多视觉特征结合有约束简化群优化的显著性目标检测  

Salient Object Detection of Multi-visual Feature Combining with Constrained Simplified Swarm Optimization

作　　者：花卉[1] 

机构地区：[1]金陵科技学院计算机工程学院,南京211169

出　　处：《计算机工程》2015年第11期257-262,共6页Computer Engineering

基　　金：江苏省高校自然科学基金资助项目(11KJD520006);江苏省教育科学"十二五"规划基金资助项目(D/2013/01/068)

摘　　要：针对一般显著性目标检测(SOD)方法容易受背景区域影响造成识别精度低下的问题,提出一种基于多视觉特征并结合有约束简化群优化的显著性目标检测方法。该方法获取3个低级视觉特征,即多尺度对比度、中心环绕直方图和颜色空间分布,利用有约束的简化群优化检测出最优权重向量,并将其与3个视觉特征结合以获取显著图,使用显著图在图像背景中提取出显著性目标。为了有效地抑制图像中的背景区域,定义一个简单的适应度函数以凸显边界目标。运用定量和定性方法在MARA SOD数据库上进行仿真实验,结果表明,与模糊聚类、低秩矩阵恢复和稀疏重构等方法相比,该方法能获得较高的识别精度和查全率。As the issue of low recognition precision of general Salient Object Detection （SOD） method that is vulnerable to the impact of the background area, method of SOD using constrained Simplified Swarm Optimization （SSO） and multi-visual feature is proposed. Three visual features such as multi-scale contrast, center-surround histogram and color spatial distribution are obtained from the given image. Constrained Simplified Swarm Optimization（CSSO） is used to determine an optimal weight vector with combining these features to obtain saliency map to distinguish a salient object. A salient target is extracted from the salient map in the image background. In order to effectively suppress the background in the image area,a simple fitness function is defined to highlight the clear target containing boundary. Simulation is on MARA SOD database using quantitative and qualitative methods for evaluation. Experimental results show that the recognition precision and the recall rate of the proposed method are higher than that of the fuzzy clustering method, low- rank matrix recovery method and sparse reconstruction method.

关 键 词：显著性目标检测 简化群优化 视觉特征 最优权重向量 适应度函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]