Cultivar differentiation in rice’s extant varieties through image analysis
Author(s):
SK Mundotiya, Jagdish Goyanka, Ravi Kumar Mundotiya and Sunil Ramling Swami
Abstract:
There are about 950 released and notified varieties of rice (Oryza sativa L.) in India for which diagnostic features are well known and the same are followed for the purpose of seed certification. Hence, variety identification is of prime importance. The scope of morphological differences between the varieties is less due to narrow genetic base, and requires skilled human power which is subjective in nature. Also this process is time, labour and cost intensive. Keeping in mind the above facts, the present study was initiated with the objective of making differentiation in rice varieties using image analysis technique. The experimental material comprised of twenty eight extant rice varieties. A complete digital database comprising of 84 images each for seed and 448 leaf images were generated. Two different types of softwares were used for extraction of features from the images viz. Grain Analysis Software (for size and shape features) and MATLAB software (for textural features). The varieties were grouped on the basis of these features generated from seed and leaf images. Seed imaging features differentiated the varieties into six clusters whereas leaf imaging features alone and combination of seed and leaf images grouped the varieties into seven clusters. The study revealed that image features extracted from seed were most helpful for distinguishing the varieties because it is supported by two kind of study, one based on Grain Analysis Software and second based on MATLAB software whereas study of leaf for cultivar differentiation is based on MATLAB software only.
How to cite this article:
SK Mundotiya, Jagdish Goyanka, Ravi Kumar Mundotiya, Sunil Ramling Swami. Cultivar differentiation in rice’s extant varieties through image analysis. Pharma Innovation 2022;11(2):1112-1118.