Individual leaf extractions from young canopy images using Gustafson-Kessel clustering and a genetic algorithm

The extraction of individual concealed leaves from images of complex plant canopies is a necessary step for taxonomic feature acquisition, species identification, and mapping using a modern personal computer. A new system for individual leaflet extraction was developed and tested, based on connected components, fuzzy clustering and a genetic optimization algorithm. Color images were taken of young, but sparse green canopies, grown in both greenhouse and field conditions. Some images contained individual leaves as connected components, which were readily apparent after separation of the vegetation from its background. Fragments of all other leaves imbedded in the canopy were obtained using the Gustafson-Kessel (GK) clustering algorithm. Each leaf fragment was labeled and placed in a variable length data structure called a chromosome, which represented selected leaf fragments and its neighbors. A genetic algorithm was then used to systematically reassemble the fragments of non-occluded, individual leaves. System performance was evaluated by comparing the number of individual leaves extracted by the computer per plant or plant canopy connected component for various soil/residue backgrounds and time after emergence. 83.5% of the plants in the second week produced at least one computer-extracted leaf for identification. Ninty-two percent of the plants had at least one computer extracted leaf by the third week. 84.7% had more than three computer extracted leaves for identification in the third week. Images of young field plants in multiple species clusters resulted in a 46% leaf extraction rate, but with at least one leaf per connected canopy component. Soybean and velvetleaf leaflets were the easiest to extract. Once individual leaves are extracted, they can be classified using traditional shape and textural feature methods. Computerized individual leaf extraction could assist plant identification and mapping, needed for weed control and crop management.

[1]  David Jones,et al.  Intensified fuzzy clusters for classifying plant, soil, and residue regions of interest from color images , 2004 .

[2]  George E. Meyer,et al.  Crop species identification using machine vision of computer extracted individual leaves , 2005, SPIE Optics East.

[3]  John F. Reid,et al.  DEVELOPMENT OF A PRECISION SPRAYER FOR SITE-SPECIFIC WEED MANAGEMENT , 1999 .

[4]  Lori J. Wiles,et al.  The cost of counting and identifying weed seeds and seedlings , 1999, Weed Science.

[5]  J. Hummel,et al.  On-The-Go Weed Sensing and Herbicide Application for the Northern Cornbelt , 2002 .

[6]  S. Christensen,et al.  Real‐time weed detection, decision making and patch spraying in maize, sugarbeet, winter wheat and winter barley , 2003 .

[7]  Yiming Wang,et al.  Real-time Detection of Between-row Weeds Using Machine Vision , 2003 .

[8]  M. F. Kocher,et al.  Textural imaging and discriminant analysis for distinguishing weeds for spot spraying , 1998 .

[9]  A. Gitelson,et al.  Novel algorithms for remote estimation of vegetation fraction , 2002 .

[10]  Leon G. Higley,et al.  Biotic stress and yield loss. , 2000 .

[11]  J. C. Neto,et al.  A combined statistical-soft computing approach for classification and mapping weed species in minimum -tillage systems , 2004 .

[12]  Lei Tian,et al.  CLASSIFICATION OF BROADLEAF AND GRASS WEEDS USING GABOR WAVELETS AND AN ARTIFICIAL NEURAL NETWORK , 2003 .

[13]  James C. Bezdek,et al.  Fuzzy mathematics in pattern classification , 1973 .

[14]  Donald Gustafson,et al.  Fuzzy clustering with a fuzzy covariance matrix , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[15]  Ta-Te Lin,et al.  LEAF SHAPE MODELING AND ANALYSIS USING GEOMETRIC DESCRIPTORS DERIVED FROM BEZIER CURVES , 2003 .

[16]  D. K. Giles,et al.  Precision weed control system for cotton , 2002 .

[17]  P. J. Pinter,et al.  Remote sensing for crop protection , 1993 .

[18]  Timothy W Hindman,et al.  A fuzzy logic approach for plant image segmentation and species identification in color images , 2001 .

[19]  Alex Martin,et al.  A simulation of herbicide use based on weed spatial distribution , 1995 .

[20]  Naoki Sakai,et al.  Identification of Idealized Leaf Types Using Simple Dimensionless Shape Factors by Image Analysis , 1996 .

[21]  J. Hemming,et al.  PA—Precision Agriculture: Computer-Vision-based Weed Identification under Field Conditions using Controlled Lighting , 2001 .

[22]  M. R. Gebhardt,et al.  Algorithms for Extracting Leaf Boundary Information from Digital Images of Plant Foliage , 1995 .

[23]  V. J. Rayward-Smith,et al.  Fuzzy Cluster Analysis: Methods for Classification, Data Analysis and Image Recognition , 1999 .

[24]  David A. Mortensen,et al.  Economic Importance of Managing Spatially Heterogeneous Weed Populations , 1998, Weed Technology.

[25]  E. Franz,et al.  Shape description of completely-visible and partially-occluded leaves for identifying plants in digital images. , 2016 .

[26]  Chun-Chieh Yang,et al.  Development of an Image Processing System and a Fuzzy Algorithm for Site-Specific Herbicide Applications , 2003, Precision Agriculture.

[27]  Gilles Rabatel,et al.  AE—Automation and Emerging Technologies: Weed Leaf Image Segmentation by Deformable Templates , 2001 .

[28]  Gaines E. Miles,et al.  Application of machine vision to shape analysis in leaf and plant identification , 1993 .

[29]  Chun-Chieh Yang,et al.  Applications of Artificial Neural Networks to Land Drainage Engineering , 1996 .

[30]  G. Meyer,et al.  Color indices for weed identification under various soil, residue, and lighting conditions , 1994 .

[31]  Isak Gath,et al.  Unsupervised Optimal Fuzzy Clustering , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  R. B. Brown,et al.  Remote Sensing for Identification of Weeds in No-till Corn , 1994 .

[33]  George E. Meyer,et al.  Shape features for identifying young weeds using image analysis , 1994 .

[34]  George E. Meyer,et al.  Digital Camera Operation and Fuzzy Logic Classification of Uniform Plant, Soil, and Residue Color Images , 2004 .

[35]  F. E. LaMastus,et al.  Using remote sensing to detect weed infestations in Glycine max , 2000, Weed Science.

[36]  George E. Meyer,et al.  Machine vision detection parameters for plant species identification , 1999, Other Conferences.

[37]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .