Image Object Recognition Method Based on Surf Feature

Abstract

The invention provides an image object recognition method based on SURF features. Firstly, the image is preprocessed, and then SURF corner points and SURF descriptors are extracted from the image to describe the image features, and then the features are processed by PCA data whitening and dimensionality reduction. The processed features are clustered by Kmeans to establish a bag-of-words model, and the bag-of-words model is used to construct the visual vocabulary histogram of the image. Finally, the non-linear support vector machine (SVM) classification method is used for training, and the classification of different categories of images is completed. After the classification model modeling of different images in the training stage is completed, the images in the test set are detected in the test stage, and the function of object recognition in different images is realized. The invention has excellent performance in both recognition rate and speed, so that it can reflect the content of the image more objectively and accurately. In addition, the classification result of the SVM classifier is optimized, and the error rate of classifier judgment and the category of training samples are reduced. limitations.

Description

technical field [0001] The invention relates to the field of image object recognition, in particular to an image object recognition method based on SURF (Speed ​​Up Robust Feature) features and a bag-of-words model. Background technique [0002] Image recognition and classification technology is an important application in the field of computer vision and pattern recognition. In machinery industry, logistics transportation, retail and other industries, accurate image object recognition technology can liberate people from heavy labor and reduce production costs. Improve work efficiency. In daily life, people can quickly and accurately grasp the characteristics of objects and recognize objects, but for computers, it is quite difficult to automatically recognize objects. The reason is that the objects in the image are affected by factors such as shooting angle, rotation change, illumination change, scale change, and shooting quality. [0003] The existing solution to these di...

AI Technical Summary

Problems solved by technology

In this patent document, the calculation of multi-scale SURF features requires a large amount of calculation, and the singular value decomposition is directly used to construct a dictionary without further processing of the features.

Images