New Engineering Findings from Jiangxi Agricultural University Described (Feature Area Size Prediction Method of Spherical Fruit Based On Projection Transformation).

A new report from Jiangxi Agricultural University in Nanchang, China discusses a method for predicting the size of surface defects on spherical fruits using projection transformation. The researchers propose a line scanning image acquisition device for spherical fruit, which collects hyperspectral images and uses feature extraction and background removal to obtain isometric and equivalent projection images. These images, along with the number of feature pixels and the width of the original feature image, are used as input parameters for a shallow neural network to predict the actual defect area. The method has been tested and shown to have good prediction accuracy, making it a potential solution for quality sorting production lines of spherical fruits. [Extracted from the article]