Unlock instant, AI-driven research and patent intelligence for your innovation.

Panda face recognition method based on limited training data

A technology for training data and face recognition, which is applied in image data processing, biometric recognition, character and pattern recognition, etc., can solve the problem of panda image analysis without verification or identification, and achieve accurate and effective recognition and elimination Effect of Manually Annotated Requirements

Active Publication Date: 2020-03-10
CHENGDU RES BASE OF GIANT PANDA BREEDING
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] As mentioned above, most of the existing panda image analysis work is not used for verification or identification, Zeng Chenying [4] and Chen Juan [1] are suitable for panda recognition

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
  • Panda face recognition method based on limited training data
  • Panda face recognition method based on limited training data
  • Panda face recognition method based on limited training data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] 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 accompanying drawings and 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, that is, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.

[0029] Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the...

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 panda face recognition method based on limited training data. Firstly, the original panda image is input and manual panda face segmentation is performed, and the boundary detection is performed on the segmented panda face images to find the difference between each face image. Corresponding key points; extract panda face image features, align key points of all other images with the target image, use partial least squares regression as a classifier, and input positive and negative samples to train the classifier separately for each panda face image; Test with leave-one-out cross-validation to complete the establishment of the panda face recognition model. The present invention uses the edge of the face for algorithm execution, and uses partial least squares regression as a classifier, which can limit the number of pandas required and the number of training images for each panda, and is more helpful on the basis of the limited number of individual pandas and images. Accurate and efficient recognition of panda faces.

Description

technical field [0001] The invention belongs to the technical field of image analysis, in particular to the field of facial image recognition analysis of pandas. Background technique [0002] The giant panda (Ailuropodamelanoleuca) is a rare and endangered animal unique to my country and the flagship species of international wildlife protection. It is our duty and obligation to protect and breed giant pandas as "China's living fossils" and to promote the sustainable development of wildlife protection. The most basic and important work. In order to better and more effectively protect giant pandas, the state has conducted a national survey every ten years since 1974. So far, my country has carried out four national giant panda surveys. According to the results of the fourth national giant panda survey released by the State Forestry Administration in February 2015, by the end of 2013, the national wild giant panda population had reached 1,864, and the captive giant panda popul...

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): G06K9/00G06K9/46G06K9/62G06T3/00G06T7/11G06T7/136G06T7/194
CPCG06T3/0006G06T7/11G06T7/136G06T7/194G06V40/10G06V10/443G06V10/50G06V10/467G06F18/24G06F18/214
Inventor 张志和江伟健侯蓉迈特科沃斯基.沃切克.麦考尔徐兴鹏苏菡陈鹏崔凯
Owner CHENGDU RES BASE OF GIANT PANDA BREEDING