An efficient approach for image sequence denoising using Zernike moments-based nonlocal means approach☆
Introduction
Image sequence denoising is an important image processing task which has wide applications in several areas such as video films, infrared imaging, X-ray imaging, ultra-sound, and confocal microscopy. Restoration of old films and videos is an important area where image sequence denoising finds an important role because of the degradation of such videos over a period of time. The image sequence denoising is a difficult task because it involves estimation of motion while performing denoising. What makes the motion estimation difficult is the movement of the local objects in a scene. Therefore, the task of the denoising process not only involves the treatment of the problem in the spatial domain but also in the temporal domain. This complexity of the problem has kept the area active and more and more researches are being carried out in this area as ever before.
Many methods have been suggested for video sequence denoising. Broadly they are divided into two classes: methods with explicit motion estimation and methods without explicit motion estimation (motion is estimated implicitly). An initial survey of image sequence denoising can be found in [1]. The survey reports that the motion compensation task enhances the performance of both spatiotemporal and temporal filters from their non-motion compensated counterparts. Also, the performance of spatiotemporal filters is reported to be better than that of temporal filters. Later, a Weiner filter based approach for denoising of image sequences using 2D parametric motion model for explicit motion estimation in a spatiotemporal filtering scheme was proposed in [2]. Another spatiotemporal filtering approach has been proposed [3] in which spatial filtering is performed by the combination of wavelet and 2D Weiner filter while for temporal filtering bi-directional block based motion compensation using enhanced predictive zonal search (EPZS) algorithm is used. In contrast to above mentioned approaches, other approaches that do not rely on explicit motion estimation can also be found in the literature. For instance, a video denoising approach has been developed in [4] which is based on 3D anisotropic diffusion equation for noise removal and deblurring of video sequences. The proposed approach has extended the 2D diffusion equations to three dimensions to derive benefit from high degree of spatial and temporal correlation between the frames and thus it is capable of suppressing the flickering effect. Also, transform domain approaches based on DCT-based filtering [5] and wavelet-based filtering [6], [7] have been extended and applied to image sequence denoising in spatiotemporal domain. Among the methods without explicit motion estimation, one of the most effective and simple approach is based on the nonlocal means (NLM) filter developed by Buades et al. [8]. This approach has been extended to image sequence denoising [9] and video-denoising [10].
In the NLM approach, denoising is achieved by replacing every pixel by a weighted sum of its neighborhood pixels. The weights are obtained after computing a similarity parameter between the block centered on the pixel being averaged and the blocks centered on the neighborhood pixels being considered for the averaging process. The weights are considered to be proportional to the probability that a pixel might have moved from its current location on an image in the sequence being denoised to the location in its neighborhood. The effectiveness of this approach has been demonstrated by Buades et al. [9], [10] and Boulanger et al. [11].
The performance of NLM-based image sequence denoising is quite satisfactory, especially on smooth areas and repetitive textures for which the redundancy is high. On singular structures where the redundancy is low, the algorithm provides poor results because it fails to detect enough similar structures [12], [13]. The presence of high noise might affect similarity between two patches because of false patch detection. The similarity measure used for neighborhood blocks in the NLM-based method is simply a Euclidean distance of pixel values between two blocks which suffers from image noise. Two visually similar blocks but affected by noise may not always yield smaller distance as compared to two slightly dissimilar blocks. Moreover, the local motion in image sequence may cause rotation of objects or a slight change in the scene. Under these situations, the NLM-based block matching and denoising process does not work well. The use of block matching under rotation for single image denoising has been analyzed by Grewenig et al. [14] where the authors have used two approaches for this purpose. The first approach uses invariant geometric moments and the second approach is based on the estimation of the rotation angle and realigning the blocks. Improvements in the quality of denoising results have been reported by these authors. Also, an adaptive regularized NLM method has been proposed in [12], [13] which combines the NLM approach with total variation (TV) minimization problem in order to reduce the over-smoothing problem of NLM approach due to a combination of multiple irrelevant candidate patches. The authors have conducted experiments on both single images as well as image sequences and have shown improved quality of denoised images/image sequences obtained with their proposed regularized-NLM method. Another major drawback of the NLM method is its high computation time. The major components contributing towards the time requirements are the process of block matching and computation of weights. Mahmoudi and Sapiro [15] have attempted to reduce the time requirements by discarding those blocks which are dissimilar using average gray values of blocks and average gradient direction and magnitude. However, it affects the denoising performance.
