| Information Science |
|
|
|
|
| Fruit shape detection by level set |
| GUI Jiang-sheng, RAO Xiu-qin, YING Yi-bin |
| School of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310029, China |
|
|
|
Abstract A novel approach for fruit shape detection in RGB space was proposed, which was based on fast level set and Chan-Vese model named as Modified Chan-Vese model (MCV). This new algorithm is fast and suitable for fruit sorting because it does not need re-initializing. MCV has three advantages compared to the traditional methods. First, it provides a unified framework for detecting fruit shape boundary, and does not need any preprocessing even though the raw image is noisy or blurred. Second, if the fruit has different colors at the edges, it can detect perfect boundary. Third, it processed directly in color space without any transformations that may lose much information. The proposed method has been applied to fruit shape detection with promising result.
|
|
Received: 21 February 2006
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
