Underwater Image Enhancement Using FPGA-Based Gaussian Filters with Approximation Techniques

Document Type : Original Research Article


Graduate University of Advanced Technology


The major challenge in marine environment imaging lies in addressing the haziness induced by natural phenomena, such as absorption and scattering in underwater scenes. This haze significantly impacts the visual quality of underwater images, necessitating improvement. This paper presents a novel approach aimed at enhancing the efficiency of Gaussian filters for reducing Gaussian noise in underwater images. The method introduces a pipeline structure in the Gaussian filter implementation and evaluates the influence of employing approximate adders on overall performance. Simulation results reveal a notable speed enhancement exceeding 150%, coupled with a substantial reduction in power consumption exceeding 34%. However, these advantages are tempered by an increase in spatial requirements. The study recognizes the inherent tradeoff between output quality and power, highlighting the applicability of the proposed design in error-resilient applications, particularly in image and video processing domains. In essence, the presented approach offers a compelling solution where the benefits of accelerated speed and reduced power consumption outweigh spatial constraints, contributing to the advancement of underwater image enhancement techniques.


Main Subjects

[1]    Fatan, M., Daliri, M. R., & Shahri, A. M. (2016). Underwater cable detection in the images using edge classification based on texture information. Measurement, 91, 309-317.
[2]    Saini, A., & Biswas, M. (2019). Object detection in underwater image by detecting edges using adaptive thresholding. 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI),
[3]    Princess, P. J. B., Silas, S., & Rajsingh, E. B. (2019). Performance analysis of edge detection algorithms for object detection in accident images. 2019 Global Conference for Advancement in Technology (GCAT),
[4]    Oliveira, A. J., Ferreira, B. M., & Cruz, N. A. (2021). A performance analysis of feature extraction algorithms for acoustic image-based underwater navigation. Journal of Marine Science and Engineering, 9(4), 361.
[5] Prasenan, P., & Suriyakala, C. (2022). A Study of Underwater Image Pre-processing and Techniques. In Computational Vision and Bio-Inspired Computing: Proceedings of ICCVBIC 2021 (pp. 313-333). Springer.
[6]    Borker, S., & Bonde, S. (2017). Contrast Enhancement and Visibility Restoration of Underwater Optical Images Using Fusion. International Journal of Intelligent Engineering & Systems, 10(4).
[7]    Mishra, A., Gupta, M., & Sharma, P. (2018). Enhancement of underwater images using improved CLAHE. 2018 International Conference on Advanced Computation and Telecommunication (ICACAT),
[8]    Yang, S., Chen, Z., Feng, Z., & Ma, X. (2019). Underwater image enhancement using scene depth-based adaptive background light estimation and dark channel prior algorithms. IEEE Access, 7, 165318-165327.
[9]    Bhairannawar, S. S. (2018). Efficient medical image enhancement technique using transform HSV space and adaptive histogram equalization. In Soft Computing Based Medical Image Analysis (pp. 51-60). Elsevier.
[10]  Ulutas, G., & Ustubioglu, B. (2021). Underwater image enhancement using contrast limited adaptive histogram equalization and layered difference representation. Multimedia Tools and Applications, 80, 15067-15091.
[11]  Priyadharsini, R., Sharmila, T. S., & Rajendran, V. (2016). An efficient edge detection technique using filtering and morphological operations for underwater acoustic images. Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies,
[12]  Shourya, S., Kumar, S., & Jha, R. K. (2016). Adaptive fractional differential approach to enhance underwater images. 2016 Sixth International Symposium on Embedded Computing and System Design (ISED),
[13]  Singh, N., & Bhat, A. (2023). A robust model for improving the quality of underwater images using enhancement techniques. Multimedia Tools and Applications, 1-22.
[14]  Xiao, B., Wang, K., Bi, X., Li, W., & Han, J. (2018). 2D-LBP: an enhanced local binary feature for texture image classification. IEEE Transactions on Circuits and Systems for Video Technology, 29(9), 2796-2808.
[15]  Ponomarev, A., Nalamwar, H. S., Babakov, I., Parkhi, C. S., & Buddhawar, G. (2016). Content-based image retrieval using color, texture and shape features. Key Engineering Materials, 685, 872-876.
[16]  Humeau-Heurtier, A. (2019). Texture feature extraction methods: A survey. IEEE Access, 7, 8975-9000.
[17]  Qasaimeh, M., Denolf, K., Lo, J., Vissers, K., Zambreno, J., & Jones, P. H. (2019). Comparing energy efficiency of CPU, GPU and FPGA implementations for vision kernels. 2019 IEEE international conference on embedded software and systems (ICESS),
[18]  Gupta, U., Babu, M., Ayoub, R., Kishinevsky, M., Paterna, F., Gumussoy, S., & Ogras, U. Y. (2018). An online learning methodology for performance modeling of graphics processors. IEEE Transactions on Computers, 67(12), 1677-1691.
