Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Zero-sample deep-sea biological picture classification method based on multiple classifiers

A technology of image classification and multi-classifiers, which is applied to instruments, computer components, character and pattern recognition, etc., to achieve high feasibility, improve classification accuracy, and reduce domain drift

Active Publication Date: 2020-01-21
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the zero-sample problem, for complex image information, the extracted features have high-dimensional characteristics and redundant information

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
  • Zero-sample deep-sea biological picture classification method based on multiple classifiers
  • Zero-sample deep-sea biological picture classification method based on multiple classifiers
  • Zero-sample deep-sea biological picture classification method based on multiple classifiers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] like figure 1 As shown, this embodiment discloses a zero-sample deep-sea biological picture classification method based on multi-classifiers, which sequentially includes: image feature data import steps, category-specific classifier training steps, and invisible category inference steps.

[0038] (1) Image feature data import steps

[0039] Import image feature data, use known public datasets, or use GoogleNet network to extract image features and import datasets. The data set consists of two parts: visible category data and invisible category data, which do not overlap with each other. The visible category is the common marine biological species with rich data, including the categories that the model needs to learn. The invisible category is the deep-sea marine biological species with scarce data. Contains the categories that the model needs to recognize. The dataset contains visual feature data, labels and semantic descriptions of each image. The label is the categor...

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 zero-sample deep-sea biological picture classification method based on multiple classifiers. The method comprises the following steps that (1) image feature data importing, wherein a data set is composed of visual features, semantics and label information of visible categories and invisible categories, common marine organism categories with labels serve as the visible categories, and deep-sea organism categories lack of data serve as the invisible categories; (2) class specific classifier training: utilizing visible class data training to establish different visual semantic mappings for different classes on the basis of reserving a manifold structure so as to improve the classification accuracy of the visible classes; and (3) inferring the invisible category, migrating the weight between the visible category and the invisible category semantics, synthesizing a mapping matrix of the invisible category by using the mapping matrix of the visible category, and obtaining the label of the invisible category according to the distance. According to the method, the influence of mapping domain drift is reduced to a certain extent, and the method is accurate and feasible.

Description

technical field [0001] The invention relates to the field of zero-sample image classification, in particular to a multi-classifier-based zero-sample deep-sea biological picture classification method. Background technique [0002] Deep-sea organisms are an important part of the marine system. From the perspective of biodiversity and ecosystems, deep-sea organisms are diverse and have extremely high research value. They also have extensive application value in the fields of industry, medicine, and environmental protection. The deep sea area where these creatures live is dark all year round, without sunlight, and the temperature is low, the pressure is high, and the seawater has high salinity. Human beings' understanding of deep-sea life usually comes from data taken by remote-controlled submarines. Most known species do not occur frequently enough and data are scarce to collect and label a representative set of example images. Moreover, as humans continue to explore the deep...

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): G06K9/62
CPCG06F18/241G06F18/214
Inventor 周智恒牛畅尚俊媛黄俊楚张鹏宇
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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