Validation of a Skin-Lesion Image-Matching Algorithm Based on Computer Vision Technology

2016 ◽  
Vol 22 (1) ◽  
pp. 45-50 ◽  
Author(s):  
Raymond H. Chen ◽  
Magnus Snorrason ◽  
Shelley M. Enger ◽  
Eslam Mostafa ◽  
Justin M. Ko ◽  
...  
Keyword(s):  
Computer Vision ◽  
Skin Lesion ◽  
Image Matching ◽  
Matching Algorithm ◽  
Computer Vision Technology

scholarly journals POOR TEXTURAL IMAGE MATCHING BASED ON GRAPH THEORY

2016 ◽  
Vol XLI-B3 ◽  
pp. 741-747 ◽  
Author(s):  
Shiyu Chen ◽  
Xiuxiao Yuan ◽  
Wei Yuan ◽  
Yang Cai
Keyword(s):  
Computer Vision ◽  
Image Matching ◽  
Urban Areas ◽  
Graph Matching ◽  
Recall Rate ◽  
Edge Weight ◽  
Matching Problem ◽  
Matching Algorithm ◽  
Low Contrast ◽  
Series Of Experiments

Image matching lies at the heart of photogrammetry and computer vision. For poor textural images, the matching result is affected by low contrast, repetitive patterns, discontinuity or occlusion, few or homogeneous textures. Recently, graph matching became popular for its integration of geometric and radiometric information. Focused on poor textural image matching problem, it is proposed an edge-weight strategy to improve graph matching algorithm. A series of experiments have been conducted including 4 typical landscapes: Forest, desert, farmland, and urban areas. And it is experimentally found that our new algorithm achieves better performance. Compared to SIFT, doubled corresponding points were acquired, and the overall recall rate reached up to 68%, which verifies the feasibility and effectiveness of the algorithm.

scholarly journals POOR TEXTURAL IMAGE MATCHING BASED ON GRAPH THEORY

2016 ◽  
Vol XLI-B3 ◽  
pp. 741-747
Author(s):  
Shiyu Chen ◽  
Xiuxiao Yuan ◽  
Wei Yuan ◽  
Yang Cai
Keyword(s):  
Computer Vision ◽  
Image Matching ◽  
Urban Areas ◽  
Graph Matching ◽  
Recall Rate ◽  
Edge Weight ◽  
Matching Problem ◽  
Matching Algorithm ◽  
Low Contrast ◽  
Series Of Experiments

Image matching lies at the heart of photogrammetry and computer vision. For poor textural images, the matching result is affected by low contrast, repetitive patterns, discontinuity or occlusion, few or homogeneous textures. Recently, graph matching became popular for its integration of geometric and radiometric information. Focused on poor textural image matching problem, it is proposed an edge-weight strategy to improve graph matching algorithm. A series of experiments have been conducted including 4 typical landscapes: Forest, desert, farmland, and urban areas. And it is experimentally found that our new algorithm achieves better performance. Compared to SIFT, doubled corresponding points were acquired, and the overall recall rate reached up to 68%, which verifies the feasibility and effectiveness of the algorithm.

An Image Matching Algorithm Based on SCCH Feature Descriptor

2011 ◽  
Vol 33 (9) ◽  
pp. 2152-2157 ◽  
Author(s):  
Yong-he Tang ◽  
Huan-zhang Lu ◽  
Mou-fa Hu
Keyword(s):  
Image Matching ◽  
Feature Descriptor ◽  
Matching Algorithm

scholarly journals A Review on Computer Vision Technology for Monitoring Poultry Farm – Application, Hardware, and Software

IEEE Access ◽  
2020 ◽  
pp. 1-1
Author(s):  
Nur Syazarin Natasha Abd Aziz ◽  
Salwani Mohd Daud ◽  
Rudzidatul Akmam Dziyauddin ◽  
Mohamad Zulkefli Adam ◽  
Azizul Azizan
Keyword(s):  
Computer Vision ◽  
Poultry Farm ◽  
Computer Vision Technology

scholarly journals Transporting Deformations of Face Emotions in the Shape Spaces: A Comparison of Different Approaches

2021 ◽  
Author(s):  
Paolo Piras ◽  
Valerio Varano ◽  
Maxime Louis ◽  
Antonio Profico ◽  
Stanley Durrleman ◽  
...  
Keyword(s):  
Computer Vision ◽  
Shape Change ◽  
Surface Matching ◽  
Human Face ◽  
Matching Algorithm ◽  
Mathematical Procedure ◽  
Shape Spaces ◽  
Diffeomorphic Deformation ◽  
Common Application ◽  
Scientific Fields

AbstractStudying the changes of shape is a common concern in many scientific fields. We address here two problems: (1) quantifying the deformation between two given shapes and (2) transporting this deformation to morph a third shape. These operations can be done with or without point correspondence, depending on the availability of a surface matching algorithm, and on the type of mathematical procedure adopted. In computer vision, the re-targeting of emotions mapped on faces is a common application. We contrast here four different methods used for transporting the deformation toward a target once it was estimated upon the matching of two shapes. These methods come from very different fields such as computational anatomy, computer vision and biology. We used the large diffeomorphic deformation metric mapping and thin plate spline, in order to estimate deformations in a deformational trajectory of a human face experiencing different emotions. Then we use naive transport (NT), linear shift (LS), direct transport (DT) and fanning scheme (FS) to transport the estimated deformations toward four alien faces constituted by 240 homologous points and identifying a triangulation structure of 416 triangles. We used both local and global criteria for evaluating the performance of the 4 methods, e.g., the maintenance of the original deformation. We found DT, LS and FS very effective in recovering the original deformation while NT fails under several aspects in transporting the shape change. As the best method may differ depending on the application, we recommend carefully testing different methods in order to choose the best one for any specific application.

An Image Matching Algorithm Based on SIFT and Invariability of Feature Points Set

2011 ◽  
Vol 121-126 ◽  
pp. 701-704
Author(s):  
Xue Tong Wang ◽  
Yao Xu ◽  
Feng Gao ◽  
Jing Yi Bai
Keyword(s):  
Image Matching ◽  
Singular Value ◽  
Feature Points ◽  
Matching Algorithm ◽  
Candidate Feature

Feature points can be used to match images. Candidate feature points are extracted through SIFT firstly. Then feature points are selected from candidate points through singular value decomposing. Distance between feature points sets is computed According to theory of invariability of feature points set, images are matched if the distance is less than a threshold. Experiment showed that this algorithm is available.

Sign in / Sign up

Export Citation Format

Share Document