Supervised manifold learning-based scene classifying method and device

Abstract

The invention discloses a supervised manifold learning-based scene classifying method and device. The supervised manifold learning-based scene classifying method comprises the following steps of: inputting N training images which are artificially labeled with scene categories, wherein the number of the scene categories is C; extracting S SIFT (Scale Invariant Feature Transform) features from the N training images and acquiring a codebook which consists of M clustering centers of the S SIFT features; for each scene category, setting up a supervised spectrogram G= (V, E) and acquiring a weight matrix which corresponds to V by taking the SIFT features and the codebook as nodes; acquiring metrics from SIFT features on each manifold structure to M codons; inputting new training images or testing images; acquiring metrics from the SIFT features on the new training images or the new testing images to the M codons; computing the membership grade of the SIFT features on the new training imagesor the new testing images to the M codons to obtain C histogram vectors; and learning the C histogram vectors by using a support vector machine to obtain judging models for each scene categories.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a scene classification method and device based on supervised manifold learning. Background technique [0002] When classifying scenes, machine learning methods are used to obtain the scene categories represented by pictures. It plays a very important role in scene recognition. The application areas of scene recognition are mainly in remote sensing image interpretation, object recognition and understanding, content-based and image and video retrieval. [0003] The existing scene classification method is that for each picture, a vector (that is, an array of 1*n) is extracted to represent it. Then the vector of the training picture and its category are sent to SVM (Support Vector Machine) for training to obtain a classifier for each scene category. For the test image, the corresponding vector is also extracted, and its scene category is obtained according to the trained classifier....

AI Technical Summary

Problems solved by technology

However, the traditional soft allocation and hard allocation algorithms do not consider the manifold characteristics of high-dimensional image feature points.

The efficiency of manifold calculation is very poor, and how to establish the manifold structure of data is also a problem

Using the method of spectrogram assignment can significantly improve the accuracy of the algorithm, but the spectrogram algorithm needs to invert the Laplacian matrix, making the algorithm less efficient than the traditional linear assignment method

And the histogram vector of the statistical image is short, and the recognition rate is poor

Images