A COMPREHENSIVE STUDY AND SURVEYON IMAGE RESTORATION TECHNIQUES
Keywords:
Image restoration, image acquisition, degradation, Inverse filtering, deconvolutionAbstract
The domain of image processing has experienced significant expansion in recent times, witnessing the introduction of numerous novel approaches to image restoration as part of this expansion. Image restoration is a challenging task in the field of Image processing field to restore image. For the reason of a single model by which to describe the image restoration problem. Dependent upon the nature of the processes by which the image was formed the actual models used and there are no universally agreed-upon criteria by which to judge the quality of a proposed image restoration process. These two criteria are the ones most frequently used in experiments with image restoration. During the process of image acquisition, sometimes images are degraded by various reason. Degradation may have various factors, such as motion of camera, blur lens, atmospheric disturbance, noise of sensor etc. Depending on the type of degradation, suitable and effective methods and algorithms of different image restoration are used. Restoration methods can categorize in to two types that are inverse filtering and Deconvolution. Inverse filtering is a fast and simple method that applies the inverse degradation function to the image. Inverse filtering is very responsive to noise and escalate it in the restored image. Therefore, inverse filtering is only suitable for images with known degradation functions and image having low noise levels. Numerous algorithms and filtering methods exist, each with distinct assumptions, advantages, and drawbacks depending on the prior understanding of the noise. Image smoothing stands out as a crucial and extensively employed procedure in image processing. In addition to addressing noise, this study also sheds light on a comparative examination of techniques for noise removal. This paper will outline diverse noise types affecting image models and explore different noise reduction methods, along with their respective strengths and weaknesses.
Downloads
References
Rani, S., Jindal, S., & Kaur, B. (2016). A brief review on image restoration techniques. International Journal of Computer Applications, 150(12), 30–33. doi:10.5120/ijca2016911623
Mohapatra, B., Ranjan, A., & Mishra, S. (2014). A comprehensive review on image restoration techniques. International Journal of Research in Advent Technology, 2(3), 101–105.
Thakur, M., SATI, Vidisha, M.P., India, & Datar, S. (2014). Image restoration based on deconvolution by Richardson Lucy algorithm. International Journal of Engineering Trends and Technology, 14(4), 161–165. doi:10.14445/22315381/ijett-v14p232
Pushpavalli, R., & Sivarajde, G. (2013). A hybrid filtering technique for eliminating uniform noise and impulse noise on digital images. Signal & Image Processing, 4.
Boracchi, G., & Foi, A. (2012). Modeling the performance of image restoration from motion blur. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 21(8), 3502–3517. doi:10.1109/TIP.2012.2192126
Singh, P., & Shree, R. (2016). A comparative study to noise models and image restoration techniques. International Journal of Computer Applications, 149(1), 18–27. doi:10.5120/ijca2016911336
Khare, C., & Nagwanshi, K. K. (2012). Image restoration technique with non linear filter. International Journal of Advanced Science and Technology, 39, 67–74.
Ali, A. M., Benjdira, B., Koubaa, A., El-Shafai, W., Khan, Z., & Boulila, W. (2023). Vision transformers in image restoration: A survey. Sensors (Basel, Switzerland), 23(5). doi:10.3390/s23052385
Li, Y. (2023). Lsdir: A large-scale dataset for image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
Xia, B., Zhang, Y., Wang, S., Wang, Y., Wu, X., Tian, Y., … Van Gool, L. (2023). DiffIR: Efficient Diffusion Model for Image Restoration. Retrieved from http://arxiv.org/abs/2303.09472
