Rapid non-destructive recognition method for kiwi fruit surface defects based on hyperspectral imaging

Abstract

The invention discloses a rapid non-destructive recognition method for kiwi fruit surface defects based on hyperspectral imaging. The method comprises the following steps: acquiring hyperspectral images of a batch of kiwi fruits in good condition and kiwi fruit samples with surface defects by utilizing a hyperspectral image acquisition system; performing black and white correction on the hyperspectral image, and performing mask processing to eliminate background, so that the image only contains the kiwi fruits; performing further de-noising processing on the hyperspectral image by adopting minimum noise fraction rotation; respectively extracting the average spectrum of a normal area and a surface defect area of the kiwi fruits, and analyzing characteristics of the curve of spectrum; and finally, sequentially segmenting and extracting the normal area and the surface defect area of the kiwi fruits by adopting threshold segmentation and mathematical morphological processing. According tothe method disclosed by the invention, the kiwi fruits with surface defects can be rapidly non-destructively recognized by virtue of the hyperspectral imaging.

Description

technical field [0001] The invention belongs to the technical field of non-destructive detection of fruit surface defects, in particular to a method for quickly and non-destructively identifying kiwi fruit surface defects based on hyperspectral imaging technology. Background technique [0002] Kiwi fruit has high nutritional value and has the reputation of "king of fruits". my country's kiwifruit cultivation area is the largest in the world, accounting for 90% of the world's varieties. However, in the growth process of kiwifruit, it is often affected by various factors to cause defects on the surface of kiwifruit, which greatly affects the quality and sales of kiwifruit. It can be seen that the detection of surface defects of kiwifruit is particularly important. However, the kiwi fruit skin is darker, and its surface defects are difficult to identify with the naked eye. Traditional detection methods are mostly manual, time-consuming, labor-intensive, and inefficient, and ...

AI Technical Summary

Problems solved by technology

However, the kiwi fruit skin is darker, and its surface defects are difficult to detect with the naked eye

Traditional detection methods are mostly manual operations, time-consuming, labor-intensive, and inefficient, and cannot meet the needs of mass production

Images