[19]  HajiRassouliha, A., Taberner, A. J., Nash, M. P., & Nielsen, P. M. (2018). Suitability of recent hardware accelerators (DSPs, FPGAs, and GPUs) for computer vision and image processing algorithms. Signal Processing: Image Communication, 68, 101-119.
[20]  Diouri, O., Gaga, A., Ouanan, H., Senhaji, S., Faquir, S., & Jamil, M. O. (2022). Comparison study of hardware architectures performance between FPGA and DSP processors for implementing digital signal processing algorithms: Application of FIR digital filter. Results in Engineering, 16, 100639.
[21]  De Haro, J. M., Bosch, J., Filgueras, A., Vidal, M., Jiménez-González, D., Alvarez, C., Martorell, X., Ayguadé, E., & Labarta, J. (2021). OmpSs@ FPGA framework for high performance FPGA computing. IEEE Transactions on Computers, 70(12), 2029-2042.
[22]  Pirzada, S. J. H., Murtaza, A., Xu, T., & Jianwei, L. (2020). A reconfigurable model-based design for rapid prototyping on FPGA. International Journal of Computer Theory and Engineering, 12(3), 80-84.
 [23] Chamola, V., Patra, S., Kumar, N., & Guizani, M. (2020). Fpga for 5g: Re-configurable hardware for next generation communication. IEEE Wireless Communications, 27(3), 140-147.
[24]  Cabello, F., León, J., Iano, Y., & Arthur, R. (2015). Implementation of a fixed-point 2D Gaussian Filter for Image Processing based on FPGA. 2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA),
[25]  Murray, K. E., Luu, J., Walker, M. J., McCullough, C., Wang, S., Huda, S., Yan, B., Chiasson, C., Kent, K. B., & Anderson, J. (2020). Optimizing FPGA logic block architectures for arithmetic. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 28(6), 1378-1391.
[26]  Nomani, T., Mohsin, M., Pervaiz, Z., & Shafique, M. (2020). xUAVs: Towards efficient approximate computing for UAVs—Low power approximate adders with single LUT delay for FPGA-based aerial imaging optimization. IEEE Access, 8, 102982-102996.
[27]  Zhu, Z., Zhang, J., Zhao, J., Cao, J., Zhao, D., Jia, G., & Meng, Q. (2019). A hardware and software task-scheduling framework based on CPU+ FPGA heterogeneous architecture in edge computing. IEEE Access, 7, 148975-148988
[28]  Guraksin, G. E., Deperlioglu, O., & Kose, U. (2019). A novel underwater image enhancement approach with wavelet transform supported by differential evolution algorithm. Nature Inspired Optimization Techniques for Image Processing Applications, 255-278.
[29]  S. M. Alex Raj, M. H. S. (2015). FPGA Implementation of Underwater Image Enhancement using Nonlinear Filtering. Indian Journal of Science and Technology, 8(35),1-5. https://doi.org/10.17485/ijst/2015/v8i35/79110
[30]  Aguirre-Castro, O., García-Guerrero, E., López-Bonilla, O., Tlelo-Cuautle, E., López-Mancilla, D., Cárdenas-Valdez, J., Olguín-Tiznado, J., & Inzunza-González, E. (2022). Evaluation of underwater image enhancement algorithms based on Retinex and its implementation on embedded systems. Neurocomputing, 494, 148-159.
[31]  Park, J. W., Lee, H., Kim, B., Kang, D.-G., Jin, S. O., Kim, H., & Lee, H.-J. (2019). A low-cost and high-throughput FPGA implementation of the retinex algorithm for real-time video enhancement. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 28(1), 101-114.
[32]  Padhy, A. P., & Das, B. P. (2023). Lightweight Approximate Multiplier with Improved Accuracy in FPGA for Error Resilient Application. 2023 36th International Conference on VLSI Design and 2023 22nd International Conference on Embedded Systems (VLSID),
[33]  Ullah, S., & Kumar, A. (2023). Approximate Arithmetic Circuit Architectures for FPGA-based Systems. Springer Nature.
 [34] Amrouch, H., Ehsani, S. B., Gerstlauer, A., & Henkel, J. (2019). On the efficiency of voltage overscaling under temperature and aging effects. IEEE Transactions on Computers, 68(11), 1647-1662.
[35]  Bahoo, A. A., Akbari, O., & Shafique, M. (2023). An Energy-Efficient Generic Accuracy Configurable Multiplier Based on Block-Level Voltage Overscaling. IEEE Transactions on Emerging Topics in Computing.
[36]  Jiang, H., Santiago, F. J. H., Mo, H., Liu, L., & Han, J. (2020). Approximate arithmetic circuits: A survey, characterization, and recent applications. Proceedings of the IEEE, 108(12), 2108-2135.
[37]  Mafi, M., Martin, H., Cabrerizo, M., Andrian, J., Barreto, A., & Adjouadi, M. (2019). A comprehensive survey on impulse and Gaussian denoising filters for digital images. Signal Processing, 157, 236-260.
[38]  Anusha, G., & Deepa, P. (2020). Design of approximate adders and multipliers for error tolerant image processing. Microprocessors and Microsystems, 72, 102940.
[39]  Assessment, I. Q. (2004). From error visibility to structural similarity. IEEE transactions on image processing, 13(4), 93.
 [40] Liang, J., Han, J., & Lombardi, F. (2012). New metrics for the reliability of approximate and probabilistic adders. IEEE Transactions on Computers, 62(9), 1760-1771.
[41]  Li, C., Guo, C., Ren, W., Cong, R., Hou, J., Kwong, S., & Tao, D. (2019). An underwater image enhancement benchmark dataset and beyond. IEEE transactions on image processing, 29, 4376-4389.