Download:
|
by P. M. Granitto, H. D. Navone, P. F. Verdes, H. A. Ceccatto
http://www.ifir.edu.ar/~redes/ps/cacic2000_1.ps.Z
Add To MetaCart
Abstract:
ABSTRACT: The analysis and classification of seeds are essential activities contributing to the final added value in the crop production. Besides varietal identification and cereal grain grading, it is also of interest in the agricultural industry the early identification of weeds from the analysis of strange seeds, with the purpose of chemically controlling their growth. The implementation of new methods for reliable and fast identification and classification of seeds is thus of major technical and economical importance. Like the manual identification work, the automatic classification of seeds should be based on knowledge of seed size, shape, color and texture. In this work we present a study of the discriminating power of morphological, color and textural characteristics of weed seeds, which can be measured from video images. This study was conducted on a large basis, considering images of weed seeds found in Argentina's commercial seed production industry and listed by the Secretary of Agriculture as prohibited and primary- and secondary-tolerated weeds. We first describe the experimental setting and hardware used to capture the seed images. Then, we define the morphological, color and textural parameters measured from these images, and discuss the selection of the most relevant ones for identification purposes. Finally, we present results for the identification of test images obtained using a Naive Bayes classifier and a committee of Artificial Neural Networks.
Citations
|
3318
|
Neural Networks for Pattern Recognition
– Bishop
- 1995
|
|
484
|
Textural features for image classification
– Haralick, Shanmugam, et al.
- 1973
|
|
187
|
Feature selection: Evaluation, application, and small sample performance
– Jain, Zongker
- 1997
|
|
34
|
Texture Analysis Using Gray Level Run Lengths
– Galloway
- 1975
|
|
22
|
Segmentation of a high-resolution urban scene using texture operators
– Conners, Trivedi, et al.
- 1984
|
|
6
|
The measurement of new characters for cultivar identification in wheat using machine vision
– Keefe, Draper
- 1986
|
|
6
|
Image analysis and characterization of cereal grains with a laser range finder and camera contour extractor
– Chen, Chiang, et al.
- 1989
|
|
6
|
Wheat grain color analysis by digital image processing II. Wheat class discrimination
– Neuman, Sapirstein, et al.
- 1989
|
|
5
|
Preliminary observations with a computer based system for analysis of the shape of seeds and vegetative structures
– Draper, Travis
- 1984
|
|
5
|
An instrumental system for cereal grain classification using digital image analysis
– Sapirstein, Neuman, et al.
- 1987
|
|
5
|
Determination of wheat kernel morphological variation by digital image analysis: I. Variation in Eastern Canadian Milling Quality Wheats
– Symons, Fulcher
- 1988
|
|
5
|
Discrimination of wheat class and variety by digital image analysis of whole grain samples
– Neuman, Sapirstein, et al.
- 1987
|
|
5
|
Seed production quality in Trifolium balansae and T. resupinatum: The role of seed color
– Jansen
- 1995
|
|
4
|
Discrimination between wheat classes and varieties by image analysis
– Zayas, Lai, et al.
- 1986
|
|
3
|
Discrimination of wheat and nonwheat components in grain samples by image analysis
– Zayas, Pomeranz, et al.
- 1989
|
|
2
|
A new algorithm for selecting diverse members of a neural network ensemble
– Navone, Verdes, et al.
- 2000
|
|
1
|
Color classifier for symptomatic 7soybean seeds using image processing
– Ahmad, Reid, et al.
- 1999
|
|
1
|
Automatic identification of weed seeds by colour machine vision
– Petersen, Krutz
- 1992
|
