Title :
Leaf Vein Extraction Using a Combined Operation of Mathematical Morphology
Author :
Zheng, Xiaodong ; Wang, Xiaojie
Author_Institution :
Dept. of Comput. Sci. & Applic., Zhengzhou Inst. of Aeronaut. Ind. Manage., Zhengzhou, China
Abstract :
The type of the leaf vein can be a useful parameter in automatic identification of plant species. Leaf vein extraction is the precondition of discriminating the leaf vein type. In this paper a new method is presented for leaf vein extraction based on mathematical morphology. Firstly, the color image of the plant leaf is transformed to gray image according to the hue and intensity information. Secondly, a combined operation of mathematical morphology is applied to the image to eliminate the color overlap between the whole leaf vein and the whole background. Thirdly, image segmentation is performed with OSTU method. Finally, the leaf vein can be got after some processing on details. Experiments have been conducted with several images and the results show the effectiveness of the method. The basic idea of the method is also applicable to other linear objects extraction.
Keywords :
botany; image colour analysis; image segmentation; mathematical morphology; OSTU method; automatic identification; color image; gray image; image segmentation; leaf vein extraction; linear object extraction; mathematical morphology; Feature extraction; Image color analysis; Image segmentation; Morphology; Noise; Surface morphology; Veins;
Conference_Titel :
Information Engineering and Computer Science (ICIECS), 2010 2nd International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-7939-9
Electronic_ISBN :
2156-7379
DOI :
10.1109/ICIECS.2010.5677786