Abstract | ||
---|---|---|
In this paper, we propose a novel approach for feature generation by appropriately fusing KAZE and SIFT features. We then use this feature set along with Minimal Complexity Machine(MCM) for object classification. We show that KAZE and SIFT features are complementary. Experimental results indicate that an elementary integration of these techniques can outperform the state-of-the-art approaches. |
Year | Venue | Field |
---|---|---|
2015 | CoRR | Scale-invariant feature transform,Pattern recognition,Computer science,Feature set,Feature generation,Artificial intelligence,Machine learning,Benchmarking,Multiclass classification |
DocType | Volume | Citations |
Journal | abs/1505.05240 | 0 |
PageRank | References | Authors |
0.34 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Siddharth Srivastava | 1 | 9 | 5.89 |
prerana mukherjee | 2 | 10 | 10.94 |
Brejesh Lall | 3 | 85 | 43.42 |