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

Chinese white dolphin dorsal fin identification method based on convolutional neural network

A technology of convolutional neural network and recognition method, which is applied in the field of Chinese white dolphin dorsal fin recognition, can solve the problems of low accuracy and achieve high positioning accuracy, high recognition accuracy and high efficiency

Pending Publication Date: 2020-02-25
SHANTOU UNIV
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using these methods to identify the dorsal fin of the Chinese white dolphin has the following disadvantages: the individual characteristic information contained in the spots of the dorsal fin is ignored, and the accuracy rate is low when identifying a population with a large number of individuals

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
  • Chinese white dolphin dorsal fin identification method based on convolutional neural network
  • Chinese white dolphin dorsal fin identification method based on convolutional neural network
  • Chinese white dolphin dorsal fin identification method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] The present embodiment provides a Chinese white dolphin dorsal fin recognition method based on a convolutional neural network, such as figure 1 , including the following steps:

[0038] S1: Build a Chinese white dolphin dorsal fin image library with location boxes and identification labels, where the location box marks the position of the dorsal fin in the image, and divide the Chinese white dolphin dorsal fin image library into training samples and test samples;

[0039] S2: Use the training samples to train the first convolutional neural network for locating the dorsal fin region, the second convolutional neural network for identifying the left and right sides of the dorsal fin, the third convolutional neural network for identifying the image quality of the dorsal fin, and the third convolutional neural network for identifying the dorsal fin image quality. A fourth convolutional neural network that identifies the individual to which the dorsal fin belongs;

[0040] S...

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 Chinese white dolphin dorsal fin identification method based on a convolutional neural network, and the method comprises the steps: constructing a Chinese white dolphin dorsal fin image library with a position box and an identification tag, and dividing the Chinese white dolphin dorsal fin image library into a training sample and a test sample; training a convolutional neural network for positioning a dorsal fin region; respectively training three convolutional neural networks for identifying the left and right sides of the dorsal fin, the image quality of the dorsalfin and an individual to which the dorsal fin belongs; positioning a dorsal fin region of the image in the test sample through a convolutional neural network for positioning; and identifying the dorsal fin area through the three convolutional neural networks for identification, and outputting identification results of the left and right sides of the dorsal fin, the dorsal fin image quality and theindividual to which the dorsal fin belongs. According to the method, the feature learning capability of the convolutional neural network is fully utilized, automatic identification of the dorsal finof the Chinese white dolphin can be efficiently and accurately realized, and marine biologists are helped to analyze the individual habits and population characteristics of the Chinese white dolphin.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, relates to a method for identifying the dorsal fin of the Chinese white dolphin based on a convolutional neural network. Background technique [0002] The Chinese White Dolphin is a coastal species that inhabits eastern Southeast Asia. In recent years, due to factors such as coastal development and increased traffic, as well as overfishing and seawater pollution, the number of Chinese white dolphins has declined sharply. At present, the Chinese white dolphin has become an endangered species and needs human protection. Usually in the protection process, in order to track and observe the growth process of Chinese white dolphins, it is often necessary to identify and statistically analyze Chinese white dolphins that appear in coastal areas. [0003] The traditional method of identifying Chinese white dolphins is to implant tags on their bodies, but this meth...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/10G06F18/214G06F18/2431
Inventor 冯靖安郑锐强范衠彭杰华朱贵杰刘文华
Owner SHANTOU 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