Aid of computer (machine) vision techniques is an accusative method which will helpful in online verification and in stepping up the accuracy of wheat seed classification in real applications of agricultural industry. The study contains the evaluation of how efficiently relegate the wheat seed types of most effective texture features group through the examination of distinct texture features of wheat seed species images. Including all, there were 60 gray scale images of bulk wheat seed species were taken under the standardized illumination condition (fluorescent light).There are 131 textural features were educed from six numbers of matrices namely LBP(local binary pattern),LSN(local similarity number),LSP(local similarity pattern),gray level, GLRM (gray level run-length matrix) and GLCM (gray level co-occurrence matrix).The substantial textural features were ranked with the use of stepwise discrimination process. This process was severally used for each matrix and features of all matrices simultaneously as well. The artificial neural network (ANN) was used for the classification of wheat seed. The percentage of average accuracy of classification result was 76% when selective 60 features were considered. KeywordsTexture features, ANN, LSN, LBP, LSP, Gray, GLRM, GLCM.
[1]
Wilhelm Burger,et al.
Digital Image Processing - An Algorithmic Introduction using Java
,
2008,
Texts in Computer Science.
[2]
S. Shouche,et al.
Potential of Artificial Neural Networks in Varietal Identification using Morphometry of Wheat Grains
,
2006
.
[3]
D. Jayas,et al.
Identification of wheat classes using wavelet features from near infrared hyperspectral images of bulk samples.
,
2009
.
[4]
D. Jayas,et al.
Classification of cereal grains using wavelet, morphological, colour, and textural features of non-touching kernel images
,
2008
.
[5]
Hamid Reza Pourreza,et al.
Identification of nine Iranian wheat seed varieties by textural analysis with image processing
,
2012
.
[6]
Chomtip Pornpanomchai,et al.
Plant Seed Image Recognition System (PSIRS)
,
2011
.