Image enhancement method based on convolutional auto-encoder
A convolutional self-encoding and image enhancement technology, which is applied in the field of image enhancement based on convolutional self-encoders, can solve the problems of reducing data preprocessing time, etc., and achieve the effects of improving efficiency, good image enhancement effect, and reducing costs
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0026] With reference to accompanying drawing, further illustrate technical scheme of the present invention:
[0027] An image enhancement method based on a convolutional self-encoder, comprising the following steps:
[0028] 1) Process the original image into a low-light image, and add Gaussian noise, salt and pepper noise, Poisson noise and speckle noise to the training of network brightening and denoising when the image is preprocessed into a low-light image;
[0029] 2) The convolution operation is used as the encoding operation of the self-encoder to obtain the low-dimensional feature representation of the low-light image. When the network is trained, the processed low-light image is input, and then encoded by the convolutional network to obtain a compressed feature map. At this time, the network learns the hidden features of low-light images and performs pooling operations;
[0030] 3) Perform deconvolution operation on the obtained compressed feature map, and decode to...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com