Quality Attributes Evaluation for Groundnut using Semi Automatic Machine Vision System
- Govind Chaudhari, L.D. College of Engineering, Ahmedabad, Gujarat, India, firstname.lastname@example.org
- Kavindra Jain, G H Patel Engineering College, V. V. Nagar, Gujarat, India
- Kinjal Mehta, L.D. College of Engineering, Ahmedabad, Gujarat, India
This paper presents a methodology for identification and classification of peanut (Arachis hypogaea L.). Texture, Color and shape features are the basis used for recognition. The texture features are extracted using gray level co-occurrence matrix method like entropy, correlation, angular second moment. Color features are calculated like skewness, kurtosis, mean, and variance. Shape features are calculated using Fourier Descriptor like Minor-Major axis, Circularity, Compactness etc. Neural network is best used for decision making of complex problems. Their decision making capabilities can be best used in image analysis of biological products where the shape and size classification is not governed by any mathematical function. This paper reviews the technique of image analysis of Peanut with reference to use of neural network classifiers for decision making. The Back Propagation neural network is developed to classify peanuts.