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

Hadoop platform based image classification method

A classification method and platform technology, which can be used in instruments, character and pattern recognition, computer parts, etc., and can solve problems such as long classification time

Inactive Publication Date: 2016-12-07
TIANJIN UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the amount of data is particularly large, the random forest classifier also faces the problem of too long classification time

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
  • Hadoop platform based image classification method
  • Hadoop platform based image classification method
  • Hadoop platform based image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention divides the image classification process into two stages: image feature extraction and random forest classifier training, and performs parallel design and programming in each stage, so that the overall process of image processing does not involve the operation of all image data ; In addition, the BoVW model is introduced in the first stage, and the image is simplified according to the model to improve the accuracy of image classification.

[0023] The present invention selects the Caltech-101 classic image database for experiments, and randomly selects eight types of images such as brain, bonsai, and leopards for classification. In each category of images, 30 images were selected as training images and 20 images were used as test images, and each experiment was performed 10 times. The present invention will be further described below.

[0024] (1) Extraction of image features

[0025] The Sift descriptor extracted by the Sift algorithm maintains ...

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 relates to a Hadoop platform based image classification method, which comprises the following steps: extracting the Sift features of an image; generating a SIFT characteristic database of a training image; using the Sift features to generate a BoVW visual dictionary; after the extraction of the BoVW model dictionary, comparing the training image already undergoing characteristic extraction with the dictionary and representing the training image as a dictionary-based histogram vector; using the histogram vector of the training image as the training input for a random forest classifier, and designing the parallelization of the classifier on Hadoop; and for test images in need of classification, performing features extraction and histogram vectorization successively before being inputted into a classifier for parallel classification on the Hadoop platform. The method of the invention not only has better classification accuracy, but also effectively reduces the classification time, and can be well applied to the large-scale image classification scenarios.

Description

technical field [0001] The invention relates to image classification technology, in particular to a distributed image classification method. Background technique [0002] 1. Image classification [0003] Image classification technology uses computer to automatically analyze and classify images, which is the basis of target detection and recognition, image retrieval and other fields. Image classification generally consists of two aspects: image feature extraction and feature-based classification. [0004] In terms of feature extraction, most of the current methods focus on the local features of images, and use algorithms such as Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) to extract local feature vectors. The Bag of Visual Words (BoVW) model goes a step further on this basis, clustering a large number of extracted feature vectors to generate a visual dictionary, and mapping the image into a histogram form of dictionary words according to t...

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 Applications(China)
IPC IPC(8): G06K9/62G06K9/46
CPCG06V10/462G06F18/24323
Inventor 侯春萍张倩楠王宝亮常鹏
Owner TIANJIN 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