Unlock instant, AI-driven research and patent intelligence for your innovation.

Apple nondestructive testing method based on machine learning

A non-destructive testing and machine learning technology, applied in neural learning methods, instruments, measuring devices, etc., can solve problems such as inaccurate identification, achieve the effect of reducing workload, increasing income, and fast, efficient and accurate detection

Pending Publication Date: 2021-11-09
XI'AN POLYTECHNIC UNIVERSITY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention device realizes intelligence as a whole, solves the problem that the existing technology cannot accurately identify, and quickly, efficiently and accurately classifies and screens apples

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Apple nondestructive testing method based on machine learning
  • Apple nondestructive testing method based on machine learning
  • Apple nondestructive testing method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] like Figure 1-5 As shown, a machine learning-based non-destructive testing method for apples includes:

[0050] S0. Collecting apple appearance pictures, size data, internal ultrasonic non-destructive data, and internal resonance acoustic wave data, and training them to obtain a training model. Specifically:

[0051] Through the appearance picture of the apple, use the quality interval described in step S1 to mark and give a label, which is used to train the convolutional neural network model based on deep learning.

[0052] By collecting internal ultrasonic non-destructive data and internal resonant acoustic wave data, use the quality interval described in step S1 to mark and give labels for training the convolutional neural network-recurrent neural network model based on deep learning.

[0053] The training process of convolutional neural network model based on deep learning:

[0054] (1) Preprocess the collected apple appearance images to obtain sub-images, which...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an apple nondestructive testing method based on machine learning, and relates to a method for intelligently detecting and grading apples by using image analysis. The method comprises the following steps: obtaining an apple multi-parameter training model; setting an apple quality screening interval; acquiring an appearance picture of a to-be-detected apple, denoising, then identifying the appearance picture of the apple by using a training model, carrying out internal nondestructive detection on the screened required apple, carrying out nondestructive judgment on the interior of the apple by using the training model, carrying out internal resonance sound wave detection on the disease-free apple, and judging the internal substance content by using the training model, completing classification of all apples. According to the method, a large number of apples are rapidly and efficiently detected accurately, the detection accuracy and efficiency are improved, and the detection process is optimized. The workload of fruit farmers can be reduced, and the income of the fruit farmers can be increased. Different grades of fruits can be provided according to the requirements of consumers, and a certain effect on improving the status of domestic fruits is achieved.

Description

technical field [0001] The invention relates to a method for intelligently detecting and grading apples by using image analysis. Background technique [0002] The development of agriculture is closely related to the development of my country's comprehensive national strength and the stability of national conditions. The revitalization of agriculture is one of the main goals at this stage. my country is currently in a critical period of transformation from traditional agriculture to modern agriculture. Although the fruit resources are very rich, and the fruit output has occupied the first place in the world, the export volume and quality are relatively low. The current fruit export volume only accounts for 2% of the world, and most of the fruits are sold in the country. Taking apples as an example, an important factor affecting its development is the inaccurate grading and screening of fruits, and the detection of fruits cannot meet the export standards, which affects the pr...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/84G01N29/04G01N29/12G06K9/62G06N3/04G06N3/08G06T5/00G06T7/00
CPCG01N21/84G01N29/043G01N29/12G06T7/0002G06N3/049G06N3/08G01N2021/8466G01N2291/023G01N2291/0289G06T2207/10004G06T2207/20032G06T2207/20081G06T2207/20084G06T2207/30188G06N3/045G06F18/241G06F18/214G06T5/70
Inventor 郝红娟王九鑫刘宇程卢定泽苏耀恒杨宁吴鑫李文龙王康华杜雨蓉杨彤彤王明墺张倩陈琳张芷叶黄磊张亚鑫
Owner XI'AN POLYTECHNIC UNIVERSITY