Int J Performability Eng ›› 2019, Vol. 15 ›› Issue (4): 1122-1130.doi: 10.23940/ijpe.19.04.p7.11221130

Previous Articles     Next Articles

Plant Leaves Recognition Combined PCA with AdaBoost.M1

Hui Chena, Haodong Zhub, *, and Xufeng Chaic   

  1. a Engineering Training Centre, Zhengzhou University of Light Industry, Zhengzhou,450002,China;
    b School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, 450002, China;
    c Sida Foreign Language Primary School, Henan Experimental High School, Zhengzhou, 450000, China
  • Revised on ; Accepted on
  • Contact: E-mail address:
  • About author:Hui Chen received her B.S. degree from Henan University, Kaifeng, Henan Province, China, in 1992. Since 1993, she has been with the faculty of the Engineering Training Centre, Zhengzhou University of Light Industry, Zhengzhou, Henan Province, China, where she is currently an experimentalist. Her major research interests include Intelligence Information Processing and Data Mining. Haodong Zhu received his B.S. degree from Lanzhou Jiaotong University in 2004, his M.S. degree from Sichuan University of Science & Engineering in 2008, and his Ph.D. from Graduate University of Chinese Academy of Sciences in 2011. As a postdoctoral researcher, he engaged in image big data processing in the Postdoctoral Mobile Station of Computer Science and Technology at Tongji University from 2014 to 2016. As a visiting scholar, he engaged in micro-blog big data processing at Griffith University from 2017 to 2018. Since 2010, he has been an associate professor and master’s tutor in the School of Computer and Communication Engineering at Zhengzhou University of Light Industry. His major research interests include cloud computation, intelligence information processing, computing intelligence, and data mining. Xufeng Chai graduated from Henan University in 2013. At present, he is a faculty member in the Sida Foreign Language Primary School at Henan Experimental High School. His major research interest is mathematics education.

Abstract: In order to improve the overall performance of plant leaves recognition, this paper proposed a novel method combining PCA with AdaBoost.M1to recognize plant leaves. The proposed method firstly carries out the image preprocessing, which includes the image gray processing, the image binarization, and the edge extraction; extracts the 13 features of plant leaf with the characteristics of rotation invariance, proportion invariance, and translation invariance; subsequently employs PCA to reduce the dimensions of these feature parameters; and finally adopts the AdaBoost.M1 classifier to train and recognize the reduced-dimension plant leaf images. Simulation experiment results indicate that the proposed method is able to improve the overall performance effectively of plant leaves recognition.

Key words: plant leaves recognition, performance improvement, PCA, AdaBoost.M1, image processing