Image identification method for two-dimensional probability linear-discriminant analysis based on L1 norm

Abstract

The invention discloses an image identification method for two-dimensional probability linear-discriminant analysis based on L1 norm. The method is used for handling the situation when dimensionalityof two-dimensional data is reduced and there are exceptional values in images, and denoted as L1-2DPLDA. The method specifically includes the steps of creating an L1-norm model on original image data;utilizing an EM algorithm to figure out a solution to the model to obtain a projection matrix; utilizing the projection matrix to classify unknown images. Compared with traditional vector data, the method is different in that dimensionality can be reduced in the line and column directions of the two-dimension data, the spatial features of the images can be maintained, and meanwhile, under the situation when there are exceptional values in the original data, the method has robustness, and an image identification rate with higher accuracy is obtained.

Description

technical field [0001] The invention relates to an image recognition method based on L1 norm-based two-dimensional probability linear discriminant analysis, which is used for image feature extraction and data dimensionality reduction, and is especially suitable for the situation with occluded blocks in the image. Background technique [0002] High-dimensional data is ubiquitous in machine learning. High-dimensional data not only increases the overhead of storage in the computer, but also increases the complexity of the algorithm. Since high-dimensional data can generally be represented by low-dimensional data, a key issue in the study of high-dimensional data is to find a mapping relationship to project high-dimensional data into low-dimensional space. In the past two or three decades, algorithms for data dimensionality reduction have made great progress. [0003] Linear discriminant analysis (LDA) is widely used for data dimensionality reduction and pattern recognition. ...

AI Technical Summary

Problems solved by technology

At the same time, another shortcoming of LDA is that the noise in reality is very complex. When there are occluded blocks in the image, the Gaussian noise is insufficient to describe the problem. The quadratic term of the Gaussian distribution will infinitely magnify the outliers in the image.

Images