Conventional neural network for blind image blur correction using latent semantics
- PDF / 1,323,790 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 108 Downloads / 160 Views
(0123456789().,-volV) (0123456789().,-volV)
METHODOLOGIES AND APPLICATION
Conventional neural network for blind image blur correction using latent semantics S. Gowthami1 • R. Harikumar2
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In this work, deep learning for enhancing the sharpness of blurred image is investigated. Initial pre-processing is blur image kernel estimation which is critical for blind image de-blurring. In prior investigation, handcrafted blur features are optimized for certain uniform blur, which is unrealistic for blind de-convolution. To deal with this crisis, initially this work attempts to carry out kernel matrix estimation using latent semantic analysis (KME-LSA) in dermatology image. In order to enhance the image sparseness, this work modelled an image descriptor based on Gaussian mixture model in autoencoder (GMM-AE) as a primary layer in convolutional neural networks. The functionality of the proposed GMM-AE triggers the selection of efficient features for subsequent layers in CNN. The features extracted from the integrated trained GMM-AE in CNN can fine-tune the quality of blurred image. Datasets used are melanoma-based dermascope images. Preprocessing procedures are carried out by LSA-based kernel matrix estimation. The attained sharp image outcome is given to the proposed model for effective feature extraction and to attain improved blind image. The anticipated KME-LSA and GMM-AE in CNN estimates blur parameters with high accuracy. Experiment illustrates the efficacy of proposed method and the competitive outcomes are compared with state-of-the-art datasets. Simulation was carried out in MATLAB environment; performance metrics like MSE—227.6, PSNR—33.6762, SSIM—0.9755 and VIF—0.08162 are evaluated. The results show better trade-off than the prevailing techniques. Keywords Blur kernel estimation Blind image de-blurring Gaussian mixture model Convolutional neural network Auto-encoder
1 Introduction Image blur is the chief cause of image degradation, and deblurring turns to be a popular research topic in image processing field. There are various causes of image blur, such as de-focus blur, Gaussian blur and motion blur (Chrysos and Zafeiriou 2019). The blurred image
Communicated by V. Loia. & S. Gowthami [email protected] R. Harikumar [email protected] 1
Department of Biomedical Engineering, Dr.NGP Institute of Technology, Coimbatore, India
2
Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam, India
restoration, i.e. image de-blurring is the procedure of deducing latent sharp images with insufficient information of degradation model. There exist diverse techniques to evaluate this crisis. De-blurring approaches are categorized into non-blind and blind image. In case of blind de-blurring, blur operator is unknown, while in non-blind, deblurring prior knowledge of blur kernel and associated parameters are needed. In real-time applications, single blurred image usually h
Data Loading...
