine the character on the bottom. In order to meet the requirements of real-time and reliability, takes improved secondary single-character segmentation algorithm based on vertical projection method.

A character segmentation algorithm for mixed-mode communication

1985 ◽  
Vol 16 (4) ◽  
pp. 66-75 ◽  
Author(s):  
Osamu Nakamura ◽  
Makoto Ujiie ◽  
Noriyoshi Okamoto ◽  
Toshi Minami
Keyword(s):  
Mixed Mode ◽  
Segmentation Algorithm ◽  
Character Segmentation

PERFORMANCE COMPARISON OF DENOISING METHODS FOR HISTORICAL DOCUMENTS

2015 ◽  
Vol 77 (22) ◽  
Author(s):  
Sayed Muchallil ◽  
Fitri Arnia ◽  
Khairul Munadi ◽  
Fardian Fardian
Keyword(s):  
Image Processing ◽  
Processing Technique ◽  
Performance Comparison ◽  
The Other ◽  
Historical Documents ◽  
Median Filtering ◽  
Document Images ◽  
Post Processing ◽  
Binary Images ◽  
Complete Procedure

Image denoising plays an important role in image processing.  It is also part of the pre-processing technique in a binarization complete procedure that consists of pre-processing, thresholding, and post-processing.  Our previous research has confirmed that the Discrete Cosine Transform (DCT)-based filtering as the new pre-processing process improved the performance of binarization output in terms of recall and precision. This research compares three classical denoising methods; Gaussian, mean, and median filtering with the DCT-based filtering. The noisy ancient document images are filtered using those classical filtering methods. The outputs of this process are used as the input for Otsu, Niblack, Sauvola and NICK binarization methods. Then the resulted binary images of the three classical methods are compared with those of DCT-based filtering. The performance of all denoising algorithms is evaluated by calculating recall and precision of the resulted binary images.  The result of this research is that the DCT based filtering resulted in the highest recall and precision as compared to the other methods. 

Sign in / Sign up

Export Citation Format

Share Document