Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder
| Autor: | Cheng Li, Ma Shiping, Zunlin Fan, Duyan Bi, Linyuan He, Shan Gao |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Artificial neural network
Computer science business.industry Cognitive Neuroscience Deep learning Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Top-hat transform 020207 software engineering Image processing Pattern recognition 02 engineering and technology Computer Science Applications Artificial Intelligence Feature (computer vision) Computer Science::Computer Vision and Pattern Recognition Digital image processing 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Feature detection (computer vision) |
| Zdroj: | Neurocomputing. 243:12-20 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2017.02.066 |
| Popis: | We use deep learning for image processing by extracting image feature.The extraction has good performance in noisy or low-light circumstance.We optimize TV and L0 smoothing filter by the proposed feature extraction.The features can extract image structure features regardless the inputs directly. In this paper, we propose a novel low-level structure feature extraction for image processing based on deep neural network, stacked sparse denoising autoencoder (SSDA). The current image processing methods via deep learning are directly building and learning the end-to-end mappings between the input/output. Instead, we advocate the analysis of the first layer learning features from input data. With the learned low-level structure features, we improve two edge-preserving filters that are key to image processing tasks such as denoising, High Dynamic Range (HDR) compression and details enhancement. Due to the validity and superiority of the proposed feature extraction, the results computed by the two improved filters do not suffer from the drawbacks including halos, edge blurring, noise amplification and over-enhancement. More importantly, we demonstrate that the features trained from natural images are not specific and can extract the structure features of infrared images. Hence, it is feasible to handle tasks by using the trained features directly. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect