摘要
图像对象定位可提供准确的对象区域,有效提高图像对象识别和分类准确率.基于此,文中提出基于多重图像分割评价的图像对象定位方法.通过图像的多层次分割,确定图像不同区域之间的语义约束关系,应用此约束关系对不同层次的对象区域模式进行频繁项集挖掘和评分,并按照此模式评分逐次合并每层图像分割中的重要区域,最终实现整个对象区域的精确定位.MSRC和GRAZ的定位实验表明,文中方法可有效定位图像的前景目标,在Caltech图像目标分类实验中也证明文中方法的有效性.
Image objects localization detects object regions accurately and therefore it can improve accuracies of image objects recognition and classification. In this paper, an image object localization method based on multiple segmentation regions scoring is proposed. Through the image of the multi-level segmentation, the semantic constraints among different image regions through multi-level segmentation results is confirmed. By these constraints, frequent itemset mining and scoring strategy are applied on different levels of object region pattern. According to pattern scores of regions, important regions in each segmentation levels are merged successively to localize the whole image object region. Experimental results on MSRC and GRAZ datasets show that the proposed method can localize image foreground object accurately, and its validity is verified on Caltech256 dataset.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2015年第8期760-768,共9页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.61005017)资助
关键词
图像分割
对象定位
视觉词袋
频繁项集挖掘
重要区域评分
Image Segmentation, Object Localization, Bag of Visual Word, Frequent hemset Mining,Key Region Scoring