An image classification algorithm and system combining superpixel saliency features and HOG features

Abstract

The invention discloses an image classification algorithm and system combining the superpixel saliency features and the HOG features, comprising the following steps of 1 extracting the HOG features from the original data set to obtain a feature set A; 2 processing the original data set by using the superpixel segmentation to obtain the reconstruct salient image data set; 3 obtaining a new featureset B by using the reconstructed salient image set in an SLBP coding mode, wherein the SLBP coding mode is an improvement of the traditional LBP coding mode; 4 carrying out the feature fusion, addingthe feature set A and the feature set B obtained in steps 1 and 3; 5 combining the training data obtained in step 4, using the KNN classifier to supervise and classify the test data and calculating the classification accuracy. The method of the invention well meets the requirements of the small-scale engineering design on the traditional machine learning algorithm, and to a certain extent improvesthe image classification accuracy.

Description

technical field [0001] The invention belongs to the technical field of image classification, and is suitable for classification scenarios such as unobvious features, difficult to capture, and high similarity of image data sets to be classified, and can be used in fields such as object recognition, object retrieval, and database management. Background technique [0002] In recent years, with the continuous integration of artificial intelligence technology into human life and industrial production, the exploration of machine vision is considered to be a research hotspot in the next decade. Object detection, pattern recognition, image segmentation and other technologies are very important as important fields of machine vision. How to improve the timeliness, classification accuracy, and robustness of image classification algorithms is a major challenge for researchers. Image classification mainly includes feature extraction, feature engineering, and feature classification proces...

AI Technical Summary

Problems solved by technology

This series of improvement methods is only an improvement on a single project, and different decisions need to be made for different data sets

[0003] In the future, deep learning has been unanimously praised by scholars. A series of deep learning networks such as convolutional neural network, recurrent neural network, and confrontational neural network have been applied to the field of image processing. Although the classification accuracy has been significantly improved, the amount of data is serious. A series of problems such as insufficient memory, insufficient memory of the machine and equipment, and excessive time consumption have come one after another.

Images