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

A method and system for cow face alignment based on depth neural network

A technology of deep neural network and convolutional neural network, applied in the field of cow face alignment method and system based on deep neural network, to achieve the effect of improving recognition accuracy, meeting performance and speed requirements, and good generalization ability

Inactive Publication Date: 2018-12-14
深源恒际科技有限公司
View PDF12 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the deficiencies in the above-mentioned prior art, the present invention provides a method and system for aligning cow faces based on a deep neural network, which solves the problem of how to improve the accuracy of cow face recognition by aligning cow face images

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
  • A method and system for cow face alignment based on depth neural network
  • A method and system for cow face alignment based on depth neural network
  • A method and system for cow face alignment based on depth neural network

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0047] see figure 1 , the present embodiment provides a method for aligning cow faces based on a deep neural network, the method for aligning cow faces based on a deep neural network includes the following steps:

[0048] S101. Collect sample data, and calibrate m key points of cow faces according to the sample data.

[0049] S102. Perform preprocessing on the calibrated sample data, perform normalization processing on all sample data, and simultaneously scale images of all sample data to the same resolution size.

[0050] S103, using the preprocessed sample data to train the cow face key point positioning model through a convolutional neural network;

[0051] S104, using the trained bull-face key point positioning model to input the cow-face image to be positioned, outputting the coordinates of the bull-face key points of the bull-face image to be positioned through the bull-face key point positioning model;

[0052] S105. Align the cow face according to the coordinates of th...

no. 2 example

[0067] see figure 2 , the present embodiment provides a deep neural network-based cow-face alignment system 200, the cow-face alignment system 200 based on a deep neural network includes:

[0068] The collection module 201 is used to collect sample data, and mark out m cow face key points for the sample data;

[0069] A preprocessing module 202, configured to preprocess the calibrated sample data, perform normalization processing on all sample data, and simultaneously scale images of all sample data to the same resolution size;

[0070] The training module 203 is used to use the preprocessed sample data to train the cow face key point positioning model through a convolutional neural network;

[0071] Key point coordinates determination module 204, for using the well-trained bull face key point positioning model input to be located cow face image, output the coordinates of the cow face key point of the cow face image to be positioned by this cow face key point positioning mod...

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 method and system for cow face alignment based on depth neural network. The method comprises the following steps: collecting sample data and marking m key points of the cow face; preprocessing the sample data, normalizing all the sample data, and zooming the image to the same resolution. The key point localization model of cow face is trained by convolution neural network. The trained model is used to input the bull face image to be located, and the coordinates of the key points of the bull face image to be located are outputted. Cow face alignment is performed according to the coordinates of the key points of the cow face. The invention solves the problem of diversified postures of cow face caused by shooting angles of shooters and cow movements in the course ofshooting dairy cows, and can eliminate the cow face images which do not conform to the recognition standard, thereby improving the recognition accuracy of dairy cows. At the same time, the invention is not only applicable to the facial recognition of dairy cows, but also applicable to the facial behavior analysis of dairy cows, age analysis of dairy cows and other scenes.

Description

technical field [0001] The invention relates to the technical field of facial recognition, in particular to a method and system for aligning cow faces based on a deep neural network. Background technique [0002] The cow face recognition technology is based on the facial features of cows, and extracts the image features contained in the cow face that can distinguish the identity of the individual cow from the input cow face image. The extracted cow face feature information can be compared with the existing cow face feature information, so as to determine whether the cows contained in two different images are the same head. The whole process generally includes steps such as cow face detection, cow face image preprocessing, cow face alignment, and cow face recognition. [0003] Among them, the cow face alignment is to align the detected cow face images to the same reference position of the image, transform the cow faces of different sizes and angles according to the correspon...

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): G06K9/00G06K9/46G06K9/62G06T3/00G06T3/40
CPCG06T3/40G06T2207/20084G06T2207/20081G06V40/10G06V10/462G06F18/214G06F18/24G06T3/02
Inventor 谢树雷
Owner 深源恒际科技有限公司
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com