Image noise types recognition using convolutional neural network with principal components analysis

• Published in: IET image processing Vol. 11; no. 12; pp. 1238 - 1245
• Main Authors: Khaw, Hui Ying, Soon, Foo Chong, Chuah, Joon Huang, Chow, Chee-Onn
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.12.2017
• Subjects: adaptive filters; backpropagation; backpropagation algorithm; channel bank filters; CNN method; computational cost reduction; convolutional neural network; data adaptive filter banks; data complexity; Gaussian noise; gradient methods; human‐eye performance; image classification; image filtering; image noise type classification; image noise types recognition model; impulse noise; intelligent system; PCA filter generating strategy; Poisson noise; principal component analysis; principal components analysis; Research Article; speckle; stochastic gradient descent optimisation techniques; stochastic programming; training time reduction; speckle; image classification; stochastic gradient descent optimisation techniques; stochastic programming; image filtering; Poisson noise; principal components analysis; Gaussian noise; impulse noise; image noise types recognition model; computational cost reduction; gradient methods; channel bank filters; adaptive filters; backpropagation algorithm; CNN method; data adaptive filter banks; convolutional neural network; PCA filter generating strategy; image noise type classification; backpropagation; data complexity; intelligent system; training time reduction; human-eye performance; principal component analysis
• ISSN: 1751-9659; 1751-9667
• DOI: 10.1049/iet-ipr.2017.0374

This study presents a model to effectively recognise image noise of different types and levels: impulse, Gaussian, Speckle and Poisson noise, and a mixture of multiple types of the noise. To classify image noise type, the convolutional neural network (CNN) method with backpropagation algorithm and stochastic gradient descent optimisation techniques are implemented. In order to reduce the training time and computational cost of the algorithm, the principal components analysis (PCA) filters generating strategy is deployed to obtain data adaptive filter banks. The authors validated their designed CNN with PCA for noise types recognition model with degraded images containing noise of single and combination of multiple types, with a total of 11,000 and 1650 datasets for training and testing purposes, respectively. The variety and complexity of data have never been addressed before in any other research work. The capability of their intelligent system in handling images degraded under this complicated environment has surpassed human-eye performance in noise types recognition. The authors’ experiments have proven the reliability of the proposed noise types recognition model by having achieved an overall average accuracy of 99.3% while recognising eight classes of noise.