Semi-automatic video object segmentation
Item Usage Stats
MetadataShow full item record
Content-based iunetionalities form the core of the future multimedia applications. The new multimedia standard MPEG-4 provides a new form of interactivity with coded audio-visual data. The emerging standard MPEG-7 specifies a common description of various types of multimedia information to index the data for storage and retrieval. However, none of these standards specifies how to extract the content of the multimedia data. Video object segmentation addresses this task and tries to extract semantic objects from a scene. Two tyj)es of video object segmentation can be identified: unsupervised and supervised. In unsupervised méthods the user is not involved in any step of the process. In supervised methods the user is requested to supply additional information to increase the quality of the segmentation. The proposed weakly supervised still image segmentation asks the user to draw a scribble over what he defines as an object. These scribbles inititate the iterative method. .A.t each iteration the most similar regions are merged until the desired numljer of regions is reached. The proposed .segmentation method is inserted into the unsupervised COST211ter .A-ualysis Model (.A.M) for video object segmentation. The AM is modified to handh' the sujiervision. The new semi-automatic AM requires the user intei actimi for onl>· first frame of the video, then segmentation and object tracking is doin' automatically. The results indicate that the new semi-automatic AM constituK's a good tool for video oliject segmentation.
Video object segmentation
Showing items related by title, author, creator and subject.
Tosun, Akif Burak; Sokmensuer, C.; Gündüz-Demir, Çiğdem (IEEE, 2010)This paper presents a new algorithm for the unsupervised segmentation of tissue images. It relies on using the spatial information of cytological tissue components. As opposed to the previous study, it does not only use ...
Koyuncu, Can Fahrettin; Durmaz, İrem; Çetin-Atalay, Rengül; Gündüz-Demir, Çiğdem (IEEE Computer Society, 2014-04)Automated cell imaging systems have been proposed for faster and more reliable analysis of biological events at the cellular level. The first step of these systems is usually cell segmentation whose success affects the ...
Object-oriented texture analysis for the unsupervised segmentation of biopsy images for cancer detection Tosun, A. B.; Kandemir, M.; Sokmensuer, C.; Gunduz Demir, C. (Elsevier BV, 2009-06)Staining methods routinely used in pathology lead to similar color distributions in the biologically different regions of histopathological images. This causes problems in image segmentation for the quantitative analysis ...