Self-learning based image decomposition for blind periodic noise estimation: a dual-domain optimization approach
- PDF / 2,289,250 Bytes
- 26 Pages / 439.37 x 666.142 pts Page_size
- 67 Downloads / 169 Views
Self-learning based image decomposition for blind periodic noise estimation: a dual-domain optimization approach Najmeh Alibabaie1 · Ali Mohammad Latif1 Received: 10 December 2019 / Revised: 16 May 2020 / Accepted: 26 July 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Periodic noise reduction is a fundamental problem in image processing, which severely affects the visual quality and subsequent application of the data. Most of the conventional approaches are only dedicated to either the frequency or spatial domain. In this research, we propose a dual-domain approach by converting the periodic noise reduction task into an image decomposition problem. We introduced a bio-inspired computational model to separate the original image from the noise pattern without having any a priori knowledge about its structure or statistics. From the filtering perspective, the proposed method filters out only a portion of the noisy frequencies. Some considerations have to be taken into account for computational resources (computing time and memory space) which permits reducing computation complexity without sacrificing the quality of the image reconstruction. In addition, the separator size provided in the decomposition algorithm does not depend on the image size. Experiments on both synthetic and non-synthetic noisy images have been carried out to validate the effectiveness and efficiency of the proposed algorithm. The simulation results demonstrate the effectiveness of the proposed method both qualitatively and quantitatively. Keywords Image noise removal · Periodic noise · Blind source separation · Spectrogram · Genetic algorithm
1 Introduction A digital image is created in digital image acquisition from a physical scene. In this process, any random variation of pixel value or color is known as image noise (Gonzalez and Woods 2007). Periodic noise is one type of image noise. It is generated by electrical or magnetic interference (Varghese 2016). This noise can be seen in some visual applications such as medicine (Carvalho et al. 2018), traffic control (Ata et al. 2019), remote sensing (Chen et al.
B
Ali Mohammad Latif [email protected] Najmeh Alibabaie [email protected]
1
Computer Engineering Department, Yazd University, Yazd, Iran
123
Multidimensional Systems and Signal Processing
2017; Sur 2015), television (Smith 2012), and real-time applications. Due to its frequent occurrence, periodic noise removal is one of the important issues in image processing. In the spatial domain, periodic noise appears as a repetitive pattern on the image and degrades the image quality. Periodic noise not only sharply degrades the image quality in the visual effect but also risks its suitability for subsequent processing, e.g., image un-mixing and classification. So, periodic noise must be removed and image quality must be improved before the subsequent interpretation. Figure 1 shows the periodic noise in the spatial and frequency domain. Periodic noise for an image of size M × N is spatially mod
Data Loading...