In this paper, we propose nonlocal means and Zernike moments (ZMs)-based image sequence denoising approach, called the NLM–ZMs, which has several advantages over the NLM-based approaches. Being orthogonal and rotation invariant, ZMs possess several useful characteristics for image description over patch-based block matching used in the NLM-based approach. The ZMs encode the singular structures in a better way as the first, second and third order ZMs can effectively encode the edges and rapid change in intensity [16]. The ZMs possess minimum information redundancy and, therefore, a few low frequency components can be used to describe an image. This facilitates the process of block matching used in NLM-based approaches. The magnitudes of ZMs are rotation invariant and hence rotation of objects in a scene can be handled effectively by ZMs. This is particularly useful for the estimation of local motion of small objects which may undergo rotation. The moments are derived using a summation process, as a consequence, the effect of noise is reduced in the block matching process. We use a small number of ZMs coefficients as compared to the large number of pixel values in the NLM-based block matching approach. This step significantly reduces the time taken for block matching and weight computation which is one of the major issues in the NLM-based image sequence denoising approaches. Another key feature of the proposed approach is the enhancement of the denoising performance which is achieved by smoothing of weights. Unlike the NLM-based approach which considers the spatial distance of pixels within a patch (intra-patch distance) for smoothing the photometric distance, we smooth weights depending on the spatial distance between a reference patch and the target patch (inter-patch distance). Thus, we improve the performance of NLM–ZMs image sequence denoising approach by incorporating the concept of geometric distance between two image blocks being matched. It is also shown that as the noise level increases, the proposed method performs much better than the NLM-based approaches because ZMs-based block matching is robust to image noise.
It is worth mentioning here that the ZMs-based NLM approach has been applied to image denoising [17] and image super-resolution [18]. In [17], the authors have normalized ZMs which sometimes become unstable due to the normalization process as explained in Section 4.3. Moreover, their approach does not take into account the geometric distance between two image blocks which greatly enhances the denoising performance. In [18], the authors have used ZMs in image super-resolution, again without the use of geometric distance being taken into consideration. Moreover, the proposed method is applied to image sequence denoising, whereas the method in [17] deals single image denoising and the method in [18] deals with image super-resolution.
The rest of the paper is organized as follows. An overview of the NLM-based image sequence denoising is described in Section 2. The proposed NLM–ZMs-based image sequence denoising is presented in Section 3. Detailed experimental results on denoising performance and time complexity analysis are demonstrated in Section 4, followed by conclusion in Section 5.
Section snippets
NLM-based image sequence denoising
The NLM-based image sequence denoising is described in [10]. Let and be the noise-free and noisy image sequences each having T number of frames. Let, ut(i) and vt(i) denote the noise-free and noisy signals at pixel i from an image frame at time t in the sequence affected by Gaussian noise signal ηt(i) with mean zero and variance σ. The relationship between the noisy and noise-free signals is given aswhere denotes an image in a sequence of T images.
Zernike moments
The Zernike moments of order p and repetition q of an image function f(x, y) over a unit disk are defined by [19] where are the complex conjugate of the Zernike polynomials Vpq(x, y) defined by
The radial functions Rpq(x, y) are defined by
The angle θ is obtained by .
Since the image function is discrete and finding an analytical solution to
Experimental analysis
Both the NLM and NLM–ZMs image sequence denoising approaches have been implemented in Visual C++ 6.0 under Microsoft Windows environment on a PC with 2.13 GHz CPU and 3 GB RAM. We consider eight image sequences: three image sequences Miss America, Suzie, and Foreman downloaded from [22] and the other five sequences Akiyo, Hall Monitor, Highway, Salesman, and Ship Container downloaded from [23]. The first three image sequences have a spatial and temporal resolution of , , and
Conclusion
The proposed NLM–ZMs-based image sequence denoising approach is observed to be much more effective than the existing NLM-based approaches both in its denoising performance and computation time. The detailed experiments conducted on eight different image sequences corrupted with additive white Gaussian noise with standard deviation 10, 15, and 20, provide improvements in denoising performance with a minimum value of 0.39 dB (1.19%) to a maximum of 4.54 dB (14.84%) on a set of eight image sequences
Acknowledgements
The comments and suggestions provided by the anonymous reviewer to raise the standard of the paper are highly appreciated. One of the authors (Ashutosh Aggarwal) is thankful to the University Grants Commission (UGC), Govt. of India, for providing fellowship under Special Assistance Programme (SAP) of UGC Vide file no.: F.4-16/2015/DRS-III (SAP-II).
