Name
Abstract | ||
|---|---|---|
Sketch-based image retrieval (SBIR) systems, which interactively search photo collections using free-hand sketches depicting shapes, have attracted much attention recently. In most existing SBIR techniques, the color images stored in a database are first transformed into corresponding sketches. Then, features of the sketches are extracted to generate the sketch visual words for later retrieval. However, transforming color images to sketches will normally incur loss of information, thus decreasing the final performance of SBIR methods. To address this problem, we propose a new method called M-SBIR. In M-SBIR, besides sketch visual words, we also generate a set of visual words from the original color images. Then, we leverage the mapping between the two sets to identify and remove sketch visual words that cannot describe the original color images well. We demonstrate the performance of M-SBIR on a public data set. We show that depending on the number of different visual words adopted, our method can achieve 9.8 similar to 13.6% performance improvement compared to the classic SBIR techniques. In addition, we show that for a database containing multiple color images of the same objects, the performance of M-SBIR can be further improved via some simple techniques like co-segmentation. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1007/978-3-319-51814-5_22 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
SBIR,Visual word,Mapping,Co-segmentation,M-SBIR | Computer vision,Information retrieval,Computer science,Image retrieval,Artificial intelligence,Sketch,Performance improvement,Visual Word | Conference |
Volume | ISSN | Citations |
10133 | 0302-9743 | 3 |
PageRank | References | Authors |
0.39 | 18 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jianwei Niu | 1 | 1643 | 141.54 |
| Jun Ma | 2 | 47 | 19.80 |
| Jie Lu | 3 | 3 | 0.73 |
| Xuefeng Liu | 4 | 4 | 1.08 |
| Zeyu Zhu | 5 | 3 | 0.73 |