HOG algorithm image recognition method based on grid cell memory

A grid cell and image recognition technology, applied in the field of image recognition, can solve the problems of high power consumption, artificial intelligence image recognition relying on big data training samples, etc.

Active Publication Date: 2020-08-28
CHONGQING UNIV
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, the object of the present invention is to provide a grid cell memory-based HOG algorithm image recognition method, which has solved the technical problem that existing artificial intelligence recognition images need to rely on large data training samples and super power consumption

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
  • HOG algorithm image recognition method based on grid cell memory
  • HOG algorithm image recognition method based on grid cell memory
  • HOG algorithm image recognition method based on grid cell memory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0064] The HOG algorithm image recognition method based on grid cell memory in this embodiment includes establishing a HOG algorithm image recognition system based on grid cell memory, and the described HOG algorithm image recognition system based on grid cell memory includes a HOG algorithm module and A grid cell memory model, the grid cell memory model comprising:

[0065] Grid cells, which are used to anchor each feature of a given stimulus, which is the input image, and the relative positions of the anchored features on all grids are consistent with each other;

[0066] distance cells, which are used to calculate displacement vectors between sites encoded by grid cell population vectors;

[0067] sensory cells, i.e. feature detectors, which are cells with a Gaussian tuning curve over possible image pixel values;

[0068] Labeling cells, driven by ...

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 an HOG algorithm image recognition method based on grid cell memory. The method comprises the steps that an HOG algorithm image recognition system based on grid cell memory isestablished, an HOG algorithm module is used for matching an image with the similarity capable of activating recognition cells, and if it is matched that the corresponding image in a test set activates the recognition cells, recognition is finished; if the image in the test set cannot activate the recognition cells, the grid cell memory model takes over image recognition, the recognition cells areactivated through feature recognition accumulation of grid cell memory, and image recognition is completed. Once the HOG algorithm image recognition system based on grid cell memory learns necessaryassociation, the recognition memory of the HOG algorithm image recognition system can be tested by presenting stimulation in a training set. The training set is single-sample learning, and the effectof small-sample learning is achieved by presenting stimulation during memory.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image recognition method. Background technique [0002] Deep learning, or ANNs, achieves remarkable results by feeding massive training datasets into large ANNs. For example, when the deep learning model continues to learn through a large number of training samples, it can indeed recognize human faces or certain special scenes with a very high accuracy rate. But it is expected that ANNs or deep learning models can use a small number of samples to learn the characteristics of new categories, better imitating the ability of humans to learn type characteristics from small sample data. Contents of the invention [0003] In view of this, the object of the present invention is to provide a grid cell memory-based HOG algorithm image recognition method, which has solved the technical problems that the existing artificial intelligence image recognition needs to rely on larg...

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): G06K9/46G06K9/62
CPCG06V10/507G06V10/757G06F18/214
Inventor 李秀敏许文强易浩薛方正
Owner CHONGQING 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