Chandan Singh received Ph.D. degree in Mathematics from Indian Institute of Technology, Kanpur, India, in 1982. Currently, He is serving as Professor in the Department of Computer Science, Punjabi University, Patiala, India. His areas of research are pattern recognition, noise removal, and image super-resolution. He has published 72 papers in international journals and 44 papers in national and international conferences.
References (27)
- et al.
Rotationally invariant similarity measures for nonlocal image denoising
J Vis Commun Image Represent
(2011) - et al.
A moment-based nonlocal-means algorithm for image denoising
Inform Process Lett
(2009) - et al.
Accurate calculation of Zernike moments
Inform Sci
(2013) - et al.
Fast and numerically stable methods for the computation of Zernike moments
Pattern Recogn
(2010) - et al.
Algorithms for fast computation of Zernike moments and their numerical stability
Image Vis Comput
(2011) - et al.
Noise reduction filters for dynamic image sequences: a review
Proc IEEE
(1995) - Dekeyser F, Bouthemy P, Pérez P. Spatio-temporal wiener filtering of image sequences using a parametric motion model....
- Cheong H-Y, Tourapis A, Llach J, Boyce J. Adaptive spatio-temporal filtering for video-denoising. In: Proceedings of...
- Lee SH, Kang MG. Spatio-temporal video filtering algorithm based on 3-D anisotropic diffusion equation. In: Proceedings...
- Rusanovskyy D, Egiazarian K. Video denoising algorithm in sliding 3D DCT domain. In: Proceedings of seventh advanced...
Cited by (5)
A local Zernike moment-based unbiased nonlocal means fuzzy C-Means algorithm for segmentation of brain magnetic resonance images
2019, Expert Systems with ApplicationsCitation Excerpt :Further, the orthogonality property of ZMs makes it suitable as image descriptors because the ZMs possess minimum information redundancy and a few low order moments are sufficient to represent an image. Therefore, the Zernike moment-based nonlocal means approach (ZM-NLM) (Ji, Chen, Sun, & Xia, 2009; Singh & Aggarwal, 2015), in which the ZMs are computed within a block around each pixel of the input image to compute the similarity between image blocks, has been found to be more effective in removing Gaussian noise than the NLM method. The approach not only retains the advantages of the NLM but also provides better similarity for singular regions (edges and fine structural objects).
Detection of Fruits Image Applying Decision Tree Classifier Techniques
2023, Lecture Notes on Data Engineering and Communications TechnologiesA comparative study of orthogonal moments for micro-Doppler classification
2018, European Signal Processing ConferenceAdaptive methods for video denoising based on the ICI, FICI, and RICI algorithms
2018, Tehnicki Vjesnik
Chandan Singh received Ph.D. degree in Mathematics from Indian Institute of Technology, Kanpur, India, in 1982. Currently, He is serving as Professor in the Department of Computer Science, Punjabi University, Patiala, India. His areas of research are pattern recognition, noise removal, and image super-resolution. He has published 72 papers in international journals and 44 papers in national and international conferences.
Ashutosh Aggarwal received B.Tech. degree from Guru Nanak Dev University, Amritsar, India, and M.Tech. degree from B.R. Ambedkar National Institute of Technology, Jalandhar, India in 2010 and 2012, respectively. He is currently pursuing Ph.D. degree in Computer Science from Punjabi University, Patiala, India. His research interests include pattern recognition, image and video interpolation, and super-resolution.
- ☆
Reviews processed and recommended for publication to the Editor-in-Chief by Area Editor Dr. E. Cabal-Yepez.