ColorED: Color edge and segment detection by Edge Drawing (ED)
| Autor: | Cuneyt Akinlar, Cihan Topal |
|---|---|
| Přispěvatelé: | Anadolu Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Akınlar, Cüneyt, Topal, Cihan |
| Rok vydání: | 2017 |
| Předmět: |
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology Edge (geometry) Helmholtz Principle Grayscale Edge detection Edge Drawing (Ed) 0202 electrical engineering electronic engineering information engineering Media Technology Canny edge detector Computer vision Electrical and Electronic Engineering Image gradient Mathematics Pixel Color image business.industry 020206 networking & telecommunications Deriche edge detector Vector Gradient Operators Compass Computer Science::Computer Vision and Pattern Recognition Color Edge Detection Signal Processing 020201 artificial intelligence & image processing Edge Segment Validation Computer Vision and Pattern Recognition Artificial intelligence business |
| Zdroj: | Journal of Visual Communication and Image Representation. 44:82-94 |
| ISSN: | 1047-3203 0003-9535 |
| Popis: | WOS: 000395355600008 We extend our recent edge and segment detector, Edge Drawing (GrayED), to detect edge segments in color images. Edge Drawing for color images, named ColorED, takes in a color image, and outputs a set of edge segments, each a contiguous, 1-pixel wide chain of pixels. Detected edge segments are then passed through an 'a contrario' validation step due to the Helmholtz principle to eliminate perceptually invalid detections. We quantitatively evaluate ColorED with different colorspaces and vector gradient operators within the precision-recall framework of the widely-used Berkeley Segmentation Dataset and Benchmark (BSDS300), and compare its results with those of GrayED and a color version of the Canny edge detector named ColorCanny. We conclude that color edge detection is in general superior to grayscale edge detection, and that ColorED with edge segment validation (ColorEDV) greatly outperforms GrayED, ColorED, and ColorCanny, producing an F-score of 0.6593 with DiZenzo and 0.6747 with the Compass operator while taking an average time of 31.5 ms for BSDS300 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect