Benchmarking KAZE and MCM for Multiclass Classification
arXiv:1505.05240v1
Originality Synthesis-oriented
AI Analysis
This addresses object classification for computer vision applications, but it is incremental as it combines existing techniques.
The paper tackled multiclass object classification by fusing KAZE and SIFT features, showing that this integration outperforms state-of-the-art methods.
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.