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

Image similarity calculation method based on improved soft-max loss function

A loss function, image similarity technology, applied in the field of deep learning, can solve the problem that the recognition accuracy needs to be improved

Active Publication Date: 2021-09-14
CHINA JILIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The image recognition model trained with the deep neural network and the traditional Soft-Max loss function has a much higher recognition accuracy than the model trained by the traditional method, but the recognition accuracy still needs to be improved

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
  • Image similarity calculation method based on improved soft-max loss function
  • Image similarity calculation method based on improved soft-max loss function
  • Image similarity calculation method based on improved soft-max loss function

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with accompanying drawing.

[0028] Such as figure 1 Shown is a schematic diagram of the image recognition network structure, and the image similarity calculation method based on the improved Soft-Max loss function of the present invention mainly includes the following steps:

[0029] Step (1): Prepare the image recognition training data set. The training data set is the open source image recognition database ImageNet 2012, including more than 1 million images of 1000 categories. The image recognition training data set is input to the convolutional neural network-based Start training in the image recognition network, and the image recognition network based on the convolutional neural network includes a convolutional layer, a maximum sampling layer, a fully connected layer, and four network layers of the improved Soft-Max layer, wherein a convolutional layer and A maximum sampling layer constitutes an ...

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 image similarity calculation method based on the improved Soft-Max loss function. The activation function of the improved Soft-Max layer in the image recognition network adopts the improved Soft-Max activation function, and the backpropagation process uses The improved Soft-Max loss function updates the network weights. Compared with the traditional Soft-Max loss function, the improved Soft-Max loss function increases the decision edge learned by the image recognition network; The model extracts feature vectors from two test images, calculates the cosine similarity between the feature vectors, and compares it with the set image similarity threshold. If it is greater than or equal to the image similarity threshold, it is determined that the two images are of the same type of image. If it is smaller than the image similarity threshold The similarity threshold determines that two images are of different types.

Description

technical field [0001] The invention belongs to the field of deep learning for extracting image features by a deep neural network, relates to technologies such as neural networks and pattern recognition, and in particular relates to an image similarity calculation method based on an improved Soft-Max loss function. Background technique [0002] Image recognition technology is a research hotspot in artificial intelligence and pattern recognition today, and it is a biometric technology that identifies the objects in the image based on the observed image. It has a wide range of applications in aerospace, medicine, industrial automation, robotics, and military. [0003] With the development of science and technology, the scope of application of image recognition has been continuously expanded, and gradually extended from the field of public security criminal investigation to industrial neighborhoods, such as laser positioning cutting, positioning marking, and positioning welding...

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 Patents(China)
IPC IPC(8): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/084G06V10/40G06N3/045G06F18/22
Inventor 章东平李建超
Owner CHINA JILIANG 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

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