# Design of a Gabor Filter-Based Image Denoising Hardware Model

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

#### 1.1. Related Works

#### 1.2. Contributions of This Paper

## 2. Theoretical Background of Gabor Filter

#### 2.1. Gabor Kernel Size (k Size)

#### 2.2. Orientation (θ)

#### 2.3. Central Frequency $\left({f}_{0}\right)$

#### 2.4. Gaussian Sharpness (γ and η)

## 3. Methodology

#### 3.1. Gabor Filter Based Image Denoising

#### 3.2. Gabor Filter Based Edge Detection Method

## 4. Proposed Architecture of Gabor Filter Hardware

## 5. Experimental Results and Discussions

#### 5.1. Performance Comparison and Analysis

^{3}. The PSNR value for ‘Flower’ image is 9.2483, and the MSE value is 7.7920 × 10

^{3}. The PSNR and MSE values gained for image ‘Lena’ is 11.8913 and 4.2398 × 10

^{3}; for the remaining input images, the output values are given in Table 1.

#### 5.2. Simulation Results and Comparison Analysis

Ref. | Method | Image Name | PSNR (dB) | MSE | |
---|---|---|---|---|---|

Proposed | Gabor Filter + Edge detection + Hardware Accelerator | Apple | 10.4857 | $5.8602\times {10}^{3}$ | |

Flower | 9.2483 | $7.7920\times {10}^{3}$ | |||

Lena | 11.8913 | $4.2398\times {10}^{3}$ | |||

Sunflower | 12.3414 | $3.8224\times {10}^{3}$ | |||

Statue of Liberty | 12.0976 | $4.0431\times {10}^{3}$ | |||

[31] | Edge detection algorithm (Canny) | Apple | 2.678 | $3.54\times {10}^{4}$ | |

Flower | 2.789 | $3.45\times {10}^{4}$ | |||

Lena | 6.206 | $1.57\times {10}^{4}$ | |||

[29] | Edge detection (Prewitt, Sobel, Laplacian of Gaussian, Canny, Roberts) | Salt Pepper Noise Effected Sun Flower Image | Roberts | 8.6962 | $8.779\times {10}^{4}$ |

Sobel | 8.6965 | $8.778\times {10}^{4}$ | |||

Prewitt | 8.6965 | $8.778\times {10}^{4}$ | |||

LOG | 8.7024 | $8.766\times {10}^{4}$ | |||

Canny | 8.7087 | $8.754\times {10}^{4}$ | |||

[32] | Edge Detection (Canny operator, Laplacian of Gaussian, Sobel operator) | Lena | LOG | 5.2217 | $1.953\times {10}^{4}$ |

Canny | 5.2161 | $1.956\times {10}^{4}$ | |||

Sobel | 5.2476 | $1.942\times {10}^{4}$ | |||

[30] | Edge detection (Sobel, Prewitt, Canny) | Statue of liberty | Sobel | 5.6365 | $1.775\times {10}^{4}$ |

