DETECTING FRAUDULENT LABELING OF SEED SAMPLES USING COMPUTER VISION

Abstract

Every grower in agriculture domain, at some point, observes the Poor seed quality has several implications, including late growth, damping out, poor growth, weak young plants, and mixed or ethnically compromised batches. The purpose is to have good quality and quantity crop seeds from it marketing point of view. Selection of right seeds can make it possible. Until now, all this has been handled manually, but machine vision approach can result better in this regard. Cotton, Wheat and Corn crops are widely cultivated in southern Punjab as well as throughout the world to produce various consumable and wearable items. Since seeds of these crops are evaluated in many areas with the aims of sowing and further processing, they should be identified in expedite and accurate manner for the selection of seed. In this research activity, an affordable machine vision approach has been investigated to classify types of wheat seeds. The experiments have been performing on the dataset collected from agriculture research center of Bahawalpur, Pakistan. Types of wheat seeds were annotated and labelled by the domain experts. Several Knowledge sets, algorithms, and algorithms for learning predictors have been investigated to get the best predictive m1odel for wheat seeds classification. Training and test sets have been used to tune the model parameters. Resultantly, fast and accurate operations have been adopted to serve agricultural industries. For quantitative assessment of the research work, standard evaluation parameters, accuracy, specificity and sensitivity have been used. The developed system achieved an overall accuracy as (98.60%).