Contrast Independent Detection of Branching Points in Network-Like Structures
Many biomedical applications require the detection of branching structures in images. While several algorithms have been proposed for (semi-)automatic extraction of these structures, branching points usually need specific treatment. We propose a vector field-based approach to identify branching poin...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2012
|
| _version_ | 1797101706743382016 |
|---|---|
| author | Obara, B Fricker, M Grau, V |
| author_facet | Obara, B Fricker, M Grau, V |
| author_sort | Obara, B |
| collection | OXFORD |
| description | Many biomedical applications require the detection of branching structures in images. While several algorithms have been proposed for (semi-)automatic extraction of these structures, branching points usually need specific treatment. We propose a vector field-based approach to identify branching points in images. A vector field is calculated using a novel contrast-independent tensor representation based on local phase. Non-curvilinear structures, including junctions and end points, are detected using directional statistics of the principal orientation as defined by the tensor. Results on synthetic and real biomedical images show the robustness of the algorithm against changes in contrast, and its ability to detect junctions in highly complex images. © 2012 SPIE. |
| first_indexed | 2024-03-07T05:55:38Z |
| format | Journal article |
| id | oxford-uuid:ea6407ac-e388-4ab2-99c2-e3a112d92bc9 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T05:55:38Z |
| publishDate | 2012 |
| record_format | dspace |
| spelling | oxford-uuid:ea6407ac-e388-4ab2-99c2-e3a112d92bc92022-03-27T11:01:59ZContrast Independent Detection of Branching Points in Network-Like StructuresJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:ea6407ac-e388-4ab2-99c2-e3a112d92bc9EnglishSymplectic Elements at Oxford2012Obara, BFricker, MGrau, VMany biomedical applications require the detection of branching structures in images. While several algorithms have been proposed for (semi-)automatic extraction of these structures, branching points usually need specific treatment. We propose a vector field-based approach to identify branching points in images. A vector field is calculated using a novel contrast-independent tensor representation based on local phase. Non-curvilinear structures, including junctions and end points, are detected using directional statistics of the principal orientation as defined by the tensor. Results on synthetic and real biomedical images show the robustness of the algorithm against changes in contrast, and its ability to detect junctions in highly complex images. © 2012 SPIE. |
| spellingShingle | Obara, B Fricker, M Grau, V Contrast Independent Detection of Branching Points in Network-Like Structures |
| title | Contrast Independent Detection of Branching Points in Network-Like Structures |
| title_full | Contrast Independent Detection of Branching Points in Network-Like Structures |
| title_fullStr | Contrast Independent Detection of Branching Points in Network-Like Structures |
| title_full_unstemmed | Contrast Independent Detection of Branching Points in Network-Like Structures |
| title_short | Contrast Independent Detection of Branching Points in Network-Like Structures |
| title_sort | contrast independent detection of branching points in network like structures |
| work_keys_str_mv | AT obarab contrastindependentdetectionofbranchingpointsinnetworklikestructures AT frickerm contrastindependentdetectionofbranchingpointsinnetworklikestructures AT grauv contrastindependentdetectionofbranchingpointsinnetworklikestructures |