CSIFT: A SIFT Descriptor with Color Invariant Characteristics

Abdel-Hakim, Alaa E.; Farag, Aly A.

doi:10.1109/cvpr.2006.95

Cited by 381 publications

(209 citation statements)

References 20 publications

Supporting

Mentioning

203

Contrasting

Unclassified

Order By: Relevance

“…The invariants derived in the work have been successfully used as image descriptors in place of grayscale for solving keypoint correspondence [9]. Among the various color-based image descriptors, it has been reported to have robust results for use in object and scene matching [10], [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching

Kobayashi

Kameyama

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn camera-based object recognition and classification, surface color is one of the most important characteristics. However, apparent object color may differ significantly according to the illumination and surface conditions. Such a variation can be an obstacle in utilizing color features. Geusebroek et al.'s color invariants can be a powerful tool for characterizing the object color regardless of illumination and surface conditions.In this work, we analyze the estimation process of the color invariants from RGB images, and propose a novel invariant feature of color based on the elementary invariants to meet the circular continuity residing in the mapping between colors and their invariants. Experiments show that the use of the proposed invariant in combination with luminance, contributes to improve the retrieval performances of partial object image matching under varying illumination conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Therefore, we employ Scale-Invariant Feature Transform (SIFT) [20] as local descriptors of the variation of illumination invariant features. SIFT using illumination invariant features is known as Colored SIFT : (CSIFT) [9]. In CSIFT, local features can utilize color information with robustness to the illumination variation.…”

Section: Local Descriptormentioning

confidence: 99%

A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching

Kobayashi

Kameyama

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Abdel-Hakim et al [9] firstly made use of color invariant H as input for SIFT to generate colored SIFT descriptors. While Burghouts et at.…”

Section: Descriptor Buildingmentioning

confidence: 99%

“…Since more stable keypoints mean better performance [9], CBRISK aims at to detect keypoints invariant to illumination and scale changes. For each keypoint, a colored local invariant binary feature descriptor is built to distinctively characterize the local region around the keypoint.…”

Section: Colored Binary Robust Invariant Scalable Keypoints (Cbrisk)mentioning

confidence: 99%

See 1 more Smart Citation

CBRISK: Colored Binary Robust Invariant Scalable Keypoints

Jing

Han

et al. 2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYBRISK (Binary Robust Invariant Scalable Keypoints) works dramatically faster than well-established algorithms (SIFT and SURF) while maintaining matching performance. However BRISK relies on intensity, color information in the image is ignored. In view of the importance of color information in vision applications, we propose CBRISK, a novel method for taking into account color information during keypoint detection and description. Instead of grayscale intensity image, the proposed approach detects keypoints in the photometric invariant color space. On the basis of binary intensity BRISK (original BRISK) descriptor, the proposed approach embeds binary invariant color presentation in the CBRISK descriptors. Experimental results show that CBRISK is more discriminative and robust than BRISK with respect to photometric variation. key words: color space, photometric invariant, binary descriptor

show abstract