ENG Transactions

Journal homepage: http://www.engtransactions.com

ENG Transactions, vol. 1, pp. 1-5, November 2020

ID: ENGT-2020116243677123

Letter

Filtering in Image Processing

Mirpouya Mirmozaffaria
Department of Industrial Manufacturing and Systems Engineering, The University of Texas at Arlington, Arlington, USA

Keywords Abstract

Filtering, Filtering can be used in various engineering and scientific problems such as signal
Signal processing, processing, image processing/analysis, electronic, physics electronic, chemistry and etc. In
Image processing, image processing and analysis, filters are used for de-blurring and smoothing. In addition,
De-blurring, with the help of the filters some facts which are clear in the original image will be blurred
Bilateral filter. and the final image will be enhanced. With considering the best sigma value for bilateral
filter, after comparing all these four filters we will find out that the bilateral filter is the best.

1. Introduction

Most of the images are influenced by some kind of unwanted noises causing disturbance in image quality and resolution. ,
Analyzing the images are usually processed right after removing these noises from the images. Filtering has various meanings
and applications in most of the engineering and scientific problems. It provides researchers with fine results comparing with
other available methods. Researchers in image/signal processing, electrical and electronic, mechanical engineering, chemistry
and physics are utilizing filtering in their problems. One of the most common applications of filtering is in image processing to
give a better resolution or to emphasize the edges properly.

2. Filtering

Box filter, Gaussian filter and bilateral filters are kind of well-known filters used in image processing. As we know all these
filters are used for de-blurring and smoothing. In addition, with the help of these filters some facts which are clear in the original
image will be blurred and the final image will be enhanced. With considering the best sigma value for bilateral filter, after
comparing all these four filters we will find out that the bilateral filter is the best.
As conserving the edge is needed, we want our image to be blurred and smoothed, so bilateral filtering is very useful in such
a case [1][2]. This filter has various applications in engineering and science [3-9]. In this technique, colors and gray levels are
joined and close values are more preferred than the far or distant ones. The main aim of the cited method is removing phantom
colors in the original image which may be appeared in the edges.

Corresponding Author: Mirpouya Mirmozaffari

E-mail address: [email protected]
Received: 27 September 2020; Revised: 16 October 2020; Accepted: 18 October 2020

Please cite this article as: M. Mirmozaffaria, “Filtering in Image Processing,” ENG Transactions, vol. 1, pp. 1–5, 2020.
 Mirmozaffari, ENG Trans., vol. 1, pp. 1-5, November 2020

Bilateral filtering is kind of de-noising methods which can preserve sharp edges and remove some colors across the edges.
This filter because of weighted mean of neighborhood pixels are easy to understand. In addition, there is a distance between
pixel values, so it can be adopted properly. Last but not least, this filter is non-iterative which is very simple.

3. Results and Discussion

Sigma value=0.08 gives the best result for bilateral filter in comparison with others. It means that by increasing the amount
of sigma, the image will be improved and de-blurred. For examples, in a test image, there may be some wrinkles in the face, so
with the help of bilateral filter with sigma value 0.08 most of the wrinkles in the face will be removed and at the end, we will get
a face which looks younger.
Such a filter is very hard to be analyzed because it is nonlinear. It is slow but it has got some accelerations as well. The
approximation is so fast in this method because of its nonlinear nature. It cannot be used for sharpening, it can just blur the
image to reduce the disturbing noise. Figure 1 shows the filtering results of box and Gaussian filter. Figure 2 demonstrate the
results of bilateral filtering for different sigma values.

Original Image

Box Filter Gaussian Filter

Figure 1. Filtering results of box and Gaussian filters.

2
 Mirmozaffari, ENG Trans., vol. 1, pp. 1-5, November 2020

Input Image

100 100

200 200

300 300

400 400

500 500

100 200 300 400 100 200 300 400

a, sigma=0.02

Input Image

100 100

200 200

300 300

400 400

500 500

100 200 300 400 100 200 300 400

b, sigma=0.05

3
 Mirmozaffari, ENG Trans., vol. 1, pp. 1-5, November 2020

Input Image

100 100

200 200

300 300

400 400

500 500

100 200 300 400 100 200 300 400

c, sigma=0.08

Figure 2. Bilateral filtering for various sigma values.

4. Conclusion

In this paper various filtering approaches are utilized to address the issue of image recovery from its noisy counterpart. The
image filtering algorithm provides us with smoothness and better resolution from the noisy version.

Experiments are conducted that bilatereal filtering performs better than other filtering techniques which are available in the
literature. For the future work, we will deall with applying some optimization algorithms and machine learning approaches [10-
25] to check and compare the performance analysis of different methods.

Conflict of Interest Statement

The author declares no conflict of interest.

