Abstract | ||
---|---|---|
Feature extraction methods have an important role in image classification. In this paper, a hybrid texture feature descriptor is proposed by utilizing the attributes of two complementary features, PRICoLBP and LPQ. PRICoLBP performs well in the case of geometric and photometric variations however it does not properly express the local texture of an image, while LPQ method performs well for the local structure of an image. We propose to use the hybrid scheme by combining the properties of PRICoLBP and LPQ and name it as Pair wise Rotation Invariant Co-occurrence Local Phase Quantization (PRICLPQ). Standard texture and material datasets have been used to verify the robustness of proposed hybrid scheme. The experiments show that the proposed hybrid scheme outperforms the state-of-the-art feature extraction methods like LBP, LPQ, CLBP, LBPV, SIFT, MSLBP, Lazebnik and PRICoLBP in term of accuracy. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/CIS.2015.22 | CIS |
Keywords | Field | DocType |
Local Phase Quantization, Texture classificatio, Feature extrection | Scale-invariant feature transform,Feature detection (computer vision),Computer science,Artificial intelligence,Contextual image classification,Computer vision,Pattern recognition,Feature (computer vision),Image texture,Support vector machine,Feature extraction,Hybrid image,Machine learning | Conference |
Citations | PageRank | References |
1 | 0.36 | 22 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hassan Dawood | 1 | 67 | 14.45 |
Hussain Dawood | 2 | 53 | 12.90 |
Ping Guo | 3 | 601 | 85.05 |