Image similarity calculation method based on improved SoftMax loss function

A loss function and image similarity technology, which is applied in the field of deep learning, can solve the problems that the recognition accuracy rate needs to be improved, and achieve the effect of avoiding low image recognition accuracy rate, strong image feature expression ability, and improving accuracy

Active Publication Date: 2018-12-07
CHINA JILIANG UNIV
View PDF8 Cites 7 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

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 SoftMax loss function
  • Image similarity calculation method based on improved SoftMax loss function
  • Image similarity calculation method based on improved SoftMax loss function

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0027] The present invention will be further described below in conjunction with the drawings.

[0028] Such as figure 1 Shown is a schematic diagram of the image recognition network structure. 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 in 1,000 categories. Input the image recognition training data set to the convolutional neural network Start training in the image recognition network. The image recognition network based on the convolutional neural network includes four network layers: convolutional layer, maximum sampling layer, fully connected layer, and improved Soft-Max layer. Among them, a convolutional layer and A maximum sampling layer constitutes an image recognition substructure. The ...

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 an improved Soft-Max loss function. An activating function of the improved Soft-Max layer in an image identification network isan improved Soft-Max activation function. In a reverse propagation process, the improved Soft-Max loss function is utilized for updating a network weight. Compared with a traditional Soft-Max loss function, the improved Soft-Max loss function has an advantage of increasing a decision edge which is obtained through learning of an image identification network. In a testing period, a trained image identification model is utilized for performing characteristic vector extraction on two testing images, and cosine similarity between the characteristic vector is calculated. Compared with an image similarity threshold, if the cosine similarity is higher than or equal with the image similarity threshold, a fact that the two images are in the same kind is determined; and if the cosine similarity is lower than the image similarity threshold, a fact that the two images are in different kinds is determined.

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
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 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