References

[1] V. Aurich, J. Weule. “Non-linear gaussian filters performing edge preserving diffusion,” in proc. DAGM Symposium, 1995.
[2] S. M. Smith and J. M. Brady. “SUSAN – a new approach to low level image processing,” International Journal of Computer Vision, vol.
23, no. 1, pp. 45–78, May 1997.
[3] E. P. Bennett and L. McMillan, “Video enhancement using per-pixel virtual exposures,” ACM Transactions on Graphics, vol. 24, no. 3,
pp.845 – 852, July 2005.
[4] C. Liu, W. T. Freeman, R. Szeliski, and S. Kang, “Noise estimation from a single image,” in proc. Computer Vision and Pattern
Recognition, 2006.
[5] G. Petschnigg, M. Agrawala, H. Hoppe, R. Szeliski, M. Cohen, and K. Toyama, “Digital photography with flash and no-flash image
pairs,” ACM Transactions on Graphics, vol. 23, no. 3, July 2004.
[6] N. Sochen, R. Kimmel, and A. M. Bruckstein, “Diffusions and confusions in signal and image processing,” Journal of Mathematical
Imaging and Vision, vol. 14, no. 3, pp. 237–244, 2001.
[7] N. Sochen, R. Kimmel, and R. Malladi, “A general framework for low level vision,” IEEE Transactions on Image Processing, vol. 7, pp.
310–318, 1998.

4
 Mirmozaffari, ENG Trans., vol. 1, pp. 1-5, November 2020

[8] D. Barash, “A fundamental relationship between bilateral filtering, adaptive smoothing and the nonlinear diffusion equation,” IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 6, pp. 844, 2002.
[9] S. Bae, S. Paris, F. Durand, “Two-scale tone management for photographic look,” ACM Transactions on Graphics, vol. 25, no. 3, pp. 637
– 645, 2006.
[10] M. Mirmozaffari et al., “Data Mining Apriori Algorithmfor Heart Disease Prediction,” Int'l Journal of Computing, Communications &
Instrumentation Engg. (IJCCIE), vol. 4, no. 1, pp. 20-23, 2017.
[11] M. Mirmozaffari et al., “Heart disease prediction with data mining clustering algorithms,” Int'l Journal of Computing, Communications
& Instrumentation Engg. (IJCCIE), vol. 4, no. 1, pp. 16-19, 2017.
[12] N. A. Golilarz, N. Robert, J. Addeh, “Survey of image de-noising using wavelet transform combined with thresholding functions,”
Computational Research Progress in Applied Science & Engineering, vol. 3, no. 4, pp. 132–135, 2017.
[13] M.Mirmozaffari, A. Alinezhad, “Window Analysis Using Two-stage DEA in Heart Hospitals,” in proc. 10th International Conference
on Innovations in Science, Engineering, Computers and Technology (ISECT), Dubai, United Arab Emirates, Oct 2017, pp.44-51.
[14] N. A. Golilarz et al., “Optimized wavelet-based satellite image de-noising with multi-population differential evolution-assisted harris
hawks optimization algorithm,” IEEE Access, vol. 8, pp. 133076-133085, 2020.
[15] M. Mirmozaffari et al., “A Novel Improved Data Envelopment Analysis Model Based on SBM and FDH Models,” European Journal of
Electrical Engineering and Computer Science, vol. 4, no. 3, pp. 1-7, 2020.
[16] M. Mirmozaffari et al., “A Novel Machine Learning Approach Combined with Optimization Models for Eco-efficiency Evaluation,”
Applied Sciences, vol. 10, no. 15, pp. 5210, 2020.
[17] N. A. Golilarz, H. Demirel, and H. Gao, “Adaptive generalized Gaussian distribution oriented thresholding function for image de-noising,”
International Journal of Advanced Computer Science and Applications, vol. 10, no. 2, pp. 10-15, 2019.
[18] A. Addeh, A. Khormali, N. A. Golilarz, “Control chart pattern recognition using RBF neural network with new training algorithm and
pracrical features,” ISA Transactions, vol 79, pp. 202–216, 2018.

[19] N. A. Golilarz, A. Addeh, H. Gao, L. Ali, A. M. Roshandeh, H. M. Munir, R. Khan, “A new automatic method for control chart patterns
recognition based on ConvNet and harris hawks meta heuristic optimization algorithm, ” IEEE Access, vol. 7, pp. 149398–149405, 2019.

[20] A. Addeh et al., “Control chart pattern recognition using RBF neural network with new training algorithm and pracrical features,” ISA
Transactions, vol 79, pp. 202–216, 2018.
[21] M. Yazdani et al., “improving Construction and Demolition Waste Collection Service in an Urban Area Using a Simheuristic Approach:
A Case Study in Sydney, Australia,” Journal of Cleaner Production, 124138, 2020.
[22] M. Mirmozaffari, A. Alinezhad, “Ranking of Heart Hospitals Using cross-efficiency and two-stage DEA,” in proc. 7th International
Conference on Computer and Knowledge Engineering (ICCKE), Mashhad, Iran, 2017, pp. 217.
[23] M. Mirmozaffari, “Presenting an expert system for early diagnosis of gastrointestinal diseases,” International Journal of Gastroenterology
Sciences, vol. 1, no. 1, pp. 21-27, 2020.
[24] L. Ali, S. Khan, N. A. Golilarz, Y. Imrana, I. Qasim, A. Noor, R. Nour, “A Feature-Driven Decision Support System for Heart Failure
Prediction Based on χ 2 Statistical Model and Gaussian Naive Bayes,” Computational and Mathematical Methods in Medicine, pp. 1–8,
2019.

[25] R. Khan, X. Zhang, R. Kumar, A. Sharif, N. A. Golilarz, M. Alazab, “An Adaptive Multi-Layer Botnet Detection Technique Using
Machine Learning Classifiers, ”Applied Sciences, vol. 9, 2019.

View publication stats