Binarization of color character strings in scene images using deep neural network
Binarization of color character strings in scene images using deep neural network
复制标题
使用深度神经网络对场景图像中的颜色字符串进行二值化
DOI：
10.1109/dicta.2018.8615837
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Jirui Lin
中科院分区：
文献类型：
--
作者：
Wengiao Bian;Toru Wakahara;Tao Wu;He Tang;Jirui Lin
针对背景复杂、图像降质严重的场景图像，研究了彩色字符串的二值化问题。该方法由三个步骤组成。第一步是通过对输入图像的组成像素在HSI颜色空间中的K均值聚类所获得的K个聚类的每个二分化来组合生成二值化图像。第二步是利用深度神经网络将每幅二值化图像分为字符串和非字符串两类。最后一步是选择字符串程度最高的单个二值化图像作为最佳二值化结果。在ICDAR 2003鲁棒字词识别数据集上的实验结果表明，该方法的二值化正确率达到87.4%，与场景字符串二值化的研究水平具有很强的竞争力。
This paper addresses the problem of binarizing multicolored character strings in scene images with complex backgrounds and heavy image degradations. The proposed method consists of three steps. The first step is combinatorial generation of binarized images via every dichotomization of K clusters obtained by K-means clustering of constituent pixels of an input image in the HSI color space. The second step is classification of each binarized image using deep neural network into two categories: character string and non-character string. The final step is selection of a single binarized image with the highest degree of character string as an optimal binarization result. Experimental results using ICDAR 2003 robust word recognition dataset show that the proposed method achieves a correct binarization rate of 87.4% that is highly competitive with the state of the art of binarization of scene character strings.