Title :
A new petiole detection algorithm based on leaf image
Author :
Zhaobin Wang ; Xu Zheng ; Xiaoguang Sun ; Hao Wang ; Ying Zhu ; Jianpeng Liu ; Yide Ma
Author_Institution :
Sch. of Inf. Sci. & Eng., Lanzhou Univ., Lanzhou, China
Abstract :
Leaf is one of the most important organs of plant and often used as one of the basic characters in plant classification. The developmental condition of leaf can provide us with lots of critical information, such as the plant´s health condition, the prospection of crop yield and so on. Leaf image processing by computer has been widely used for the extraction and dissection of leaf images in relevant researches. Image processing of leaf also offers an effective platform for plant classification and growth observation. A basic problem of leaf image processing is detecting and dislodging the petiole from the whole leaf image. Here this paper presents an algorithm which combines the dual-channel pulse coupled neural network (PCNN) model and HSI color space for leaf petiole detection. Totally 169 sorts of leaf images are tested by the proposed algorithm. The experimental results show that our method has potential availability in reducing mis-evaluation and increasing application scale as a tool in relative study.
Keywords :
biology computing; botany; crops; feature extraction; image classification; image colour analysis; neural nets; HSI color space; PCNN model; crop yield; dual-channel pulse coupled neural network model; leaf developmental condition; leaf image dissection; leaf image extraction; leaf image processing; petiole detection; petiole detection algorithm; petiole dislodging; plant classification; plant health condition; plant organs; Color; Computers; Conferences; Decision support systems; Pattern recognition; Signal processing; TV;
Conference_Titel :
Electrical and Computer Engineering (CCECE), 2015 IEEE 28th Canadian Conference on
Conference_Location :
Halifax, NS
Print_ISBN :
978-1-4799-5827-6
DOI :
10.1109/CCECE.2015.7129490