Prewitt | 5.6342 | $1.776\times {10}^{4}$ | |||

Canny | 5.6182 | $1.783\times {10}^{4}$ |

## 6. Conclusions

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## References

- Guo, J.M.; Prasetyo, H.; Wong, K. Vehicle verification using Gabor filter magnitude with gamma distribution modeling. IEEE Signal Process. Lett.
**2014**, 21, 600–604. [Google Scholar] [CrossRef] - Kwolek, B. Face detection using convolutional neural networks and Gabor filters. In International Conference on Artificial Neural Networks; Springer: Berlin/Heidelberg, Germany, 2005; pp. 551–556. [Google Scholar]
- Gabor, D. Theory of communication. Part 1: The analysis of information. J. Inst. Electr.-Eng.-Part III Radio Commun. Eng.
**1946**, 93, 429–441. [Google Scholar] [CrossRef] [Green Version] - Rajan, S.; Chenniappan, P.; Devaraj, S.; Madian, N. Facial expression recognition techniques: A comprehensive survey. IET Image Process.
**2019**, 13, 1031–1040. [Google Scholar] [CrossRef] - Mehrotra, R.; Namuduri, K.R.; Ranganathan, N. Gabor filter-based edge detection. Pattern Recognit.
**1992**, 25, 1479–1494. [Google Scholar] [CrossRef] - Licciardo, G.D.; Cappetta, C.; Di Benedetto, L. FPGA optimization of convolution-based 2D filtering processor for image processing. In Proceedings of the 2016 8th Computer Science and Electronic Engineering (CEEC), Colchester, UK, 28–30 September 2016; pp. 180–185. [Google Scholar]
- Kamarainen, J.K.; Kyrki, V.; Kalviainen, H. Invariance properties of Gabor filter-based features-overview and applications. IEEE Trans. Image Process.
**2006**, 15, 1088–1099. [Google Scholar] [CrossRef] [PubMed] - Licciardo, G.D.; Cappetta, C.; Di Benedetto, L. Design and FPGA implementation of a real-time processor for the HDR conversion of images and videos. In Proceedings of the 2016 8th Computer Science and Electronic Engineering (CEEC), Colchester, UK, 28–30 September 2016; pp. 192–197. [Google Scholar]
- Khan, M.; Mufti, N. Comparison of various edge detection filters for ANPR. In Proceedings of the 2016 Sixth International Conference on Innovative Computing Technology (INTECH), Dublin, Ireland, 24–26 August 2016; pp. 306–309. [Google Scholar]
- Humpire-Mamani, G.; Traina, A.J.; Traina, C. k-Gabor: A new feature extraction method for medical images providing internal analysis. In Proceedings of the 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS), Rome, Italy, 20–22 June 2012; pp. 1–6. [Google Scholar]
- Cappetta, C.; Licciardo, G.D.; Di Benedetto, L. Hardware accelerator using Gabor filters for image recognition applications. In Proceedings of the 2017 International Symposium on Signals, Circuits and Systems (ISSCS), Iasi, Romania, 13–14 July 2017; pp. 1–4. [Google Scholar] [CrossRef]
- Kamarainen, J.K.; Kyrki, V.; Kälviäinen, H. Robustness of Gabor Feature Parameter Selection; MVA, 2002; pp. 132–135. Available online: https://www.researchgate.net/publication/221280166_Robustness_of_Gabor_Feature_Parameter_Selection (accessed on 22 March 2022).
- Jiang, W.; Lam, K.M.; Shen, T.Z. Efficient edge detection using simplified Gabor wavelets. IEEE Trans. Syst. Man, Cybern. Part B (Cybern.)
**2009**, 39, 1036–1047. [Google Scholar] [CrossRef] [PubMed] - Zhang, W.C.; Wang, F.P.; Zhu, L.; Zhou, Z.F. Corner detection using Gabor filters. IET Image Process.
**2014**, 8, 639–646. [Google Scholar] [CrossRef] - Hu, H. Enhanced gabor feature based classification using a regularized locally tensor discriminant model for multiview gait recognition. IEEE Trans. Circuits Syst. Video Technol.
**2013**, 23, 1274–1286. [Google Scholar] [CrossRef] - Daugman, J.G. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. JOSA A
**1985**, 2, 1160–1169. [Google Scholar] [CrossRef] [PubMed] - Licciardo, G.D.; D’Arienzo, A.; Rubino, A. Stream processor for real-time inverse Tone Mapping of Full-HD images. IEEE Trans. Very Large Scale Integr. Syst.
**2014**, 23, 2531–2539. [Google Scholar] [CrossRef] - Cappetta, C.; Licciardo, G.D.; Di Benedetto, L. Optimal design of a Gabor filter for medical imaging applications. In Proceedings of the 2017 7th IEEE International Workshop on Advances in Sensors and Interfaces (IWASI), Vieste, Italy, 15–16 June 2017; pp. 228–232. [Google Scholar]
- Licciardo, G.D.; Cappetta, C.; Di Benedetto, L. Design Criteria for Real-time Processing of HW Gabor Filters in Visual Search. In Proceedings of the 2018 IEEE International Symposium on Circuits and Systems (ISCAS), Florence, Italy, 27–30 May 2018; pp. 1–5. [Google Scholar]
