Method for classifying images by performing pairwise-constraint-based online dictionary reweighting

Abstract

The invention discloses a method for classifying images by performing pairwise-constraint-based online dictionary reweighting. The method comprises the following steps of: performing bottom-layer feature extraction on all images of a training set to construct an initial visual dictionary; performing feature transform on extracted bottom-layer features by adopting sparse coding to obtain coded features; performing maximum aggregation on the coded features to obtain a feature expressed by a vector for the classification of a classifier; and performing online dictionary reweighting on the feature expressed by the vector by utilizing pairwise constraints, and transmitting the feature to the classifier for training and classification. By the pairwise constraints, a relationship between pairwise images can be effectively coded; by an online learning algorithm provided on the basis of a conservative-radical training strategy, training time is greatly shortened, and incremental updating can be realized; and the method is particularly applied to massive datasets.

Description

technical field [0001] The invention relates to the technical field of image classification in computer vision, in particular to a method for object classification based on bag-of-words model and online learning. Background technique [0002] With the rapid improvement of computer computing power, computer vision, artificial intelligence, machine perception and other fields are also developing rapidly. Image classification, as one of the basic problems in computer vision, has also been greatly developed. Image classification is the use of computers to intelligently analyze images to determine the category to which the image belongs. [0003] With the development of Internet technology and computer technology, image classification has been widely used in many fields. Content-based image retrieval can retrieve images based on image content, and quickly obtain images that are similar in appearance to the retrieved image, which is incomparable to text-based image retrieval tec...

AI Technical Summary

Problems solved by technology

[0004] Although image classification technology has been widely used in many fields, there are still many difficulties to be solved

Most of the existing applications currently work in restricted scenarios, which have strong restrictions on background, weather, lighting, posture, etc.

Images