Enhancing image registration performance by incorporating distribution and spatial distance of local descriptors

Lv, Guohua; Teng, Shyh Wei; Lu, Guojun

doi:10.1016/j.patrec.2018.01.008

Cited by 8 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With N keypoint matches, there exist C 3 N combinations of keypoint triangles in both of query and target images. As N increases, the number of keypoint triangles C 3 N goes up dramatically. To ensure that the computational cost of the proposed technique is acceptable, it is vital to limit the number of keypoint triplets.…”

Section: Step 2: Refining Keypoint Matches With Self-similaritymentioning

confidence: 99%

“…The recall is defined as recall = number of correct matches found number of correspondences × 100%. (10) The recall vs 1-precision curve is generally plotted for a particular image pair [3], [16]. To make statistics on a set of image pairs, the area under the recall vs 1-precision curve [35] will be used.…”

Section: A Evaluation Metricsmentioning

confidence: 99%

“…The proposed technique is evaluated against S-SIFT and IS-SIFT thoroughly on a few image registration datasets by using both accuracy and recall. In the existing literature, IS-SIFT is mostly evaluated using accuracy and recall vs 1-precision curves of sample image pairs [1], [3], [5], [23], [24]. In addition to matching accuracy, this paper is the first work that utilizes the area under the recall vs 1-precision curve to make quantitative comparisons on S-SIFT and its improvements.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Self-Similarity and Symmetry With SIFT for Multi-Modal Image Registration

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper presents a novel feature-based multi-modal image registration technique called selfsimilarity and symmetry with a scale invariant feature transform (3S-SIFT). The proposed technique has the following two main components. First, a ubiquitous problem existing in registering multi-modal images, gradient reversal, is well studied and addressed. Second, the proposed technique takes into account selfsimilarity information between keypoint triangles, which is conducive to enhancing the registration accuracy. Moreover, a simplified version of 3S-SIFT called 4S-SIFT is proposed as a pruning technique for feature matching. The proposed techniques are generally applicable to the registration of multi-modal images with changes in scale, rotation, and translation. The experiments have been conducted on a set of benchmark datasets in the domain of image registration, demonstrating that the proposed techniques achieve the stateof-the-art performance in both matching accuracy and recall. INDEX TERMS Multi-modal image registration, local descriptors, self-similarity, symmetric SIFT.

show abstract

Section: Step 2: Refining Keypoint Matches With Self-similaritymentioning

confidence: 99%

Section: A Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Similarity and Symmetry With SIFT for Multi-Modal Image Registration

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The precision in Equation (10) is simply the equivalent of accuracy defined in Equation (8). The recall vs 1-precision curve is generally plotted for a particular image pair [6,20]. To make statistics on a set of image pairs, the area under the recall vs 1-precision curve [38] will be used.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Local image features [1] are of vital importance in the field of image processing and have been widely studied in various applications such as object recognition [2], image retrieval [3] and image registration [4][5][6][7][8][9][10][11]. A local image feature [12,13] such as a keypoint or corner is encoded into a local descriptor by representing image information within a local region such as color, gradient and shape [14].…”

Section: Introductionmentioning

confidence: 99%

Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors

Dong¹,

Han²,

Lv³

et al. 2019

Symmetry

Self Cite

View full text Add to dashboard Cite

The utilization of gradient information is a key issue in building Scale Invariant Feature Transform (SIFT)-like descriptors. In the literature, two types of gradient information, i.e., Gradient Magnitude (GM) and Gradient Occurrence (GO), are used for building descriptors. However, both of these two types of gradient information have limitations in building and matching local image descriptors. In our prior work, a strategy of combining these two types of gradient information was proposed to intersect the keypoint matches which are obtained by using gradient magnitude and gradient occurrence individually. Different from this combination strategy, this paper explores novel strategies of weighting these two types of gradient information to build new descriptors with high discriminative power. These proposed weighting strategies are extensively evaluated against gradient magnitude and gradient occurrence as well as the combination strategy on a few image registration datasets. From the perspective of building new descriptors, experimental results will show that each of the proposed strategies achieve higher matching accuracy as compared to both GM-based and GO-based descriptors. In terms of recall results, one of the proposed strategies outperforms both GM-based and GO-based descriptors.

show abstract

Improved Nearest Neighbor Distance Ratio for Matching Local Image Descriptors

Han

Ren

et al. 2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

Enhancing image registration performance by incorporating distribution and spatial distance of local descriptors

Cited by 8 publications

References 30 publications

Self-Similarity and Symmetry With SIFT for Multi-Modal Image Registration

Self-Similarity and Symmetry With SIFT for Multi-Modal Image Registration

Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors

Improved Nearest Neighbor Distance Ratio for Matching Local Image Descriptors

Contact Info

Product

Resources

About