文本区域字符颜色极性判断方法  

Method to Recognize Character's Color Polarity of Text Region

作　　者：孙红星[1] 赵楠楠[2] 王蓉[3] 徐心和[1] 

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110004 [2]辽宁科技大学电子与信息工程学院,辽宁鞍山114044 [3]中国人民公安大学安全防范系,北京100038

出　　处：《东北大学学报（自然科学版）》2007年第3期316-319,共4页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(60475036)

摘　　要：文本区域的字符存在着不同的颜色极性.为了能够正确地把文本区域的灰度图像转换成OCR识别软件可以识别的二值图像,提出了一种判断文本区域字符颜色极性的方法.首先计算文本区域的灰度-梯度共生矩阵,并根据目标函数快速地找到分割的灰度和梯度最佳阈值;然后在此基础上提取特征向量,送入神经网络进行分类;最后根据颜色极性判断的结果,分割出字符.实验结果表明,提出的方法在复杂度不同的背景下,正确地识别出了不同类别的字符颜色极性.Characters in a text region may have different color polarities. To convert correctly the image with grayscale in an accepted text region into the OCR-ready binary image, a method is proposed to classify then recognize the color polarity of characters in a text region. The graygradient co-occurrence matrix of the text region is calculated, and the optimum thresholds of segmented grayscale and gradient are found quickly according to the objective function. Then, the feature vector is extracted from the gray-gradient matrix and fed into neural network to classify the color polarity. All the characters in the text region are finally segmented according to the classification of color polarities. Experimental results showed that the proposed method can recognize correctly different color polarities of characters in the background with different complexities.

关 键 词：文本提取 字符 颜色极性 灰度-梯度共生矩阵 神经网络 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]