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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Caselles, V., Kimmel, R., Sapiro, G., 1997. Geodesic active contours. Int. J. Computer Vision, 22(1):61–79. [doi: 10.1023/A: 1007979827043]
Chan, T.F., Sandberg, B.Y., Vese, L.A., 2000. Active contours without edges for vector-valued images. J. Visual Commun. Image Represent., 11(2):130–141. [doi: 10.1006/jvci.1999.0442]
Chan, T.F., Vese, L.A., 2001. Active contours with out edges. IEEE Trans. on Image Processing, 10(2):266–277. [doi: 10.1109/83.902291]
Chen, Y.D., Chao, K.L., Kim, M.S., 2002. Machine vision technology for agricultural applications. Computer Electr. Agr., 36:173–191. [doi: 10.1016/S0168-1699(02)00100-X]
Cheng, F., Ying, Y., 2004. Image recognition of diseased rice seeds based on color feature. Proc. SPIE, 5587:224–231. [doi: 10.1117/12.570095]
Gomes, J., Faugeras, O., 2000. Reconciling distance functions and level sets. J. Visual Commun. Image Represent., 11(2):209–233. [doi: 10.1006/jvci.1999.0439]
Gui, J., Ying, Y., Rao, X., 2004. Real-time fruit size inspection based on machine vision. Proc. SPIE, 5587:262–269. [doi: 10.1117/12.571275]
Li, Q.Z., Wang, M.H., Gu, W.K., 2002. Computer vision based system for apple surface detection. Computer Electr. Agr., 36:215–223. [doi: 10.1016/S0168-1699(02)00093-5]
Li, C.M., Xu, C.X., Gui, C.F., Marting, D., 2005. Level Set Evolution without Re-initialization: A New Variational Formulation. CVPR. San Diego, p. 430–436.
Liu, J.C., Hwang, W.L., 2003. Active contour model using wavelet modulus for object segmentation and tracking in video sequences. Int. J. Wavel., Multiresol. Inf. Processing, 1(1):93–113. [doi: 10.1142/S0219691303000062]
Malladi, R., Sethian, J.A., Vemuri, B., 1995. Shape modeling with front propagation: a level set approach. IEEE Trans. on Pattern Anal. Machine Intell., 17(2):158–175. [doi: 10.1109/34.368173]
Osher, S., Sethian, J.A., 1988. Fronts propagating with curvature dependent speed: algorithms based on Hamilton-Jacobi formulations. J. Comput. Phys., 79(1):12–49. [doi: 10.1016/0021-9991(88)90002-2]
Peng, D., Merryman, B., Osher, S., Zhao, H., Kang, M., 1999. A PDE-based fast local level set method. J. Comput. Phys., 155(2):410–438. [doi: 10.1006/jcph.1999.6345]
Shatadal, P., Tan, J., 2003. Identifying damaged soybeans by color image analysis. Trans. ASAE, 19(1):65–69.
Zhang, G., Jayas, D.S., White, N.D.G., 2005. Separation of touching grain kernels in an image by ellipse fitting algorithm. Biosyst. Eng., 92(2):135–142. [doi: 10.1016/j.biosystemseng.2005.06.010]
Author information
Authors and Affiliations
Corresponding author
Additional information
Project supported by the National Natural Science Foundation of China (No. 30671197) and the Program for New Century Excellent Talents in University (No. NCET-04-0524), China
Rights and permissions
About this article
Cite this article
Gui, Js., Rao, Xq. & Ying, Yb. Fruit shape detection by level set. J. Zhejiang Univ. - Sci. A 8, 1232–1236 (2007). https://doi.org/10.1631/jzus.2007.A1232
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/jzus.2007.A1232