Detection of Soya Beans Ripeness Using Image Processing Techniques and Artificial Neural Network
Umar Faruk Abdulhamid *
Department of Mathematical Sciences, Kaduna State University, Kaduna, Nigeria
Muhammad Ahmad Aminu
Department of Mathematical Sciences, Kaduna State University, Kaduna, Nigeria
Simon Daniel
Department of Mathematical Sciences, Kaduna State University, Kaduna, Nigeria
*Author to whom correspondence should be addressed.
Abstract
The use of technology in agriculture has paved ways for new farming techniques across the globe and the benefits cannot be overemphasised. These benefits include an increase in the quality and quantity of crops produced, minimising cost of farming, providing suggestions for prompt action among others. Traditionally, to detect the ripeness of soya beans, farmers rely on a change in colour of leaves from green to brown, this process cannot be fully reliable as the colour is subjective to human naked eyes, and failure to harvest when ripe causes the seed pods to burst which reduces the crops expected to harvest. The research aim at detecting the ripeness of soya beans. The research employs the use of colour and texture features of leaves through image processing techniques in the pre-processing phase and artificial neural network for the detection of ripeness with the aid of MATLAB as the simulation tool. An accuracy of 95.7% is obtained in the classification of the various categories of soya beans leaves.
Keywords: Artificial neural network, image processing, soya beans, MATLAB