Apple nondestructive testing method combining laser speckle and Kmeans clustering algorithm

Abstract

The invention relates to an apple nondestructive testing method combining a laser speckle and a Kmeans clustering algorithm. The method comprises the following steps of: 1, acquiring speckle displacement of N apples by adopting a laser speckle measurement method, and calculating resonant frequencies of the N apples; 2, adopting a standard Kmeans clustering algorithm to perform center clustering calculation on the resonant frequencies of the N apples; and 3, acquiring the resonant frequency of the apple to be detected, and judging the defect category of the apple to be detected according to the center clustering result in the step 2. The method has strong generalization ability, and the method based on computer vision can only detect the defect type marked in advance, but the method is suitable for any defect type which can cause the change of the apple resonance frequency. By selecting the high-order resonance frequency and combining the noise reduction technology, the new method provided by the invention has very strong noise resistance, is suitable for various actual working conditions with uncontrollable environment, and has the outstanding advantage different from that of a traditional computer vision method.

Description

technical field [0001] The invention relates to the field of nondestructive testing, in particular to an apple nondestructive testing method combining laser speckle and Kmeans clustering algorithm. Background technique [0002] The non-destructive testing of apples has great application value, which is helpful to realize the grading of apples according to their quality, thereby increasing the economic added value. At the same time, this is also a challenging scientific problem. The current mainstream nondestructive testing of apples is a large class of methods based on computer vision, including traditional machine learning algorithms that artificially extract the characteristics of apple skin and the current relatively cutting-edge artificial intelligence based on deep learning. method. These visual methods are suitable for detecting defect types with obvious characteristics of apple skin, such as defects such as rot and large bumps, but are not effective for defect types ...

AI Technical Summary

Problems solved by technology

These visual methods are suitable for detecting defects with obvious characteristics of apple skin, such as rot, large bumps and other defects, but are not effective for defect types with insignificant characteristics such as dehydration

Images