A New Threshold Selection Method Based on Fuzzy Expert Systems for Separating Text from the Background of Document Images

被引:9
作者
Annabestani, Mohsen [1 ]
Saadatmand-Tarzjan, Mahdi [2 ]
机构
[1] Sharif Univ Technol, Fac Elect Engn, Azadi Ave,POB 11365-11155, Tehran, Iran
[2] Ferdowsi Univ Mashhad, Med Imaging Lab, Dept Elect Engn, Fac Engn, Vakil Abad Blvd,POB 91775-1111, Mashhad 9177948974, Razavi Khorasan, Iran
关键词
Threshold selection; Text segmentation; Fuzzy expert system; BINARIZATION;
D O I
10.1007/s40998-018-0160-7
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Threshold selection for text segmentation is an essential preprocessing step in most document processing algorithms. Although there are a number of sophisticatedly well-trained methods for text extraction, many researchers still prefer a fast and simple threshold selection algorithm for preprocessing. In this paper, a new global threshold selection method is proposed based on fuzzy expert systems (FESs). It initially enhances image contrast by using a FES. Then, the range of the threshold value is adjusted by using another FES and a pixel-counting algorithm. Finally, the threshold value is obtained as the middle value of the above range. To evaluate the performance of the proposed algorithm, we employed a database of 20 English, Farsi, and Chinese document images. Experimental results demonstrated that our method provided superior solution quality compared to a number of well-known frequently used counterpart algorithms. The computational burden of the proposed algorithms is actually light with the computational complexity of O(MN) for the image of size MxN.
引用
收藏
页码:219 / 231
页数:13
相关论文
共 29 条
[1]   Thresholding images of historical documents with back-to-front interference based on color quantization by genetic algorithms [J].
Bastos Filho, C. J. A. ;
Mello, C. A. B. ;
Andrade, J. D. ;
Falcao, D. M. A. ;
Lima, M. P. ;
Santos, W. P. ;
Oliveira, A. L. I. .
19TH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, VOL I, PROCEEDINGS, 2007, :488-491
[2]  
Bhattacharya S, 2014, ANN FUZZY MATH INF, V7, P495
[3]  
Bukhari SS, 2009, J UNIVERS COMPUT SCI, V15, P3343
[4]  
Chandrasekaran, 2009, EUR J SCI RES, V36, P502
[5]   A multi-plane approach for text segmentation of complex document images [J].
Chen, Yen-Lin ;
Wu, Bing-Fei .
PATTERN RECOGNITION, 2009, 42 (07) :1419-1444
[6]   MAP IMAGE SEGMENTATION BASED ON THRESHOLDING AND FUZZY RULES [J].
CHI, Z ;
YAN, H .
ELECTRONICS LETTERS, 1993, 29 (21) :1841-1843
[7]   A binarization method with learning-built rules for document images produced by cameras [J].
Chou, Chien-Hsing ;
Lin, Wen-Hsiung ;
Chang, Fu .
PATTERN RECOGNITION, 2010, 43 (04) :1518-1530
[8]   Adaptive degraded document image binarization [J].
Gatos, B ;
Pratikakis, I ;
Perantonis, SJ .
PATTERN RECOGNITION, 2006, 39 (03) :317-327
[9]  
Gatos Basilis, 2009, 2009 10th International Conference on Document Analysis and Recognition (ICDAR), P1375, DOI 10.1109/ICDAR.2009.246
[10]   A spatially adaptive statistical method for the binarization of historical manuscripts and degraded document images [J].
Hedjam, Rachid ;
Moghaddam, Reza Farrahi ;
Cheriet, Mohamed .
PATTERN RECOGNITION, 2011, 44 (09) :2184-2196