Name
Abstract | ||
|---|---|---|
This paper presents a novel effective method for line segment extraction using chain code differentiation. The resulting line segments are employed for shape feature extraction. Length distribution of the extracted segments along with distribution of the angle between adjacent segments are exploited to extract compact hybrid features. The extracted features are used for sketch-based shape retrieval. Comparative results obtained from six other well known methods within the literature have been discussed. Using MPEG-7 contour shape database (CE-1) as the test bed, the new proposed method shows significant improvement in retrieval performance for sketch-based shape retrieval. The Average Normalized Modified Retrieval Rank (ANMRR) is used as the performance indicator. Although the retrieval performance has been improved using the proposed method, its computational intensity and subsequently, its feature extraction time are slightly higher than some other methods. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1007/978-3-540-30503-3_34 | IWCIA |
Keywords | Field | DocType |
line segment extraction,sketch-based shape retrieval,retrieval performance,feature extraction time,digital contour,novel effective method,mpeg-7 contour shape database,performance indicator,new proposed method,shape feature extraction,feature extraction,chain code,test bed | Line segment,Computer vision,Normalization (statistics),Curvature,Computer science,Effective method,Image processing,Feature extraction,Artificial intelligence,Chain code,Sketch | Conference |
Volume | ISSN | ISBN |
3322 | 0302-9743 | 3-540-23942-1 |
Citations | PageRank | References |
2 | 0.44 | 16 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Abdolah Chalechale | 1 | 73 | 7.12 |
| Golshah Naghdy | 2 | 29 | 9.36 |
| Prashan Premaratne | 3 | 72 | 15.97 |