A free-fall fruit and vegetable sorting method and system based on deep learning
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A free fall, deep learning technology, applied in sorting and other directions, can solve problems such as poor rejection accuracy, and achieve the effect of solving large attenuation, improving light intensity, and improving accuracy.
Inactive Publication Date: 2021-04-23
福建铂格智能科技股份公司
View PDF17 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
The detection object is small, and the area detection algorithm is used, and the rejection accuracy is poor
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0053] Specific implementation mode one: refer to figure 1 , figure 2 , Figure 7-Figure 9 As shown, this embodiment discloses a free-fall fruit and vegetable sorting system based on deep learning, including: a feeding funnel 1, an electrical control box 2, a touch display 3, multiple quick-release protective plates 4, and a first image acquisition box 5. Two color line scan cameras 6, the first light source box 8, the first light source background box 9, the photoelectric sensor 10, the high-frequency solenoid valve array 11, the first blanking blocking curtain 12, two nozzle arrays, the first falling Material plate 15, second blanking plate 16, air jet baffle 17, third blanking blocking curtain 18, second blanking blocking curtain 19, second light source background box 20, second light source box 21, second image acquisition box 22, frame 23, damping spring 24, straight vibrator 25, bucket 27, material curtain 29, chute 30; The two nozzle arrays are respectively the firs...
specific Embodiment approach 2
[0064] Specific implementation mode two: as figure 2 and Figure 7 As shown, this embodiment is a further description of Embodiment 1. The free-fall fruit and vegetable sorting system based on deep learning also includes two optical protection windows 7, and the two optical protection windows 7 are respectively installed on the The left side and the right side of the first image acquisition box 5 and the second image acquisition box 22. Two optical protection windows 7 are used to protect the lens.
specific Embodiment approach 3
[0065] Specific implementation mode three: as figure 2 and Figure 7 As shown, this embodiment is a further description of Embodiment 2, and the two optical protection windows 7 are both made of quartz glass.
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
Login to view more
Abstract
A deep learning-based free-fall fruit and vegetable sorting method and system belong to the field of fruit and vegetable sorting. The electrical control box is installed on the outside of the equipment shell, the display touch device is installed on the front side of the equipment shell, the bucket is installed obliquely below the feed inlet, the straight vibrator is installed at the bottom of the bucket, the chute is connected to the bucket, and the material arrangement curtain The first nozzle array is connected to the high-frequency solenoid valve array, the second nozzle array is connected to the high-frequency electromagnetic valve array, and the second blanking plate is arranged between the first and second nozzle arrays. On the opposite side of the frame, the first and second image acquisition boxes are installed at the front and rear ends of the frame, the two color line scan cameras are installed in the first and second image acquisition boxes, and the first light source box and the first light source background box are at an angle to each other It is located on the right side of the chute, and the second light source box and the second light source background box are located on the left side of the chute at an angle to each other. The invention can greatly improve the detection speed of fruits and vegetables, has a sorting function, has high rejection precision and low maintenance cost.
Description
technical field [0001] The invention belongs to the field of fruit and vegetable sorting, and in particular relates to a deep learning-based free-fall fruit and vegetable sorting method and system. Background technique [0002] At present, the fruit and vegetable sorting industry mainly relies on manual sorting, with low automation level, low efficiency, and high human resource costs. For small particles such as wolfberry, the color sorting technology is used to check for defects by color, which has been mature and widely used. However, for varieties such as dried red dates and tomatoes, it still remains at the stage of manual selection, which involves quality judgment and complex defects rather than simple color and size recognition. [0003] In terms of detection algorithms, conventional image processing algorithms are commonly used in fruit and vegetable sorting at present, mainly through color, edge detection and other technologies to detect the color size and obvious d...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more