Multi-feature-fusion-convolutional-neural-network-based plankton image classification method

A convolutional neural network and multi-feature fusion technology, applied in the field of plankton image classification, can solve problems such as difficulty in classifying plankton images, and achieve the effect of improving the accuracy rate

Active Publication Date: 2017-02-01
OCEAN UNIV OF CHINA
View PDF2 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This application solves the technical problem of difficult classification of large-scale multi-category plankton images in the prior art by providing a plankton image classification method based on multi-feature fusion convolutional neural network

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
  • Multi-feature-fusion-convolutional-neural-network-based plankton image classification method
  • Multi-feature-fusion-convolutional-neural-network-based plankton image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] A plankton image classification method based on multi-feature fusion convolutional neural network, such as figure 1 shown, including the following steps:

[0030] S1: Collect clear plankton images and build a large-scale multi-category plankton image data set. The plankton images in this data set are used as original feature images. The number of collected images is about 30,000 to 90,000, and the types of plankton are About 30 to 50 categories;

[0031] S2: Process the original feature image, extract the global feature of plankton, and obtain the global feature image. The specific processing steps are:

[0032] S21: Using the image segmentation Scharr operator to convert the original feature image, the converted image includes global features and local features;

[0033] S22: Using a bilateral filtering method to remove local features in the converted image;

[0034] S23: Enhance the contrast to highlight the global features in the converted image;

[0035] S3: Pro...

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 provides a multi-feature-fusion-convolutional-neural-network-based plankton image classification method. The method comprises: lots of clear plankton images are collected and a large-scale multi-type plankton image data set is constructed; a global feature and a local feature are extracted by using an image conversion and edge extraction algorithm; an original feature image, a global feature image, and a local feature image are inputted into a depth-learning multi-feature-fusion convolutional neural network to carry out training, thereby obtaining a multi-feature-fusion convolutional neural network model; and then the plankton images are inputted into the multi-feature-fusion convolutional neural network model and classification is carried out based on a finally outputted probability score. According to the invention, the angle of biological morphology, the computer vision method, and the depth learning technology are combined; and thus the classification accuracy for plankton images, especially large-scale multi-type plankton images is high.

Description

technical field [0001] The invention relates to the technical fields of biomorphological analysis, computer vision and deep learning, in particular to a plankton image classification method based on a multi-feature fusion convolutional neural network. Background technique [0002] Due to the importance of plankton in ecosystems, the processing and analysis of plankton images is becoming more and more important. However, due to the large number of types of plankton, and there are also very large differences in morphological characteristics and other aspects of various types of plankton. For plankton images, the appearance of the same type of plankton is not necessarily identical, and may have great differences. For different types of plankton, their appearance and other characteristics may also have a high degree of similarity. This intra-category difference and inter-category similarity pose a huge challenge to plankton image classification. Traditional image classificatio...

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): G06K9/46G06K9/62G06T7/00G06T7/41
CPCG06T2207/20081G06T2207/20084G06V10/443G06V10/462G06F18/2415
Inventor 郑海永王超俞智斌戴嘉伦郑冰
Owner OCEAN UNIV OF CHINA
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap