A hybrid approach combining CUR matrix decomposition and weighted kernel sparse representation for plant leaf recognition

Abstract

Plant species recognition is one of the important and difficult research areas. Many existing plant recognition and classification methods cannot meet the requirements of the automatic plant recognition system, due to the irregular, complex, and diverse nature of plant leaves. In this paper, a plant recognition approach is proposed by combining CUR decomposition and weighted kernel sparse representation (WKSR). The proposed method is different from traditional plant leaf classification methods. Instead of establishing a classification model by extracting the color, shape, and texture classifying features, the proposed method directly reduces the dimensionality of image and recognizes the test samples based on WKSR coefficients. In order to reduce the recognition time the proposed method uses class specific dictionary learning for sparse modeling. By using the comparison analysis, the proposed method is verified on four plant leaf datasets namely, Flavia leaf dataset, Swedish leaf dataset, Original leaf images and Leafsnap dataset with existing plant classification methods such as Random Forest, Support Vector Machine and K-Nearest Neighbors. The accuracy of the proposed method is 98% which is the best classification rate.

KEYWORDS:

• Plant species recognition
• CUR decomposition
• dimensionality
• dictionary learning
• sparse modeling
• weighted kernel sparse representation

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

K. Pankaja

K. Pankaja holds a B.E. degree in CSE from Mysuru University and an M.Tech degree in CSE from the Visvesvaraya Technological University, and currently pursuing Ph.D under Visvesvaraya Technological University. She participated and conducted in various workshops and faculty development programs held by various colleges. She is Chief Alumni Coordinator and Joint Cultural Secretary for Cambridge Institute of Technology. She has around 11+ years of teaching experience and is associated with Cambridge Institute of Technology since 2010. She guided B.E. and M.Tech. students in their seminars and project dissertations. Her academic interests include Data Structures, File Structures, Database Management systems, Object Oriented Modeling and Design, Design and Analysis of Algorithm. In addition to her interest in academics, she also focuses on research in the area of Image Processing.

V. Suma

V. Suma holds a B.E, an M.S and a Ph.D in Computer Science and Engineering. She has vast experience spread across industry, academics and R&D. She is currently Dean of Research and Industry Incubation Centre and Professor of Dayananda Sagar College of Engineering, India. She is an invited author for several international book chapters. She is listed in various International biographical centers and recipient of various recognition awards. She is supervising several doctoral students in the areas of Software Engineering, Cloud Computing, and Data Mining. She is frequently invited as speaker in various International forums.