DocumentCode :
2287906
Title :
Research on insect identification based on pattern recognition technology
Author :
Yang, Huiyong ; Liu, Wei ; Xing, Kun ; Qia, Jian ; Wang, Xin ; Gao, Lingwang ; Shen, Zuorui
Author_Institution :
Taiyuan Extension Station of Applic. Technol., Taiyuan, China
Volume :
2
fYear :
2010
fDate :
10-12 Aug. 2010
Firstpage :
545
Lastpage :
548
Abstract :
This paper presents a method of insect recognition using computer vision technology. First, we extracted fourteen features from images of some species of insects. These features are rectangularity, elongation, roundness, eccentricity, sphericity, lobation, compactness and seven Hu moment invariants. Second, a machine learning algorithm named Random Trees was employed, to play a role of a classifier in pattern recognition. The classifier was trained with the extracted features and the trained result was saved in a database. Then, the data can be loaded from the database into the algorithm, and then the algorithm can be used to recognize the species of insects which have been trained. In order to implement these algorithms, a series of software modules were developed to extract features, train algorithm, and do recognitions, based on an open source computer vision library named OpenCV, which is portable on Windows and Unix platforms.
Keywords :
biology computing; feature extraction; image classification; learning (artificial intelligence); random processes; trees (mathematics); Hu moment invariant; OpenCV; feature extraction; insect identification; insect recognition; insect species; machine learning; open source computer vision library; pattern recognition classifier; random trees; software module; Classification algorithms; Classification tree analysis; Feature extraction; Image segmentation; Insects; Pattern recognition; Training; computer vision; insect; pattern recognition; random trees;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation (ICNC), 2010 Sixth International Conference on
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-5958-2
Type :
conf
DOI :
10.1109/ICNC.2010.5583156
Filename :
5583156
Link To Document :
بازگشت