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

Establishment method of pig face facial expression recognition framework based on multi-task cascade

A technique for facial expression and method building, applied in neural learning methods, character and pattern recognition, neural architecture, etc.

Active Publication Date: 2022-04-29
JILIN AGRICULTURAL UNIV
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention classifies and recognizes pig face facial expressions in video images based on multi-attention mechanism cascaded long-short-term memory network model

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
  • Establishment method of pig face facial expression recognition framework based on multi-task cascade
  • Establishment method of pig face facial expression recognition framework based on multi-task cascade
  • Establishment method of pig face facial expression recognition framework based on multi-task cascade

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] see Figure 1 to Figure 3 As shown, the pig face facial expression recognition framework model based on the multi-attention mechanism cascaded long-short-term memory network model of the present invention firstly performs data expansion on the basis of sharing the pig face facial expression data set, and the specific method is the change of video brightness , small-angle rotation, left-right flip, etc., the data set divides expressions into four categories, namely anger, joy, fear and peace. The division of the training set and the verification set adopts the method of 5-fold cross-validation. The training set is used for training, and the error between the actual output result of the training and the label value is calculated. The difference is transferred from top to bottom through the back propagation algorithm, and the Weights Update the weights. After training, save the trained neural network model, and input the verification set to adjust the parameters to make 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 relates to a method for establishing a pig face facial expression recognition framework based on multi-task cascading, and belongs to the technical fields of computer image recognition and artificial intelligence. It is the first time to propose the application of the cascade framework model to the classification and recognition of time-series facial expression images of domestic pigs. The network model is composed of three cascaded structures. Firstly, the pig face facial expression video frame images are selected at equal intervals and input into the simplified multi-task cascaded convolutional neural network. Secondly, the extracted feature map of the pig face sequence frame is input into the multi-attention mechanism module to capture the facial salient area caused by the expression change, and realize the attention to the subtle changes of the face. Then, the fine feature map and multi-attention feature map extracted from the video frame are fused through the merge array operation and then input into the long short-term memory network to realize expression classification and recognition. Through the expression recognition of livestock, emotional regulation can be better realized, thereby improving feed digestibility and utilization rate, increasing growth rate, and improving production efficiency.

Description

technical field [0001] The present invention relates to the technical fields of computer image recognition and artificial intelligence, in particular to a method for establishing a pig face facial expression recognition framework based on multi-task cascading, and an end-to-end model framework for livestock facial expression recognition in videos. Background technique [0002] Animal emotion research is one of the important research goals of animal science, which can better evaluate the welfare of livestock, including pigs and other livestock in the process of feeding a good mood to ensure the highest feed digestibility and utilization rate, thereby increasing growth rate and increasing production Benefit plays an important role, and thus has great significance for emotion research based on facial expression recognition. [0003] Animal facial expression recognition faces challenges. First, compared with human facial expression recognition, animal facial expression changes a...

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 Patents(China)
IPC IPC(8): G06V20/40G06V10/764G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06V20/46G06N3/045G06N3/044G06F18/2415
Inventor 温长吉张笑然吴建双于合龙石磊郭宏亮毕春光李卓识苏恒强薛明轩杨之音
Owner JILIN AGRICULTURAL UNIV
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