针对JSEG算法在图像分割中出现的明显过分割现象,提出一种基于边缘信息的JSEG[1]改进方法。该方法首先将图像的颜色空间转换为LUV颜色空间,用PGF(Peer Group Filtering)[2]算法对图像进行平滑去噪,用分裂算法确定图像的类数,用GLA(Gener...针对JSEG算法在图像分割中出现的明显过分割现象,提出一种基于边缘信息的JSEG[1]改进方法。该方法首先将图像的颜色空间转换为LUV颜色空间,用PGF(Peer Group Filtering)[2]算法对图像进行平滑去噪,用分裂算法确定图像的类数,用GLA(Generalized Lloyd Algorithm)[3]算法完成量化,生成"类图"。然后计算每个像素的J值,并利用Canny算子检测的边缘信息,对J值进行修正,计算每个像素的局部相似程度,并在不同的尺寸下构建J图像,这样就能反映出最有可能的边界位置。最后在J图像上进行种子区域增长,直到获得最终的分割结果。实验结果表明该方法可以有效地改善JSEG算法在图像分割中存在的过分割现象。展开更多
Automatic labeling of the action held by the players in a live-in sports video is the main motivation of this paper. In this paper, we proposed a fuzzy-based action recognition system from a basketball sports image. T...Automatic labeling of the action held by the players in a live-in sports video is the main motivation of this paper. In this paper, we proposed a fuzzy-based action recognition system from a basketball sports image. This paper deals with the intellectual sports event action recognition from a live video stream. It required an intelligent system which would automatically and semantically label the action in the videos through machine understandability concept. The machine knowledge can be feed through the domain ontology of particular sports event. The major required component for this kind of system is an efficient image analysis component and automation action labelling component. The image is labelled using Type-2 Fuzzy set concept.展开更多
An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift ...An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift （AMS） based clustering is used for nonparametric clustering of image data set. The clustering results are used to construct Gaussian mixture modelling （GMM） of image data for the calculation of soft J value. The region growing algorithm used in JSEG is then applied in segmenting the image based on the multiscale soft J-images. Experiments show that the synergism of JSEG and the soft classification based on AMS based clustering and GMM overcomes the limitations of JSEG successfully and is more robust.展开更多
基金supported by the 863 High Technology Program of the People’s Republic of China under Grant Nos.2007AA12Z148 and 2007AA12Z181the National Natural Science Foundation of China under Grant Nos.40771139 and 40523005
文摘针对JSEG算法在图像分割中出现的明显过分割现象,提出一种基于边缘信息的JSEG[1]改进方法。该方法首先将图像的颜色空间转换为LUV颜色空间,用PGF(Peer Group Filtering)[2]算法对图像进行平滑去噪,用分裂算法确定图像的类数,用GLA(Generalized Lloyd Algorithm)[3]算法完成量化,生成"类图"。然后计算每个像素的J值,并利用Canny算子检测的边缘信息,对J值进行修正,计算每个像素的局部相似程度,并在不同的尺寸下构建J图像,这样就能反映出最有可能的边界位置。最后在J图像上进行种子区域增长,直到获得最终的分割结果。实验结果表明该方法可以有效地改善JSEG算法在图像分割中存在的过分割现象。
文摘Automatic labeling of the action held by the players in a live-in sports video is the main motivation of this paper. In this paper, we proposed a fuzzy-based action recognition system from a basketball sports image. This paper deals with the intellectual sports event action recognition from a live video stream. It required an intelligent system which would automatically and semantically label the action in the videos through machine understandability concept. The machine knowledge can be feed through the domain ontology of particular sports event. The major required component for this kind of system is an efficient image analysis component and automation action labelling component. The image is labelled using Type-2 Fuzzy set concept.
文摘An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift （AMS） based clustering is used for nonparametric clustering of image data set. The clustering results are used to construct Gaussian mixture modelling （GMM） of image data for the calculation of soft J value. The region growing algorithm used in JSEG is then applied in segmenting the image based on the multiscale soft J-images. Experiments show that the synergism of JSEG and the soft classification based on AMS based clustering and GMM overcomes the limitations of JSEG successfully and is more robust.
