Ganglion differentiation-based incremental target identification system

A target recognition and ganglion technology, applied in the field of target recognition, can solve problems such as poor anti-noise ability and solidified network structure

Active Publication Date: 2017-07-04
NANJING UNIV
View PDF7 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the following technical problems. The existing recognition method has a solidified

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
  • Ganglion differentiation-based incremental target identification system
  • Ganglion differentiation-based incremental target identification system
  • Ganglion differentiation-based incremental target identification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the present invention clearer and easier to understand, specific embodiments are described in detail below in conjunction with the accompanying drawings.

[0050] Such as figure 1 As shown, the present invention discloses an incremental target recognition system based on ganglion differentiation, which learns online while recognizing, and realizes the growth of the network structure in an unsupervised manner. The method comprises the steps of:

[0051] Step 1, image preprocessing: perform grayscale, normalization and whitening preprocessing on all images in the dataset, such as figure 2 shown.

[0052] Firstly, the color image I is weighted grayscale by the original RGB three-channel according to the ratio of [0.2989, 0.5870, 0.1140] to obtain the image X.

[0053] Next, subtraction normalization is performed, that is: Y ij =X ij -∑ pq w pq ·X i+p,j+q , where w pq is the weight of row p and column q of the Gaussian weighted window, and satisfi...

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 ganglion differentiation-based incremental target identification system. The system is composed of a low hidden layer, a ganglion layer, a high hidden layer and a classifier, wherein the ganglion layer is located between the low hidden layer and the high hidden layer; ganglions of the ganglion layer extract a sample characteristic law, and through activation and differentiation of the ganglions, corresponding independent characteristic sets are formed in the high hidden layer and characteristic memory of samples is formed; a quantity of the characteristic sets of the high hidden layer is variable; newly added ganglions form new memory for new samples, and the characteristic sets of the high hidden layer are adaptively updated, so that incremental target identification is realized; the ganglions refer to neural network nodes used for representing a group of samples with similar distribution laws, and when an input sample characteristic parameter is greater than an activation threshold, the ganglions are activated and form the independent characteristic sets in the high hidden layer; when the activity of the activated ganglions is lower than a threshold, the ganglions die; and different ganglions are activated for the samples with different characteristics, and ganglions are newly added.

Description

technical field [0001] The invention belongs to the field of target recognition, in particular to an incremental target recognition system based on ganglion differentiation. Background technique [0002] The early deep neural network is end-to-end, and the network structure remains unchanged during the training process, which is the process of learning network parameters. When the training set is complete and the network depth is sufficient, it can theoretically express arbitrarily complex original data. In many practical applications, the complete data set cannot be obtained at one time, so the learning algorithm also needs to be a continuous process. For example, in software products such as image search and photo shopping, pre-obtain the existing product image set, and use the deep neural network to find the closest top items for the input image as the recommendation result. However, when inputting a newly developed product image with a new appearance, although the trai...

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): G06N3/08G06K9/62
CPCG06N3/082G06F18/2111
Inventor 王元庆胡晶晶王冉詹伶俐
Owner NANJING UNIV
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