Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Topic model-fused scene image classification method

A technology of scene images and topic models, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as the bottom-level and high-level semantic gap, and achieve the effect of increasing the number and expanding the data set

Inactive Publication Date: 2018-03-16
CHONGQING UNIV OF POSTS & TELECOMM
View PDF6 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims to solve the problem of the semantic gap between the bottom layer and the high layer caused by the inconsistency between the bottom layer visual information of the image and the high layer semantic information that people understand the image in the prior art

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
  • Topic model-fused scene image classification method
  • Topic model-fused scene image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The technical solutions in the embodiments of the present invention will be described clearly and in detail below with reference to the drawings in the embodiments of the present invention. The described embodiments are only some of the embodiments of the invention.

[0021] The technical scheme that the present invention solves the problems of the technologies described above is:

[0022] figure 1 A flow chart of the method for realizing scene image classification based on deep learning of the present invention is shown, and the specific steps are as follows:

[0023] (1) Preprocessing the image data set, including using cropping, flipping, histogram equalization, adjusting the brightness of the image, expanding the data set, and adjusting the image format to the readable format of the convolutional neural network model, selecting the data set 70% of the set is used as the training set, and the remaining 30% is used as the verification set;

[0024] (2) Use the open...

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 topic model-fused scene image classification method, and relates to the field of deep learning and image classification. The method comprises the following steps of: preprocessing data sets, and expanding the quantity of obtained data sets so as to obtain an image data format according with deep learning model processing; constructing a convolutional neural network modelaccording with scene image classification, and pre-training the processed image data sets by using a convolutional neural network; and carrying out end-to-end iterative training on the constructed convolutional neural network by using training sets, adjusting parameters in the network, verifying the trained model by using verification sets, modeling extracted scene image features with discrimination ability, extracting hidden topic variables between the features and images so as to obtain image topic distribution represented by a k-dimensional vector, wherein k represents a topic quantity, each image can be considered as a probability distribution diagram formed by a plurality of topics, and scene image classification is realized by utilizing a classifier.

Description

technical field [0001] The invention belongs to the technical field of deep learning and image classification and recognition, and specifically relates to a method for classifying scene images by integrating theme models. Background technique [0002] Scene image classification, that is, given a set of scene images containing multiple target categories (such as mountains, rivers, roads, etc.), the global semantics of the image is analyzed and understood according to the distribution relationship of each target category. Scene image classification not only has an overall understanding of the category of the entire image, but also analyzes the context information between objects and regions in the image, which enables a deeper understanding of the content of the image and promotes machine vision. The development of fields such as object recognition and image retrieval has a wide range of applications. [0003] With the rapid development of intelligent camera equipment and com...

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): G06K9/00G06K9/62
CPCG06V20/35G06F18/24
Inventor 丰江帆付阿敏孙文正夏英
Owner CHONGQING UNIV OF POSTS & TELECOMM
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
Eureka Blog
Learn More
PatSnap group products