Abstract | ||
---|---|---|
An interactive color image segmentation technique is presented for use in applications where the segmented regions correspond to meaningful objects, such as for image retrieval. The proposed technique utilizes the perceptual HSI (hue, saturation, intensity) color space. The scheme incorporates user interaction so that the best possible results can be achieved. Interaction with the user allows the segmentation algorithm to start efficiently and to refine the results. Interaction is performed for the key images (usually the first image or those where new ojects enter the scene) of the video-telephony sequence. The user is allowed to identify on the screen the relevant regions by marking their seeds. The user guidance can be given by the sender, by the receiver, or by both. The effectiveness of the algorithm is found to be much improved over techniques used in the past. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1007/3-540-48762-X_13 | VISUAL |
Keywords | Field | DocType |
meaningful object,segmentation algorithm,interactive color image segmentation,user guidance,new ojects,proposed technique,region-based color image,image retrieval,color space,key image,user interaction | Computer vision,Scale-space segmentation,Color space,Segmentation,Computer science,Image retrieval,Hue,Image processing,Image segmentation,Artificial intelligence,Color image | Conference |
ISBN | Citations | PageRank |
3-540-66079-8 | 1 | 0.40 |
References | Authors | |
5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicolaos Ikonomakis | 1 | 1 | 0.74 |
Kostas N. Plataniotis | 2 | 34 | 7.69 |
Anastasios N. Venetsanopoulos | 3 | 1104 | 123.13 |