Veterinary drug production pointer type instrument image recognition method and device based on RFID and deep learning

A technology of deep learning and image recognition, applied in the direction of character and pattern recognition, collaborative work devices, instruments, etc., can solve the problems of physical health injuries, heavy workload, error-prone and other problems of staff, and achieve strong practicability and low cost , strengthen the effect of the edge

Pending Publication Date: 2020-01-17
AGRI INFORMATION INST OF CAS
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the advancement of science and technology, veterinary drug biological products and production models are constantly innovating, but there are still many problems. Most of the reading of instrument data in veterinary drug production workshops now uses wired remote transmission or manual reading. The workload of these traditional methods Large size, low efficiency, and error-prone; at the same time, because veterinary drugs are extremely sensitive to environmental requirements, precise management of temperature, humidity and other environments is required to ensure the suitability of drug storage conditions; at the same time, due to the production of toxic gases or radiation, It will cause great damage to the health of the staff, and it is also necessary to timely and effectively monitor the dangers in the production workshop

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
  • Veterinary drug production pointer type instrument image recognition method and device based on RFID and deep learning
  • Veterinary drug production pointer type instrument image recognition method and device based on RFID and deep learning
  • Veterinary drug production pointer type instrument image recognition method and device based on RFID and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] Such as figure 1 As shown, the present invention provides a kind of veterinary medicine production pointer instrument image recognition method based on RFID and deep learning, and this method comprises the following steps:

[0056] S1, collect instrument image: use the camera to collect the image of the pointer instrument dial that contains the reading to be identified in the veterinary drug production workshop, and obtain the relevant data of the instrument stored in the RFID electronic tag 6;

[0057] S2. Extract the dial area: use the Faster-RCNN algorithm trained based on deep learning to detect the image acquired in S1, quickly locate the coordinates of the dial area, and extract this area as the dial image;

[0058] S3. Image preprocessing: grayscale, image filtering and denoising, and binarization preprocessing are performed on the dial image extracted in S2 to obtain a binarized image of the dial that only contains black and white pixels;

[0059] S4. Pointer p...

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 provides a veterinary drug production pointer type instrument image identification method based on RFID and deep learning. The veterinary drug production pointer type instrument image identification method comprises the following steps: S1, collecting an instrument image; S2, extracting a dial area; S3, preprocessing the image; S4, performing pointer positioning fitting; S5, performing instrument reading judgment; and S6, performing instrument early warning judgment. According to the identification method provided by the invention, a large amount of electronic data can be stored;the problem of health injury caused by the fact that workers are poisonous, harmful, radiated and easily polluted in a veterinary drug production workshop is solved; the system is simple in structureand convenient to use, personal safety of workers is guaranteed to the maximum extent, the system further has the advantages of being fast in reading, high in accuracy, high in adaptability and intelligent in management, an abnormal environment can be warned in time, veterinary drug production efficiency is greatly improved, and safety of a veterinary drug storage environment and a veterinary drug production environment is guaranteed.

Description

technical field [0001] The invention belongs to the technical field of instrument data identification, and in particular relates to a method and device for recognizing an image of a pointer instrument in veterinary drug production based on RFID and deep learning. Background technique [0002] With the advancement of science and technology, veterinary drug biological products and production models are constantly innovating, but there are still many problems. Most of the reading of instrument data in veterinary drug production workshops now uses wired remote transmission or manual reading. The workload of these traditional methods Large size, low efficiency, and error-prone; at the same time, because veterinary drugs are extremely sensitive to environmental requirements, precise management of temperature, humidity and other environments is required to ensure the suitability of drug storage conditions; at the same time, due to the production of toxic gases or radiation, It will...

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): G06K9/20G06K9/40G06K9/34G06K17/00G06N3/04
CPCG06K17/0029G06V10/22G06V10/267G06V10/30G06V2201/02G06N3/045
Inventor 曹姗姗孙伟孔繁涛吴建寨金忠明邱琴
Owner AGRI INFORMATION INST OF CAS
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