Image classification method based on noise reduction sparse automatic encoder and density space sampling

Abstract

The invention discloses an image classification method based on a noise reduction sparse automatic encoder and density space sampling. The image classification method based on a noise reduction sparseautomatic encoder and density space sampling includes the steps: constructing an image block training set; constructing a noise reduction sparse automatic encoder of single hidden layer, inputting the image block training set, and training the noise reduction sparse automatic encoder; performing density space sampling on each image in a training image data set and a test image data set; using thenoise reduction sparse automatic encoder to extract local characteristic set information from the space area obtained by performing density space sampling on each image; using two layers of laminatedFisher Vector to encode the characteristic set information, so as to obtain the final Fisher vector of each image; and training a classifier by means of the Fisher vector, so as to realize image classification. The image classification method based on a noise reduction sparse automatic encoder and density space sampling can accurately acquire the image information, can improve the classificationaccuracy of images, and can be used for construction of a large scale image classification and retrieval system.

Description

Technical field [0001] The invention belongs to the technical field of image classification, and particularly relates to an image classification method based on a noise reduction sparse automatic encoder and density space sampling. Background technique [0002] With the development of multimedia technology, image classification has become a hot issue in the field of computer vision. Image classification is to classify images into different pre-set categories based on certain attributes. How to effectively express the image is the key to improving the accuracy of image classification. Among them, the selection and extraction of features are the key and difficult problems in image classification. Although the traditional Gabor filter, SIFT, LBP, HOG and other artificially designed feature methods have achieved certain results in image classification, these methods need to be carefully designed and cannot be well applied to specific problems. In recent years, deep learning has ach...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides an image classification method based on denoising sparse autoencoder and density space sampling, aiming at solving the problem of image feature extraction and encoding, overcoming the defects existing in existing image classification methods, reducing computing cost, and improving classification accuracy

Images