A method for image super-resolution based on SAE and sparse representation

Abstract

The invention discloses an image super-resolution method based on SAE and sparse representation, belonging to the field of image processing. This method mainly includes two stages of offline training and test reconstruction. The former mainly conducts dictionary training on the image features extracted by the sparse self-encoding SAE model, and establishes dictionary pairs reflecting the corresponding relationship between high and low resolution image features. The latter uses the obtained Dictionary and sparse representation methods perform super-resolution reconstruction on user-input low-resolution images. This method uses the SAE model to perform unsupervised learning training on the original image sampling data, which avoids the time-consuming and labor-intensive disadvantages of traditional manual design of feature extraction operators and the disadvantages of single feature extraction. Training is conducive to dictionary training, and the use of sparse representation methods can estimate the lost detail components in the image, which is convenient for recovering higher-quality high-resolution images from low-resolution images.

Description

technical field [0001] The invention belongs to the field of image processing and relates to an image super-resolution method based on SAE and sparse representation. Background technique [0002] With the development of science and technology and the continuous strengthening of social security awareness, video surveillance systems are widely used in the field of public security. High-quality, high-resolution images are crucial to the realization of video surveillance system functions because they can reflect more detailed information in visual scenes and people. However, in practical applications, the generation of low-resolution images is unavoidable. On the one hand, many imaging systems (such as infrared imagers, CCDs, CMOS sensors, etc.) are limited by their inherent sensor array arrangement density and affected by factors such as target movement, poor focus, and system noise. It is difficult to achieve the desired level, with defects such as blurring, noise, and defor...

AI Technical Summary

Problems solved by technology

[0007] However, traditional sparse representation-based image super-resolution techniques mostly use artificially designed feature extraction operators (such as gradient or Laplacian operators) to extract features from images (blocks). The advantage of this method is that The extracted features can describe the structure and edge features of the image. The disadvantage is that on the one hand, the features extracted by the artificially designed feature extraction operator are fixed and single. On the other hand, this method is easy to increase the dimension of the feature space. During dictionary training, dictionary training is difficult and data overfitting tends to occur. In order to avoid this phenomenon, some data dimensionality reduction methods (such as PCA method, popular dimensionality reduction methods, etc.) are often used to reduce the dimension of the feature space. The features after dimensionality reduction are used for dictionary training. Since manual feature extraction and dimensionality reduction methods are performed independently, this method will damage the reliability of the original feature space description image to a certain extent.

Images