Weighted feature fusion for content-based image retrieval

Omurhan A. Soysal; Emre Sumer

doi:10.1117/12.2242956

Translator Disclaimer

11 July 2016 Weighted feature fusion for content-based image retrieval

Omurhan A. Soysal, Emre Sumer

Author Affiliations +

Proceedings Volume 10011, First International Workshop on Pattern Recognition; 100110S (2016) https://doi.org/10.1117/12.2242956
Event: First International Workshop on Pattern Recognition, 2016, Tokyo, Japan

Abstract

The feature descriptors such as SIFT (Scale Invariant Feature Transform), SURF (Speeded-up Robust Features) and ORB (Oriented FAST and Rotated BRIEF) are known as the most commonly used solutions for the content-based image retrieval problems. In this paper, a novel approach called ”Weighted Feature Fusion” is proposed as a generic solution instead of applying problem-speciﬁc descriptors alone. Experiments were performed on two basic data sets of the Inria in order to improve the precision of retrieval results. It was found that in cases where the descriptors were used alone the proposed approach yielded 10-30% more accurate results than the ORB alone. Besides, it yielded 9-22% and 12-29% less False Positives compared to the SIFT alone and SURF alone, respectively.

Citation Download Citation

Omurhan A. Soysal and Emre Sumer "Weighted feature fusion for content-based image retrieval", Proc. SPIE 10011, First International Workshop on Pattern Recognition, 100110S (11 July 2016); https://doi.org/10.1117/12.2242956

ACCESS THE FULL ARTICLE