Name
Abstract | ||
|---|---|---|
This paper presents an effective feature descriptor that integrates intensity order and textures in multi support regions into a compact vector. We first propose the novel Intensity Order Local Binary Pattern (IO-LBP) to encode the texture around each point in an interest region, divide the region according to pixel intensity orders, and then pool patterns to these segments. The IO-LBP descriptor is built by concatenating histograms of all segments together. Besides, multi support regions are used to further improve the discriminative ability. The proposed descriptor can effectively capture both local and global information of an interest region and thus high performance is expected. We evaluate IO-LBP on the standard Oxford dataset and additional images of shadows. Experimental results show that our method is not only invariant to common photometric and geometric transformations, such as illumination change, image rotation, but also robust to complex illumination effects caused by shadows. A significant improvement in performance, comparing to state-of-the-art descriptors, is achieved by IO-LBP. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CW.2013.9 | CW |
Keywords | Field | DocType |
high performance,image coding,illumination change,multi support region,intensity order local binary,binary pattern,effective feature descriptor,image resolution,multisupport regions,io-lbp descriptor,standard oxford dataset,global information capture,local binary pattern,image rotation,effective feature description,local information capture,discriminative ability,feature extraction,pixel intensity orders,proposed descriptor,feature description,photometric transformations,geometric transformations,texture encoding,complex illumination effects,intensity order,complex illumination effect,image texture,interest region,texture,intensity order local binary pattern | Histogram,Computer vision,Pattern recognition,Computer science,Image texture,Transformation geometry,Local binary patterns,Feature extraction,Invariant (mathematics),Artificial intelligence,Pixel,Discriminative model | Conference |
ISBN | Citations | PageRank |
978-1-4799-2245-1 | 3 | 0.36 |
References | Authors | |
17 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Thao Nguyen | 1 | 187 | 27.73 |
| Bac H. Le | 2 | 495 | 45.11 |
| Kazunori Miyata | 3 | 161 | 41.73 |