Abstract | ||
---|---|---|
Line detection plays a vital role in visual analysis tasks like Traditional Chinese Medicine (TCM) image analytics. However, most of the current methods ignore line thickness and perform poorly for the lines with different widths. This paper proposes a novel line detection method by using the water flow method. Unlike most edge-based and region-based line detectors, the water flow method is applied to obtaining the whole line response map by simply imitating the movement of water in the image smoothed by guided filter, which is viewed as a geomorphological map. In addition, this paper also proposes an adaptive parameter selection method so that the line detection can be more robust and accurate. Experimental results demonstrate the effectiveness of the proposed method on tongue crack images in comparison to the existing line extraction methods. |
Year | Venue | Keywords |
---|---|---|
2016 | 2016 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM) | Line detection,Water flow method,Existing line extraction method |
Field | DocType | ISSN |
Computer vision,Water flow,Computer science,Artificial intelligence,Analytics,Detector | Conference | 2156-1125 |
Citations | PageRank | References |
1 | 0.38 | 8 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yangyang Hu | 1 | 2 | 2.43 |
Wengqiang Zhang | 2 | 43 | 16.10 |
hong lu | 3 | 1 | 1.39 |
Fufeng Li | 4 | 1 | 0.38 |
Weifei Zhang | 5 | 1 | 0.38 |