Animal identification method based on deep neural network
A technology of deep neural network and recognition method, applied in the direction of neural learning method, biological neural network model, neural architecture, etc., which can solve the problems of pet loss, pets and stray cats and dogs not being effectively managed, stray cats and dogs breeding overflow, etc. , to achieve the effect of structural improvement, excellent recognition performance, and good recognition performance
Pending Publication Date: 2022-08-05
WUHAN UNIV OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Pets have gradually entered thousands of households. However, problems such as pet loss and the proliferation of stray cats and dogs are also emerging. The lack of effective management of pets and stray cats and dogs is a major problem in the current pet industry.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0021] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.
[0022] like figure 1 As shown, an animal recognition method based on a deep neural network includes the following steps:
[0023] 1) Receive the picture p of the animal submitted by the user, trim and correct the original animal picture p submitted by the user, and then frame the facial area of the animal to obtain the animal face picture;
[0024] In step 1), the improved YOLOv3 model is used to crop and correct the picture p, and then frame the facial area of the animal. YOLOv3, as a representative of the unit price segment target detection algorithm, has the characteristics of high real-time performance. I...
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
The invention discloses an animal identification method based on a deep neural network, and the method comprises the following steps: 1), receiving an animal picture submitted by a user, cutting the original animal picture submitted by the user, and selecting a facial region of the animal to obtain an animal facial picture; 2) according to the animal face picture, extracting animal features through a feature extraction model; and 3) calculating the Euclidean distance between the feature vector t and the animal features in the animal feature information database, performing feature matching by using a KNN algorithm, and performing identification. According to the animal face feature extraction method, the face of the animal can be corrected, it is guaranteed that the extracted features have higher recognition degree, and the recognition model has good recognition performance.
Description
technical field [0001] The invention relates to computer vision technology, in particular to an animal identification method based on a deep neural network. Background technique [0002] In the context of the era of intelligence, artificial intelligence has gradually penetrated into various fields and affects all aspects of people, of which face recognition is an important manifestation of artificial intelligence. People are paying more and more attention to face recognition technology, and the application scenarios of face recognition technology are also constantly trying. With the rapid economic growth, people pay more attention to spiritual needs. Pets have gradually entered thousands of households. However, problems such as lost pets and the proliferation of stray cats and dogs continue to appear. The lack of effective management of pets and stray cats and dogs is a major problem and difficulty in the current pet industry. Therefore, how to digitally register and manag...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06V40/16G06V10/74G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06V40/168G06V40/172G06V10/761G06V10/82G06N3/08G06N3/045G06F18/24143
Inventor 赵冬冬彭晾张芝芝冀子晗
Owner WUHAN UNIV OF TECH