- Licciardo, G.D.; Cappetta, C.; Di Benedetto, L. Design of a Gabor filter HW accelerator for applications in medical imaging. IEEE Trans. Components Packag. Manuf. Technol.
**2018**, 8, 1187–1194. [Google Scholar] [CrossRef] - Kayalvizhi, E.; Sasirekha, N. A modified low power architecture for Gabor filter. In Proceedings of the 2016 International Conference on Communication and Signal Processing (ICCSP), Melmaruvathur, India, 6–8 April 2016; pp. 0597–0600. [Google Scholar]
- Namuduri, K.R.; Mehrotra, R.; Ranganathan, N. Edge detection models based on Gabor filters. In Proceedings of the International Conference on Pattern Recognition; IEEE Computer Society Press: Piscataway, NJ, USA, 1992; p. 729. [Google Scholar]
- Wang, K.; Chen, B.; Wu, G. Edge detection from high-resolution remotely sensed imagery based on Gabor filter in frequency domain. In Proceedings of the 2010 18th International Conference on Geoinformatics, Beijing, China, 18–20 June 2010; pp. 1–6. [Google Scholar]
- Razak, A.; Taharim, R. Implementing Gabor filter for fingerprint recognition using Verilog HDL. In Proceedings of the 2009 5th International Colloquium on Signal Processing & Its Applications, Kuala Lumpur, Malaysia, 6–8 March 2009; pp. 423–427. [Google Scholar]
- Fredj, A.H.; Malek, J. FPGA-accelerated anisotropic diffusion filter based on SW/HW-codesign for medical images. J. Real-Time Image Process.
**2021**, 18, 2429–2440. [Google Scholar] [CrossRef] - Sengupta, A.; Rathor, M. Obfuscated Hardware Accelerators for Image Processing Filters—Application Specific and Functionally Reconfigurable Processors. IEEE Trans. Consum. Electron.
**2020**, 66, 386–395. [Google Scholar] [CrossRef] - Goyal, B.; Dogra, A.; Agrawal, S.; Sohi, B.S.; Sharma, A. Image denoising review: From classical to state-of-the-art approaches. Inf. Fusion
**2020**, 55, 220–244. [Google Scholar] [CrossRef] - Papitha, J.; Nedumaran, D. Performance Evaluation of Gabor Filter in Removing Rician Noise in MR Images. In Proceedings of the Fourth International Conference on Signal and Image Processing 2012 (ICSIP 2012); Springer: Berlin/Heidelberg, Germany, 2013; pp. 353–363. [Google Scholar]
- Ansari, M.A.; Kurchaniya, D.; Dixit, M. A comprehensive analysis of image edge detection techniques. Int. J. Multimed. Ubiquitous Eng.
**2017**, 12, 1–12. [Google Scholar] [CrossRef] - Ahmed, A.S. Comparative study among Sobel, Prewitt and Canny edge detection operators used in image processing. J. Theor. Appl. Inf. Technol.
**2018**, 96, 6517–6525. [Google Scholar] - Patil, P.P.R. Image Edge Detection Techniques using MATLAB Simulink. Int. J. Eng. Res. Technol.
**2014**, 3, 2149–2153. [Google Scholar] - Poobathy, D.; Chezian, R.M. Edge detection operators: Peak signal to noise ratio based comparison. IJ Image Graph. Signal Process.
**2014**, 10, 55–61. [Google Scholar] [CrossRef] [Green Version] - Sujatha, C.; Selvathi, D. A Novel Image Edge Detection Method Using Simplified Gabor Wavelet. In International Conference on Computer Science and Information Technology; Springer: Berlin/Heidelberg, Germany, 2012; pp. 620–630. [Google Scholar]
- Negi, N.; Mathur, S. An improved method of edge detection based on Gabor wavelet transform. In Recent Advances in Electrical Engineering And Electronic Devices; WSEAS: Geneva, Switzerland, 2014; pp. 184–191. [Google Scholar]
- Available online: https://in.mathworks.com/help/wavelet/ref/measerr.html (accessed on 20 March 2022).
- Zhang, L.; Zhang, L.; Mou, X.; Zhang, D. FSIM: A feature similarity index for image quality assessment. IEEE Trans. Image Process.
**2011**, 20, 2378–2386. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Chen, G.H.; Yang, C.L.; Po, L.M.; Xie, S.L. Edge-based structural similarity for image quality assessment. In Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, Toulouse, France, 14–19 May 2006; Volume 2, p. II. [Google Scholar]

