Identification and classification of similar looking food grains

B. S. Anami; Sunanda D. Biradar; D. G. Savakar; P. V. Kulkarni

doi:10.1117/12.2009957

28 January 2013 Identification and classification of similar looking food grains

B. S. Anami, Sunanda D. Biradar, D. G. Savakar, P. V. Kulkarni

Proceedings Volume 8760, International Conference on Communication and Electronics System Design; 876008 (2013) https://doi.org/10.1117/12.2009957
Event: International Conference on Communication and Electronics System Design, 2013, Jaipur, India

Abstract

This paper describes the comparative study of Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers by taking a case study of identification and classification of four pairs of similar looking food grains namely, Finger Millet, Mustard, Soyabean, Pigeon Pea, Aniseed, Cumin-seeds, Split Greengram and Split Blackgram. Algorithms are developed to acquire and process color images of these grains samples. The developed algorithms are used to extract 18 colors-Hue Saturation Value (HSV), and 42 wavelet based texture features. Back Propagation Neural Network (BPNN)-based classifier is designed using three feature sets namely color – HSV, wavelet-texture and their combined model. SVM model for color- HSV model is designed for the same set of samples. The classification accuracies ranging from 93% to 96% for color-HSV, ranging from 78% to 94% for wavelet texture model and from 92% to 97% for combined model are obtained for ANN based models. The classification accuracy ranging from 80% to 90% is obtained for color-HSV based SVM model. Training time required for the SVM based model is substantially lesser than ANN for the same set of images.

Citation Download Citation

B. S. Anami, Sunanda D. Biradar, D. G. Savakar, and P. V. Kulkarni "Identification and classification of similar looking food grains", Proc. SPIE 8760, International Conference on Communication and Electronics System Design, 876008 (28 January 2013); https://doi.org/10.1117/12.2009957

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available