利用小波变换和K均值聚类实现字幕区域分割  

Segmentation of Caption Region Using Wavelet Transform and K-Mean Clustering

作　　者：王建宇[1] 张峰[1] 周献中[2] 史迎春[3] 骆文[1] 

机构地区：[1]南京理工大学自动化学院,南京210094 [2]南京大学工程管理学院,南京210093 [3]武汉通信指挥学院仿真中心,武汉430010

出　　处：《计算机辅助设计与图形学学报》2006年第10期1508-1512,共5页Journal of Computer-Aided Design & Computer Graphics

基　　金：江苏省自然科学基金(BK2004137)

摘　　要：提出一种字幕区域分割算法.首先对图像做小波变换和重构,并抽取字幕区域特征,再分块计算统计特征;然后对子块进行K均值聚类,实现字幕区域分割.与已有算法相比,该算法简单,不需要设置阈值.实验结果表明,即使在复杂背景下,对于字体、大小和位置都不确定的字幕,该算法仍具有良好的分割效果.An algorithm is proposed in the paper to segment caption region. By the algorithm, firstly, the caption features are extracted by wavelet transformation and reconstruction on the image, and secondly, statistic features are calculated block by block. At last blocks are classified by K-mean clustering method. In comparison with other algorithms, the algorithm is simpler and no requirement for setting any threshold. Experimental results show that the proposed algorithm performs well, even for captions with unknown font, size, and position.

关 键 词：字幕分割 小波变换 K均值聚类 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]