A new method using feature extraction for identifying paddy rice species for quality seed selection

The purpose of this work was to explore a new feature extraction method for classifying paddy seeds using a feature extraction algorithm to achieve the area ratio, horizontal–slant and front–rear angles and find whether the proposed features have high discriminating power. Another objective was to find the smallest feature set that can ensure highly accurate recognition of seeds. A total of a 100 image features were extracted, and features having significant discriminating power were identified based on the analysis of variance (ANOVA). From the 100 features, 14 features were found to have high discriminating power and from these features, six were selected as the proposed features. Experimental results show that the proposed features and removal of redundant features enhanced the discriminating power of the feature set, and that the proposed features have an excellent discriminating property for seeds. The presented features resulted in the highest classification accuracy (98.8%) when compared to other methods.