Feature extraction method for image scene recognition

Abstract

The invention relates to a feature extraction method for image scene recognition. The feature extraction method comprises the first step of mining information in a group of training images of which the classes are known and the second step of recognizing test images to be recognized. The first step comprises the sub-steps of preprocessing the images, extracting target features of the images, decreasing the dimensions of the target features, executing the LDA model training algorithm, generating scene environment features of the training images, carrying out feature combination and executing the SVM training algorithm. The second step comprises the sub-steps of preprocessing the testing images, generating code words of the testing images, generating scene environment features of the testing images, extracting target features of the testing images, decreasing the dimensions of the target features of the testing images, carrying out feature combination on the testing images and generating image classes through a trained SVM classifier. By means of the feature extraction method, the calculation amount of an existing method is deceased, the application range is expanded, and the recognition accuracy is improved.

Description

technical field [0001] The invention belongs to image scene recognition technology, in particular to a feature extraction method for image scene recognition. Background technique [0002] The purpose of image scene recognition is to obtain the semantic information of the image and give its category label. It is an important research content in the fields of computer vision, pattern recognition and machine learning, and it is also an indispensable technology in practical fields such as image library management and image retrieval. The method based on bag of features (Bag of Features) and topic model is a research boom in recent years, and many new achievements and progress have been made. This type of method draws on the natural language processing process, treats the image as a collection of local observations and builds a feature bag, uses the feature bag to build a topic model, and generates features or directly generates categories. In addition, the object recognition t...

AI Technical Summary

Problems solved by technology

[0005]By disclosing a dimensionality reduction method for Object Bank features, it solves the technical problem that its dimensions are too high and difficult to combine with theme features

Images