An algorithm of parameters adaptive scale-invariant feature for high precision matching of multi-source remote sensing image

Wang, Guanghui; Zhang, Shubi; Wang, Huabin; Li, Canhai; Tang, Xinming; Tian, Jiaojiao; Tian, Jie

doi:10.1109/urs.2009.5137515

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [13], a set of SIFT parameters (sigma, contrast threshold, curvature threshold, octave, intervals, peak ratio, descriptor magnitude threshold, and match ratio) were adjusted using a parameter sweep by a graphical processing unit. A novel method for automatic determination of the main thresholds (contrast threshold, curvature ratio, and matching threshold) was proposed in [18] based on image information. In [19], the authors noted that facial images have no strict corners or lines, in contrast to other objects that have distinct structures and high contrast.…”

Section: Introductionmentioning

confidence: 99%

Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions

Mahamdioua

Bahaj²

2018

IET Computer Vision

View full text Add to dashboard Cite

The scale invariant feature transform (SIFT), which was proposed by David Lowe, is a powerful method that extracts and describes local features called keypoints from images. These keypoints are invariant to scale, translation, and rotation, and partially invariant to image illumination variation. Despite their robustness against these variations, strong lighting variation is a difficult challenge for SIFT-based facial recognition systems, where significant degradation of performance has been reported. To develop a robust system under these conditions, variation in lighting must be first eliminated. Additionally, SIFT parameter default values that remove unstable keypoints and inadequately matched keypoints are not well-suited to images with illumination variation. SIFT keypoints can also be incorrectly matched when using the original SIFT matching method. To overcome this issue, the authors propose propose a method for removing the illumination variation in images and correctly setting SIFT's main parameter values (contrast threshold, curvature threshold, and match threshold) to enhance SIFT feature extraction and matching. The proposed method is based on an estimation of comparative image lighting quality, which is evaluated through an automatic estimation of gamma correction value. Through facial recognition experiments, the authors find significant results that clearly illustrate the importance of the proposed robust recognition system.

show abstract

Section: Introductionmentioning

confidence: 99%