Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dairy cow individual recognition method based on deep convolutional neural network

A convolutional neural network and neural network technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve the problems of low recognition accuracy of dairy cows and insufficient utilization of dairy cows.

Inactive Publication Date: 2017-05-31
HEBEI UNIV OF TECH
View PDF3 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a cow individual recognition method based on a deep convolutional neural network, which is a method of extracting features from a convolutional neural network in deep learning and combining texture features of a cow to realize effective recognition of a cow individual. It overcomes the defect that the existing algorithm for processing dairy cow images using image processing technology is single, and does not make full use of the stripe characteristics of cows themselves to combine well with image processing and pattern recognition technology, resulting in low cow recognition accuracy.

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
  • Dairy cow individual recognition method based on deep convolutional neural network
  • Dairy cow individual recognition method based on deep convolutional neural network
  • Dairy cow individual recognition method based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] The first step, the collection of cow data:

[0073] Using camera equipment, collect videos of 20 cows walking from a small dairy farm in Yi County, Dingzhou, Hebei Province during the period of 7:00-18:00 without fog and haze. The collection starts when all individual cows appear on the left side of the field of view. , continue to collect cows walking to the right edge of the field of view as a video segment, and remove the video that contains cows pause and abnormal behavior, each cow has 8 videos, each video is about 14s, and the frame rate is 60fps, as the experimental data , use the optical flow method to extract the cow torso image from the input cow video data to form an image data set, each cow has its own image data set, and randomly classify all the obtained image data sets to form a training set and a test set , so far the collection of cow data is completed;

[0074] The second step is to preprocess the training set and test set:

[0075] Through the caff...

Embodiment 2

[0118] Others are the same as in Embodiment 1 except that the cow torso image is extracted from the input cow video data using the frame difference method.

Embodiment 3

[0120] Test the performance of a convolutional neural network:

[0121] Use the test picture to test the network, and use the calculation formula (6) to calculate the probability that the cows belong to different individuals,

[0122]

[0123] Among them, i is the individual number ordinal number, i=1,...,20, choose the maximum value c m , then the cow belongs to the mth individual.

[0124] Algorithm experiments were carried out on the data sets of the 10th, 15th and 20th dairy cows, and the experimental results are shown in Table 1.

[0125] Table 1. Recognition accuracy (%) of the two algorithms

[0126]

[0127] The data in Table 1 shows that the present embodiment tests the recognition accuracy of the 10th, 15th and 20th milk cow data sets respectively, and the recognition results of the method of the present invention are respectively 94.3%, 97.1%, 95.6%, and the average result 95.7%, these results are higher than the SIFT algorithm, about 6.7% higher than the a...

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 dairy cow individual recognition method based on a deep convolutional neural network, and relates to an image recognition method in image data processing. According to the dairy cow individual recognition method, the dairy cow individual can be effectively recognized by extracting characteristics by virtue of a convolutional neural network in deep learning and combining the characteristics with textural features of dairy cows. The dairy cow individual recognition method comprises the following steps: collecting dairy cow data; preprocessing a training set and a test set; designing the convolutional neural network; training the convolutional neural network; generating a recognition model; and recognizing the dairy cow individual by virtue of the recognition model. By virtue of the dairy cow individual recognition method, the defects that an existing algorithm for processing dairy cow images by virtue of an image processing technique is single, the stripe characteristics of the dairy cows are not adequately and well combined with an image processing technique and a mode recognition technique, and therefore, the recognition rate of the daily cows is low are overcome.

Description

technical field [0001] The technical solution of the present invention relates to an image recognition method in image data processing, in particular to a cow individual recognition method based on a deep convolutional neural network. Background technique [0002] At present, my country has basically formed a high-density and centralized dairy farming system, but there are still many problems such as low milk quality, low production efficiency and high cost. The main reason is that it relies too much on labor-intensive and extensive operations, the level of automation in the production process is low, and the accuracy and pertinence of disposal in each production link are obviously insufficient. For example, at present, the dairy industry in my country still generally adopts artificial observation feeding method, which is limited by the number of breeders and technical professional quality, which not only seriously restricts the efficiency of milk production, but also increa...

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
IPC IPC(8): G06K9/62G06K9/00G06N3/08
CPCG06N3/082G06N3/084G06V20/40G06V20/46G06F18/24G06F18/214A01K11/006
Inventor 张满囤徐明权于洋郭迎春阎刚单新媛米娜于明
Owner HEBEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com