Arecanut Grading Based on Three Sigma Controls and SVM

Arecanut Grading Based on Three Sigma Controls and SVM

Abstract:

In this paper, effective grading of arecanuts is proposed. The Arecanut RGB image is converted into YCBCR color space. Three sigma control limits on color features are determined for effective segmentation of arecanuts. Color features are used for the grading of arecants with the help of support vector machines (SVMs) into two grades i.e. Boiling and Non-boiling nuts effectively. Experimental k-fold cross validation method demonstrated the efficiency of the proposed approach.

Existing System:

The habit of chewing arecanut is typical of the Indian sub-continent and its neighborhood. Arecanut is grown in Bangladesh, China, Malaysia, Indonesia, Vietnam, Philippines and Thailand. India accounts for about 57 percent of world production. The quality, variety and types of arecanut vary from one place to another. Recent studies have shown that arecanut has pharmalogical uses such as hypoglycermic effect, mitotic activity etc. So far human has a prominent role in classifying the grades and variety of the arecanut. There are several computer based technologies for other crops but there is no computer vision based advanced technology in identifying grade for the arecanut.

Disadvantage:

The SVM, which is based on the theory of structural risk minimization in statistical learning [18], has outperformed many traditional learning algorithms. It is now generally recognized as a powerful method for various machine learning problems. As is well known, the SVM first maps the inputs to a high-dimensional feature space and then finds a large margin hyperplane between the two classes. Computationally, this leads to a quadratic programming (QP) problem.

Proposed System:

In the segmented region, the blue color component is normally suppressed and only red and green components are used to classify the arecanuts. The upper and lower control limits of the blue chroma and red chroma color components are determined using three sigma variations from the mean. These control limits are effective enough to segment the arecanut regions. Further classification is done based on the red and green color components of the segmented region of the arecanut using SVM classifier. Experimental kfold cross validation method demonstrated the efficiency of the proposed approach.