Abstract
With the rapid development of computer vision and artificial intelligence, people are increasingly demanding image decomposition. Many of the current methods do not decompose images well. In order to find the decomposition method with high accuracy and accurate recognition rate, this study combines convolutional neural network and probability map model, and proposes a single-image intrinsic image decomposition method that is on both standard dataset images and natural images. Compared with the existing single-image automatic decomposition algorithm, the visual effect comparable to the user interaction decomposition algorithm is obtained, and the method of this study also obtains the lowest error rate in the quantitative comparison on the standard dataset image. The multi-image collaborative intrinsic image decomposition method proposed in this study obtains the decomposition result of consistent foreground reflectivity on multiple sets of image pairs. In this study, the eigenimage decomposition is applied to the illumination uniformity in the small change detection, and the promising reflectivity layer image obtained by the decomposition helps to improve the accuracy of the cooperative saliency detection. This study proposes an algorithm for the cooperation between CNN and probability graph model, and introduces how to combine the probability graph model with the traditional CNN to accomplish the pixel-level eigendecomposition task. This study also designs a single-image and multi-image intrinsic image decomposition results analysis experiments, then analyzes the probabilistic graphical model coordination intrinsic image decomposition results, and finally analyzes the convolutional neural network coordination intrinsic decomposition performance to draw the conclusion of this study. The effect on the Msrc-v2 dataset was increased by 0.8% over the probability plot model.
Highlights
Research on convolutional neural networks began in the 1980s and 1990s, and time delay networks and LeNet-5 were the first convolutional neural networks
In order to find an intrinsic decomposition method that combines convolutional neural network and probability map model to improve the accuracy and recognition efficiency of eigendecomposition, this study draws the following conclusions: (1) is study proposes a single-image eigenimage decomposition method based on a hierarchical structure. e hierarchical structure improves the efficiency of decomposition, and makes the algorithm not rely too much on chrominance features
Based on the constraints on the reflectivity layer and the illumination layer, the single-image intrinsic image decomposition method proposed in this study achieves better than the existing singleimage auto-decomposition algorithm on both the standard dataset image and the natural image. e user interaction decomposition algorithm can compare the visual effects, and in the quantitative comparison on the standard dataset image, the method of this study obtains the lowest error rate
Summary
Research on convolutional neural networks began in the 1980s and 1990s, and time delay networks and LeNet-5 were the first convolutional neural networks. E intrinsic image decomposition problem was proposed by Barrow and Tenenbaum in 1978. Ese essential features include the reflectivity of the surface of the object in the scene, and the object’s process of restoring these features from the input image, such as geometry, scene depth information, direction, and color of incident illumination, is called the intrinsic image decomposition problem. The image forming model commonly used in the intrinsic image decomposition method is I R × S, where R represents the reflectance layer image of the object, reflecting the reflection ability of the surface of the object to the illumination, and S represents the illumination layer image (shading). Is model is the result of the interaction between the geometry of the object and the lighting, and × means multiplication by pixel The image forming model commonly used in the intrinsic image decomposition method is I R × S, where R represents the reflectance layer image of the object, reflecting the reflection ability of the surface of the object to the illumination, and S represents the illumination layer image (shading). is model is the result of the interaction between the geometry of the object and the lighting, and × means multiplication by pixel.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
