Peeled potato quality identification method based on depth separable convolution

A potato and convolution technology, applied in character and pattern recognition, measuring devices, testing material hardness, etc., can solve the problems of inability to detect potato hardness, inability to detect potato germs, and inability to identify and judge potatoes, so as to reduce the amount of theoretical calculation, It is like the effect of comparing accuracy and improving the speed of comparison

Pending Publication Date: 2021-01-29
JILIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, during the processing of existing peeled potatoes, it is impossible to accurately and effectively identify and judge the quality of potatoes, and it is also impossible to detect whether there are germs in potatoes. Not only that, it is impossible to detect the hardness of potatoes

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
  • Peeled potato quality identification method based on depth separable convolution
  • Peeled potato quality identification method based on depth separable convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0019] see Figure 1-2 , the present invention provides a technical solution: a method for identifying the quality of peeled potatoes based on depthwise separable convolution, comprising the following steps:

[0020] Step 1: first use the three-dimensional scanning mechanism to scan the potatoes without quality problems, and use depth separable convolution in the industrial computer 10 to establish a potato model without quality problems. The three-dimensional scanning mechanism includes a fixed frame plate 9, an industrial computer 10, a fixed plate 5, fixed rod 6 and three-dimensional scanning camera 7, the left and right sides of the bottom of the fixed frame plate 9 are welded with fixed plates 5, and the fixed rod 6 is fixedly connected betwe...

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 a peeled potato quality identification method based on depth separable convolution, and the method comprises the following steps: 1, scanning potatoes without quality problemsthrough a three-dimensional scanning mechanism, and building a potato model without quality problems in an industrial control computer through depth separable convolution, the three-dimensional scanning mechanism comprises a fixing frame plate, an industrial control computer, fixing plates, fixing rods and three-dimensional scanning cameras, the fixing plates are welded to the left side and the right side of the bottom of the fixing frame plate, the fixing rod is fixedly connected between the two fixing plates, and the three-dimensional scanning cameras are fixedly connected to the middles ofthe bottoms of the fixing rods. According to the method, a depth separable convolution technology is adopted, convolution operation is carried out on sequences of different granularities input by themodel by adding a depth separable convolution neural network, more feature data are extracted, compared with traditional convolution, the theoretical calculation amount of the model is reduced, the comparison speed of the model is increased, and through more feature data, the accuracy of model comparison is improved. And the comparison accuracy is better.

Description

technical field [0001] The invention relates to the technical field of quality identification of peeled potatoes, in particular to a quality identification method of peeled potatoes based on depthwise separable convolution. Background technique [0002] Potato has high yield, rich nutrition and strong adaptability to the environment. It has been spread all over the world. Tropical and subtropical countries can even cultivate and obtain high yield in winter or cool season. Potatoes are very suitable for growing in alpine areas where the original grain output is extremely low and only naked oats (naked oats) can be grown. [0003] However, the existing peeled potatoes cannot accurately and effectively identify and judge the quality of the potatoes during processing, and cannot detect whether there are germs in the potatoes, not only that, but also cannot detect the hardness of the potatoes. Contents of the invention [0004] The purpose of the present invention is to provid...

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): G06Q10/06G06T17/00G06K9/62G06N3/04G01B11/24G01N3/40
CPCG06Q10/06395G06T17/00G01B11/24G01N3/40G06V10/751G06N3/045
Inventor 王岩谢旭平何凯李大琳黄岚
Owner JILIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products