Extraction of character string region by a correlation method

被引：0
|
作者：
Miyamoto, Kazumasa [1 ,5 ,6 ,7 ,8 ,11 ]
Tamagawa, Mitsuaki [1 ,8 ,9 ,10 ,11 ]
Fujita, Ichiro [2 ,10 ,12 ,13 ]
Hayama, Yasunobu [3 ,6 ,14 ,15 ,16 ,17 ,18 ,19 ]
Eiho, Shigeru [4 ]
机构：
[1] Electronics R. and D. Department, Technical Headquarters, MHI Ltd., Kobe, 652-8585, Japan
[2] Electron. Syst. Space Syst. Eng. D., Kobe Shipyard and Machinery Works, MHI Ltd., Kobe, 652-8585, Japan
[3] Ryomei Engineering Co. Ltd., Hiroshima, 733-8553, Japan
[4] Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, 611-0011, Japan
[5] Kyoto University
[6] MHI Hiroshima Laboratories
[7] MHI System Development Center Kobe
[8] System Engineering Center, Electronics Technology Department
[9] Waseda University
[10] MHI
[11] IEICE Japan
[12] Tokyo Institute of Technology
[13] MHI Electronics Syst. Space Syst. E., Kobe, Japan
[14] Kyushu University
[15] Syst. Eng. Research Laboratory, Hiroshima, Japan
[16] Plant System Engineering Center, Kobe, Japan
[17] Technology Training Center, Nagoya, Japan
[18] Ryomei Engineering Co.
[19] IEICE Japan, JSME, ISCIE Japan
来源：
Systems and Computers in Japan | 1999年 / 30卷 / 14期
关键词：
Feature extraction - Image analysis - Image quality - Image segmentation - License plates (automobile) - Optical correlation - Probability - Vehicle locating systems;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
This article describes a three-level thresholding method that is used for the preprocessing for searching character-string regions on a natural image, and a method of defining the region by using the correlation process of two kinds of binary images obtainable from the three-level thresholding. Three-level thresholding is a method by which a high-frequency image is obtained by subtracting a moving-average image from the original image and the high-frequency image is changed to an image consisting of three kinds of elements {-1, 0, 1} using the variance of the image. This method is effective when the brightness of characters and their background are not known or fixed at. When the length of a moving average length is sufficiently longer than the width of a character, the three-level thresholding produces an image in which character regions are represented by 1 or -1. The correlation procedure that is made by multiplying pixel values of the two images, one of which is shifted by the width of a line segment of a character, can generate a character region in high probability. A character region is detected by matching of the correlation image with a rectangular template representing the numberplate. The proposed method has been successfully applied to detection of vehicle registration numbers by a roadside camera.
引用
收藏
页码：43 / 52
相关论文
共 50 条
  • [31] Character string extraction from newspaper headlines with a background design by recognizing a combination of connected components
    Takebe, H
    Katsuyama, Y
    Naoi, S
    DOCUMENT RECOGNITION AND RETRIEVAL VI, 1999, 3651 : 22 - 29
  • [32] Emoticon Extraction Method Based on Eye Characters and Symmetric String
    Yokoi, Takeru
    Kobayashi, Mizuki
    Ibrahim, Roliana
    2015 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2015): BIG DATA ANALYTICS FOR HUMAN-CENTRIC SYSTEMS, 2015, : 2979 - 2984
  • [33] String extraction based on statistical analysis method in color space
    Yan Heping
    Wang, Zhiyan
    Guo, Sen
    GRAPHICS RECOGNITION: TEN YEARS REVIEW AND FUTURE PERSPECTIVES, 2006, 3926 : 173 - 181
  • [34] Character String Envelope Correlation based Vehicle License Plate Tilt Correction in Vertical Direction
    Fu Zhizhong
    Zhao Yu
    Li Xiaofeng
    Guo Wenbo
    2016 IEEE INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC), 2016, : 160 - 164
  • [35] Extraction of Characters String Region from Color Scene Image Engineering, Japan
    Denki Gakkai Ronbunshi C Denshi Joho Shisutemu Bumonshi, 11 (1252):
  • [36] Scene Text Detection with Robust Character Candidate Extraction Method
    Sung, Myung-Chul
    Jun, Bongjin
    Cho, Hojin
    Kim, Daijin
    2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, : 426 - 430
  • [37] OPTICAL CHARACTER RECOGNITION USING A NEW METHOD OF CHARACTERISTIC EXTRACTION
    SHONO, Y
    INUZUKA, T
    APPLIED OPTICS, 1972, 11 (05): : 1271 - &
  • [38] A hidden Markov model-based character extraction method
    Huang, Songtao
    Ahmadi, Majid
    Sid-Ahmed, M. A.
    PATTERN RECOGNITION, 2008, 41 (09) : 2890 - 2900
  • [39] Robust Character Recognition Using Adaptive Feature Extraction Method
    Mori, Minoru
    Sawaki, Minako
    Yamato, Junji
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2010, E93D (01): : 125 - 133
  • [40] Scene text detection with robust character candidate extraction method
    Department of Computer Science and Engineering, POSTECH, Pohang, Korea, Republic of
    不详
    Proc. Int. Conf. Doc. Anal. Recognit., (426-430):
12345