摘要
版面分割是版面分析的重要组成部分,实现复杂版面的快速、有效分割是目前亟待解决的问题。针对复杂版面分割问题,文中将相位一致性统计特征和改进灰度共生矩阵的纹理特征相结合,得到一种新的组合特征向量。将该组合特征向量作为训练样本,最终得到基于支持向量机的复杂图像分割算法。实验结果表明,与其他方法相比,基于支持向量机的方法在版面分割任务中表现出了较好的召回率与准确率,能有效区分复杂图像中的各类不同区域,该方法为如何提高复杂版面的分割准确率提供了理论参考。
The layout segmentation is an important part of the layout analysis.The rapid and effective segmentation of complex layout is an urgent problem to be solved.As for the problem of complex layout segmentation,a new combined feature vector is obtained in combination with the phase consistency statistical features and the texture features of the improved gray level co⁃occurrence matrix.The combined feature vector is taken as the training sample to obtain the complex image segmentation algorithm based on the support vector machine.The experimental results show that in comparison with other methods,the method based on the support vector machine has better recall rate and accuracy in the layout segmentation task,which can effectively distinguish the different regions in the complex images.It provides a theoretical reference for how to improve the segmentation accuracy of the complex layouts.
作者
逯瑜娇
方建军
张姗
刘彩霞
LU Yujiao;FANG Jianjun;ZHANG Shan;LIU Caixia(Beijing Key Laboratory of Information Service Engineering,Beijing Union University,Beijing 100101,China;School of Urban Rail Transit and Logistics,Beijing Union University,Beijing 100101,China)
出处
《现代电子技术》
北大核心
2020年第2期149-153,共5页
Modern Electronics Technique
基金
国家自然科学基金（61602041）
北京市属高等学校高层次人才引进与培养计划(CIT&TCD20150314)
关键词
版面分割
支持向量机
特征向量
图像分割算法
图像识别
对比验证
layout segmentation
support vector machine
feature vector
image segmentation method
image recognition
comparison verification