**Figure 6.**Hardware models for realizing the fractional values of parameters involved in the Gabor function.

**Figure 7.**Histogram for original image, Gabor filtered image and the image after Edge detection. X label in each histogram: intensity level; Y label in each histogram: number of pixels against the intensity level.

**Table 1.**Results of PSNR and MSE values for different image datasets applied with the Gabor filter-based edge detection.

S. No. | Image Name | PSNR (Gabor) | MSE (Gabor) |
---|---|---|---|

1 | Apple (256 × 256) | 10.4857 | $5.8602\times {10}^{3}$ |

2 | Flower (256 × 256) | 9.2483 | $7.7920\times {10}^{3}$ |

3 | Women (256 × 256) | 10.0816 | $6.4315\times {10}^{3}$ |

4 | Lady (256 × 256) | 9.4466 | $7.4442\times {10}^{3}$ |

5 | Lena (512 × 512) | 11.8913 | $4.2398\times {10}^{3}$ |

6 | Coffee (512 × 512) | 12.5336 | $3.6569\times {10}^{3}$ |

7 | Monkey (512 × 512) | 8.5536 | $9.1437\times {10}^{3}$ |

8 | Sunflower (512 × 512) | 12.3414 | $3.8224\times {10}^{3}$ |

9 | Statue of Liberty (512 × 512) | 12.0976 | $4.0431\times {10}^{3}$ |

Image | Method | L2RAT | SSIM | FSIM |
---|---|---|---|---|

Apple | Sobel | $5.64\times {10}^{-7}$ | $2.00\times {10}^{-6}$ | 0.032 |

log | $1.49\times {10}^{-6}$ | $4.91\times {10}^{-6}$ | 0.046 | |

Canny | $1.90\times {10}^{-6}$ | $3.47\times {10}^{-6}$ | 0.823 | |

Prop. | 0.8696 | 0.779 | 0.788 | |

Lena | Sobel | $2.23\times {10}^{-6}$ | $9.75\times {10}^{-7}$ | 0.286 |

log | $3.62\times {10}^{-6}$ | $8.04\times {10}^{-6}$ | 0.754 | |

Canny | $5.26\times {10}^{-6}$ | $2.31\times {10}^{-7}$ | 0.568 | |

Prop. | 0.7819 | 0.3992 | 0.383 | |

Sunflower | Sobel | $1.84\times {10}^{-6}$ | $1.19\times {10}^{-6}$ | 0.054 |

log | $4.42\times {10}^{-6}$ | $1.13\times {10}^{-5}$ | 0.779 | |

Canny | $7.98\times {10}^{-6}$ | $3.66\times {10}^{-6}$ | 0.13 | |

Prop. | 0.6218 | 0.3827 | 0.494 | |

Statue | Sobel | $2.04\times {10}^{-6}$ | $1.35\times {10}^{-6}$ | 0.469 |

log | $2.48\times {10}^{-6}$ | $8.61\times {10}^{-6}$ | 0.337 | |

Canny | $3.75\times {10}^{-6}$ | $9.24\times {10}^{-6}$ | 0.794 | |

Prop. | 0.7625 | 0.3921 | 0.393 | |

Flower | Sobel | $6.75\times {10}^{-7}$ | $4.97\times {10}^{-7}$ | 0.529 |

log | $6.86\times {10}^{-7}$ | $6.61\times {10}^{-7}$ | 0.602 | |

Canny | $8.77\times {10}^{-7}$ | $3.30\times {10}^{-7}$ | 0.654 | |

Prop. | 0.891 | 0.7699 | 0.737 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Dakshayani, V.; Locharla, G.R.; Pławiak, P.; Datti, V.; Karri, C.
Design of a Gabor Filter-Based Image Denoising Hardware Model. *Electronics* **2022**, *11*, 1063.
https://doi.org/10.3390/electronics11071063

**AMA Style**

Dakshayani V, Locharla GR, Pławiak P, Datti V, Karri C.
Design of a Gabor Filter-Based Image Denoising Hardware Model. *Electronics*. 2022; 11(7):1063.
https://doi.org/10.3390/electronics11071063

**Chicago/Turabian Style**

Dakshayani, Virodhi, Govinda Rao Locharla, Paweł Pławiak, Venkataramana Datti, and Chiranjeevi Karri.
2022. "Design of a Gabor Filter-Based Image Denoising Hardware Model" *Electronics* 11, no. 7: 1063.
https://doi.org/10.3390/electronics11071063