Journal Press India^®

Author Details ( * ) denotes Corresponding author

Classification of rice grains is important for human beings as it directly impacts the human health. Hence there is a great need to measure the quality of rice grains and identifying the adulteration and analysing the grains manually is more time consuming and complicated process and having more chances of errors with the subjectivity of the human perception. In order to achieve the uniform standard quality and precision, machine learning techniques are evolved.Rice quality is nothing but the combination of physical and chemical characteristics grain size, shape and colour are some physical characteristics. This paper obtained all physical features and classification of rice grains using SVM and CNN. By implementing these two and comparing both SVM and CNN outputs, identifyingwhich technique will perform classification efficiently.

Keywords

Image processing; Rice quality analysis; Grain classification; SVM; CNN.

1. 2^nd IEEE international conference on recent trends in electronic information communication technology, 2017.


2. HMKKMB Herath, WR De Mel. Rice Grains Classification Using Image Processing Techniques department of mechanical engineering, 2018.


3. Non-Destructive image processing-based system for assessment of rice quality and defects for classification according to inferred commercial value.


4. Simonvan, Karen,  A Zisserman. Very deep convolution network for large scale image recognition.


5. R Girshick, Jeff Donahue Trevor Darrel, J Malik. Rich feature hierarchies for accurate object detection and semantic segmentation computer vision pattern recognition, IEEE conference, 2018.