Abstract | ||
---|---|---|
The problem of content-based image retrieval is becoming essential in many real-world applications, mostly due to the growth in size of modern image databases. In particular, this work addresses the retrieval of trademark emblems, which is key for detecting trademark infringement. A common approach that proved suitable for this task, is to encode emblems using shape descriptors and Zernike complex moments. This work focuses on their study, proposing a two-fold contribution. First, we present some modifications to Zernike complex moments and then we explore the use of different comparison metrics. Both have shown to report improvements in retrieved results and in execution time. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-16687-7_15 | CIARP |
Keywords | Field | DocType |
modern image databases,complex moment,execution time,zernike moment,trademark infringement,trademark emblem,real-world application,different comparison metrics,content-based image retrieval,zernike complex moment,content-based emblem retrieval,common approach | Computer vision,ENCODE,Emblem,Information retrieval,Computer science,Image retrieval,Trademark,Zernike polynomials,Artificial intelligence,Execution time,Trademark infringement | Conference |
Volume | ISSN | ISBN |
6419 | 0302-9743 | 3-642-16686-5 |
Citations | PageRank | References |
1 | 0.38 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ezequiel Cura | 1 | 1 | 0.38 |
Mariano Tepper | 2 | 68 | 12.80 |
Marta Mejail | 3 | 76 | 18.68 |