Graph-Based Methods for Retinal Mosaicing and Vascular Characterization

Aguilar, Wendy; Martínez-Pérez, M. Elena; Frauel, Yann; Escolano, Francisco; Lozano, Miguel Ángel; Espinosa-Romero, A.

doi:10.1007/978-3-540-72903-7_3

Cited by 28 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have improved our previous mosaicing results presented in [2] by using a new and larger set of images in order to get larger vessel tree views. The set of retinal images used in the present application was captured using a fundus camera with a 45°field-of-view (Zeiss VISUCAM Digital Camera).…”

Section: Feature Point Matchingmentioning

confidence: 90%

See 1 more Smart Citation

A robust Graph Transformation Matching for non-rigid registration

Aguilar

Frauel

Escolano

et al. 2009

Image and Vision Computing

Self Cite

152

114

View full text Add to dashboard Cite

Section: Feature Point Matchingmentioning

confidence: 90%

“…A series of retinal images of the same eye can be registered to form a mosaic image giving a wider view of the inside of the eye-ball. We have presented a previous work on the GTM matching algorithm in [2]. Some improvements and a deeper evaluation of its performance are included herein.…”

Section: Introductionmentioning

confidence: 99%

A robust Graph Transformation Matching for non-rigid registration

Aguilar

Frauel

Escolano

et al. 2009

Image and Vision Computing

Self Cite

152

114

View full text Add to dashboard Cite

“…In order to avoid the GA converges to the local minimum, we have designed another particular operation. Wendy Aguilar has proposed a simple K-NN graph [16] relying on finding nearest neighbors from candidate matches to eliminate the error matching point. We use the K-NN graph propose a special operator.…”

Section: E Pseudo Mutationmentioning

confidence: 99%

Non-rigid point matching via genetic algorithm searching

Liu

Wang

Tian

et al. 2015

2015 8th International Congress on Image and Signal Processing (CISP)

View full text Add to dashboard Cite

Abstract-Point sets registration, also known as point matching, is to find the one-to-one correspondence between two point sets as well as the related transformation. In comparison with most state-of-the-arts handling the rigid transformation between two point sets, in this paper, we focus on the more complex nonrigid transformation by considering it as a linear assignmentleast square problem. We design a non-rigid point matching algorithm by adopting the Genetic Algorithm (GA) to find an optimal solution of the liner assignment-least square problem, where we define a series of excellent Genetic operators. A population initialization method and a special genetic operator in this paper significantly improve the performance of the GA. The experimental results using public 2D point sets justify that Genetic Algorithms based point matching algorithm can achieve good performance in terms of large scale deformation and rotation.

show abstract

“…Graph transformational matching [6,7] relies on the hypothesis that outlying matchings in M may be iteratively removed: (i) select an outlying matching; (ii) remove matched features corresponding to the outlying matching, as well as this matching itself; (iii) recompute both median K-NN graphs. Structural disparity is approximated by computing the residual adjacency matrix R ¼j A À B j and selecting j out ¼ arg max j¼1...M P M i¼1 R ij , that is, the one which maximizes the number of different edges in both graphs.…”

Section: Size Of Consensus Graph and Gtmmentioning

confidence: 99%