An eigendecomposition method based on deep learning and probabilistic graph model
- PDF / 1,365,166 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 106 Downloads / 182 Views
ORIGINAL RESEARCH
An eigendecomposition method based on deep learning and probabilistic graph model Xin Li1 · Guyu Hu1 · Zhisong Pan1 Received: 31 July 2019 / Accepted: 14 October 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract With the rapid development of computer, computer vision derived from computer vision has also made important progress in the field of image research. The extraction of image information is the most basic work in the field of image research. However, in the current environment, there is still a lack of effective methods to understand more complex image problems, such as image shape, material and illumination distribution in the environment. Eigenimage decomposition can be achieved by obtaining albedo eigenvalues and luminance eigenvalues. The color and illumination information of the image can be obtained more intuitively. Based on this, this paper proposes an intrinsic image decomposition method based on depth learning and probability graph model, in order to extract image information more accurately. Firstly, a deep convolution neural network is trained to decompose reflectivity image and shadow image. Then the conditional random field is used to optimize the reflectivity image and shadow image. The convolutional neural network designed in this paper obtains preliminary results through multi-scale architecture, deep supervision, step-by-step refinement of synthetic images and multi-stage training, which has been significantly improved compared with previous algorithms. Then the essential image and the corresponding gradient image are further optimized by conditional random field, and the eigenvalue image with richer details and clearer boundary can be obtained. Keywords Eigendecomposition method · Deep learning · Probability graph model · Convolutional neural network · Conditional random field
1 Introduction Although some progress has been made in the field of computer vision in recent years, at the current stage, we usually use the characteristics of the image itself to analyze the objects in the scene, but when the illumination information in the environment is unevenly distributed, the analysis method makes it difficult to accurately interpret the key information of the image extracted from the image. This is the case. Based on this, the research of intrinsic image decomposition has begun in the field of computer vision. It * Zhisong Pan [email protected] Xin Li [email protected] Guyu Hu [email protected] 1
Army Engineering University of PLA, Nanjing 210007, China
is hoped that through the decomposition of intrinsic images, some essential features of the scene can be obtained, and then higher-level image processing can be carried out according to the essential features of the scene. Because the color, texture and shape of image information are extracted in different light distribution environments, there are still some drawbacks in the current common image information extraction methods. The Eigen image decomposition method can decompo
Data Loading...
