Deep learning classification method based on feature screening

Abstract

The invention discloses a deep learning classification method based on feature screening. An accurate image classification model can be obtained by training and testing a data set by using the deep learning classification method based on feature screening provided by the invention. According to the method, accurate classification of the images can be efficiently completed, the number (dimensionality reduction) of the features can be reduced through a feature screening method under the conditions that serious over-fitting, redundancy, much noise and the like exist between the features and the target, and therefore the generalization ability of the model is improved to obtain higher classification accuracy. In an image classification task, data and features determine the upper limit of machine learning, and a model and an algorithm only approach the upper limit. Therefore, the feature engineering plays a very important role in machine learning. The classification of the input data can bepredicted, so that the method is widely applied to the fields of traffic scene object recognition, vehicle counting, license plate recognition and internet and biomedical image analysis in the security field and the traffic field.

Description

technical field [0001] The invention belongs to the field of computer image processing, and in particular relates to an image classification technology based on a deep convolutional neural network, a machine learning classification algorithm and a feature screening method. Background technique [0002] Computer vision is a research field that focuses on helping computers understand pictures and videos. Understanding the content of digital images includes extracting descriptions from images, which may be objects in the images, text descriptions, 3D models, etc. At an abstract level, the goal of computer vision is to use observed image data to infer things about the world. It is a multidisciplinary field that includes computer science (graphics, algorithms, theory, systems, architecture), mathematics (information retrieval, machine learning), engineering (robotics, speech, natural language processing, image processing), physics ( Optics), biology (neuroscience), and psycholog...

AI Technical Summary

Problems solved by technology

However, one of the most important shortcomings of vision tasks is that the requirements for image quality are relatively strict.

The image information acquired by vision technology has a lot of noise, which brings great challenges to the accuracy of classification algorithms

Images