Abstract

In this paper, we have presented different methodologies devised for recognition and classification of images of agricultural/horticultural produce. A classifier based on BPNN is developed which uses the color, texture and morphological features to recognize and classify the different agricultural/horticultural produce. Even though these features have given different accuracies in isolation for varieties of food grains, mangoes and jasmine flowers, the combination of features proved to be very effective. The average recognition and classification accuracies using colour features are 87.5%, 78.4% and 75.7% for food grains, mango and jasmine flowers, respectively, and the average accuracies have increased to 90.8%, 80.2% and 85.8% for food grains, mangoes and jasmine flowers ,respectively, using texture features. The average accuracies have increased to 94.1%, 84.0% and 90.1% for food grains, mangoes and jasmine flowers, respectively. The results are encouraging and promise a good machine vision system in the area of recognition and classification of agricultural/horticultural produce.

Submitted: May 13, 2009 · Accepted: October 8, 2009 · Published: October 28, 2009

Recommended Citation

Savakar, Dayanand G. and Anami, Basavaraj S. (2009) "Recognition and Classification of Food Grains, Fruits and Flowers Using Machine Vision," International Journal of Food Engineering: Vol. 5 : Iss. 4, Article 14.
DOI: 10.2202/1556-3758.1673
Available at: http://www.bepress.com/ijfe/vol5/iss4/art14