Color Reduction for Complex Document Images

被引:49
作者
Nikolaou, Nikos [1 ]
Papamarkos, Nikos [1 ]
机构
[1] Democritus Univ Thrace, Dept Elect & Comp Engn, Image Proc & Multimedia Lab, GR-67100 Xanthi, Greece
关键词
color reduction; text information extraction; mean-shift; edge preserving smoothing; MEAN SHIFT; QUANTIZATION; ALGORITHM; SPACE; TEXT; SEGMENTATION; EXTRACTION; MAP;
D O I
10.1002/ima.20174
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
A new technique for color reduction of complex document images is presented in this article. It reduces significantly the number of colors of the document image (less than 15 colors in most of the cases) so as to have solid characters and uniform local backgrounds. Therefore, this technique can be used as a preprocessing step by text information extraction applications. Specifically, using the edge map of the document image, a representative set of samples is chosen that constructs a 3D color histogram. Based on these samples in the 3D color space, a relatively large number of colors (usually no more than 100 colors) are obtained by using a simple clustering procedure. The final colors are obtained by applying a mean-shift based procedure. Also, an edge preserving smoothing filter is used as a preprocessing stage that enhances significantly the quality of the initial image. Experimental results prove the method's capability of producing correctly segmented complex color documents where the character elements can be easily extracted as connected components. (C) 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 14-26, 2009; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.20174
引用
收藏
页码:14 / 26
页数:13
相关论文
共 38 条
[1]   An adjustable algorithm for color quantization [J].
Bing, Z ;
Shen, JY ;
Peng, QK .
PATTERN RECOGNITION LETTERS, 2004, 25 (16) :1787-1797
[2]   New adaptive color quantization method based on self-organizing maps [J].
Chang, CH ;
Xu, PF ;
Xiao, R ;
Srikanthan, T .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (01) :237-249
[3]  
Chang YC, 2007, 2007 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN IMAGE AND SIGNAL PROCESSING, P127
[4]   Adaptive page segmentation for color technical journals' cover images [J].
Chen, WY ;
Chen, SY .
IMAGE AND VISION COMPUTING, 1998, 16 (12-13) :855-877
[5]   A fast and novel technique for color quantization using reduction of color space dimensionality [J].
Cheng, SC ;
Yang, CK .
PATTERN RECOGNITION LETTERS, 2001, 22 (08) :845-856
[6]   MEAN SHIFT, MODE SEEKING, AND CLUSTERING [J].
CHENG, YZ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (08) :790-799
[7]   Mean shift: A robust approach toward feature space analysis [J].
Comaniciu, D ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619
[8]   KOHONEN NEURAL NETWORKS FOR OPTIMAL COLOR QUANTIZATION [J].
DEKKER, AH .
NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1994, 5 (03) :351-367
[9]  
FUKUNAGA K, 1975, IEEE T INFORM THEORY, V21, P32, DOI 10.1109/TIT.1975.1055330
[10]  
Gervautz M., 1990, GLASSNER GRAPHICS GE, P287, DOI 10.1016/B978-0-08-050753-8.50061-9