Digital-vein feature extraction method based on nonnegative-matrix factorization

Abstract

The invention belongs to the technical field of digital image processing and mode identification and specifically relates to a digital-vein feature extraction method based on a nonnegative-matrix factorization theory. The method includes: extracting a region of interest (ROI) from a digital-vein panel pool; performing image matrix column vectorization on the ROI and obtaining a digital-vein data set; training the digital-vein data set and obtaining a feature matrix and a factor matrix; and extracting a test-sample RIO and performing column vectorization on the test-sample ROI which is then changed into a test-sample vector and projecting on the feature matrix so that an obtained projecting factor is a to-be-identified feature. The digital-vein feature extraction method based on the nonnegative-matrix factorization theory applies the nonnegative-matrix factorization theory which is more aligned with cognition and has more physical significance to a digital-vein image feature extraction task and further studies and promotes the sparseness of the digital-vein feature based images.

Description

Technical field [0001] The invention belongs to the technical field of digital image processing and pattern recognition, and specifically relates to a method for extracting finger vein image features based on non-negative matrix factorization theory. Background technique [0002] For image processing tasks, in most cases, classification and recognition cannot be performed directly in the measurement space of the image data itself. This is because most of the image information has a high dimensionality, or the number of images to be processed is huge, which is not suitable for the design of classifiers and recognition methods. More importantly, such a description does not directly reflect the nature of the measurement object. , And it changes with the changes of the illumination brightness, shooting angle and positional energy factors. Therefore, in order to design the classifier and recognition method, it is necessary to transform the image from the measurement space to the featu...

AI Technical Summary

Problems solved by technology

However, the pixels in these method theories can be positive or negative, and there may be a subtraction relationship in the linear combination of feature bases, which lacks the effect of synthesizing the whole from parts in an intuitive sense, and for image matrices, negative values The existence of the decomposition results lacks explainable and clear physical meaning, and loses connection with practical problems

Images