Interactive segmentation is one of the most popular and challenging segmentation methods. For the purpose to accurately extract objects from different images, this paper presents an interactive image segmentation method based on initial segmentation and region merging that the users only need to roughly mark the regions of the object and background by using markers. First, a Super-pixel based initial segmentation is applied to the original image. After that, the original image will be divided into some regions. Second, a novel region feature based on color histogram and Contourlet transform is computed for each region. Third, merge the regions which are similar to marked object region and merge the regions similar to marked background region, until there are only two kinds of regions - object and background. Compared with other algorithms, our experiment shows that the proposed scheme can reliably and rapidly extract the desired object from the complex background.
{"title":"Interactive Segmentation Based on Initial Segmentation and Region Merging","authors":"Guoheng Huang, Chi-Man Pun","doi":"10.1109/CGIV.2013.33","DOIUrl":"https://doi.org/10.1109/CGIV.2013.33","url":null,"abstract":"Interactive segmentation is one of the most popular and challenging segmentation methods. For the purpose to accurately extract objects from different images, this paper presents an interactive image segmentation method based on initial segmentation and region merging that the users only need to roughly mark the regions of the object and background by using markers. First, a Super-pixel based initial segmentation is applied to the original image. After that, the original image will be divided into some regions. Second, a novel region feature based on color histogram and Contourlet transform is computed for each region. Third, merge the regions which are similar to marked object region and merge the regions similar to marked background region, until there are only two kinds of regions - object and background. Compared with other algorithms, our experiment shows that the proposed scheme can reliably and rapidly extract the desired object from the complex background.","PeriodicalId":342914,"journal":{"name":"2013 10th International Conference Computer Graphics, Imaging and Visualization","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133583897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
3D animations have been widely used in the movie and gaming industries. However, the huge storage requirements of dynamic mesh data make it difficult for a number of applications such as rendering, transmitting over a network, etc.This study proposes a multiresolution representation for 3D animation. The results show that the coarse animation appears by using only 10% of the original faces. More detailed animation appears by using 80% of original faces, but only requires 3% of original storage space. Consequently, this approach enables a continuous level of detail for dynamic 3D mesh sequences.
{"title":"Progressive Animation Sequences","authors":"P. Lee","doi":"10.1109/CGIV.2013.32","DOIUrl":"https://doi.org/10.1109/CGIV.2013.32","url":null,"abstract":"3D animations have been widely used in the movie and gaming industries. However, the huge storage requirements of dynamic mesh data make it difficult for a number of applications such as rendering, transmitting over a network, etc.This study proposes a multiresolution representation for 3D animation. The results show that the coarse animation appears by using only 10% of the original faces. More detailed animation appears by using 80% of original faces, but only requires 3% of original storage space. Consequently, this approach enables a continuous level of detail for dynamic 3D mesh sequences.","PeriodicalId":342914,"journal":{"name":"2013 10th International Conference Computer Graphics, Imaging and Visualization","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122044653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
3D objects play a vital role in computer games, movies, TV, engineering design, and biological sciences. Researchers have studied 3D object retrieval techniques using 2D and 3D shape descriptors in the last several decades. In this paper, some of the most popular shape descriptors are reviewed. We first discuss the important criteria for a good shape descriptor. Then, we classify 2D and 3D shape descriptors into several categories. For each category, we review the state-of-the-art techniques along with their advantages and disadvantages. We also examine the recent contributions and improvements in these techniques and provide a comparison with other successful techniques based on previous literature and surveys. Finally we discuss the possible future directions.
{"title":"A Survey of 2D and 3D Shape Descriptors","authors":"I. Kazmi, L. You, Jian-Jun Zhang","doi":"10.1109/CGIV.2013.11","DOIUrl":"https://doi.org/10.1109/CGIV.2013.11","url":null,"abstract":"3D objects play a vital role in computer games, movies, TV, engineering design, and biological sciences. Researchers have studied 3D object retrieval techniques using 2D and 3D shape descriptors in the last several decades. In this paper, some of the most popular shape descriptors are reviewed. We first discuss the important criteria for a good shape descriptor. Then, we classify 2D and 3D shape descriptors into several categories. For each category, we review the state-of-the-art techniques along with their advantages and disadvantages. We also examine the recent contributions and improvements in these techniques and provide a comparison with other successful techniques based on previous literature and surveys. Finally we discuss the possible future directions.","PeriodicalId":342914,"journal":{"name":"2013 10th International Conference Computer Graphics, Imaging and Visualization","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113942128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：