1. Sand-Dust Image Enhancement
Numerous studies have been conducted to tackle the aforementioned issue. These studies encompass the use of
histogram equalization and its modifications for the purpose of improving image contrast [1, 2, 3]. Additionally,
Retinex-based methodologies have been employed to boost image contrast and brightness. Furthermore, the challenge
of sand dust enhancement has been approached as a dehazing problem in [4]. Sand dust images can also be enhanced
using fusion strategies [5, 6, 7, 8, 9]. Enhancement of images is very essential in object tracking and classification [10,
11, 12, 13, 14, 15, 16, 17, 18].
Sand dust images show typical strip noise. It's tough to reduce noise from these images with poor texture without
sacrificing delicate image details. Human viewers are especially sensitive to the high-frequency visual distortions that
occur. In the field of computer vision, many outstanding image denoising methods have been proposed [19].
The deterioration of hazy, sand-dust and underwater images is mostly attributed to the phenomena of absorption of
light and scattering. [20, 21, 22, 23, 24]. To be more precise, the scattering of visible light occurs as a result of the
physical properties of the surrounding medium. Hence, the ambient light source will comprise both original visible
light and scattered light. Typically, the imaging device concludes the imaging procedure by capturing the emitted light
from the scene of the object. The absorption of visible light by the surrounding medium results in a reduction in the
intensity of the acquired radiation. Furthermore, the extent of attenuation is contingent upon the spatial separation of
the objects in the scene and the imaging apparatus. Most of the key scene recovery challenges, namely enhancement
of sand-dust/ underwater images and dehazing of images, are tackled as independent computer vision applications.
These image deteriorations have identical features namely low contrast, low visibility and color distortion.
Scene recovery has been the subject of considerable research, yielding significant and noteworthy findings.
Ongoing investigations continue to advance current knowledge in this field. There has been a surge in the use of
Convolutional Neural Network (CNN) based approaches for the restoration of single images. [25] introduced a deep
neural network called DehazeNet to address the task of estimation of transmission map. Subsequently, a standard
method was employed to assess the atmospheric light. The transmission map estimation was performed with the help
of a multiscale variant of Dehazenet [26]. [27] introduced a method called AOD-Net, which utilizes a lightweight
CNN to directly enhance the latent sharp image from a hazy image.
The dark channel, haze imaging model, and transmission priors were all included into a deep architecture to propose
a proximal Dehaze-Net in [28]. To improvise the quality of the underwater image, [29] proposed a deep learning
system based on wavelet-corrected transforms. With the premise of an underwater scenario, [30] used a CNN network
for the purpose of underwater images visual improvement. An underwater image improvement benchmark was
developed, and a network (Water-Net) was proposed to be trained on this benchmark. These imaging outcomes from
supervised learning rely heavily on the diversity and volumes of the datasets available for analysis. The unsupervised
learning technique known as the Generative Adversarial Network (GAN) has shown promising results in the field of
scene recovery. It can improve the visual quality in a variety of weather and imaging settings, and generate synthetic
images that appear incredibly authentic.
References
[1] J.-Y. Kim, L.-S. Kim and S.-H. Hwang, "An advanced contrast enhancement using partially
overlapped sub-block histogram equalization," IEEE Transactions on Circuits and Systems for Video
Technology, vol. 11, no. 4, pp. 475-484, 2001.
2. [2] J. Wang, Y. Pang, Y. He and C. Liu, "Enhancement for Dust-Sand Storm Images," in International
Conference on Multimedia Modeling, 2016.
[3] N. Zhi, S. J. Mao and M. Li, "Visibility restoration algorithm of dustdegraded images," J. Image
Graph, vol. 21, no. 12, p. 1585–1592, 2016.
[4] S. G. Narasimhan and S. K. Nayar, "Contrast restoration of weather degraded images," IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 6, pp. 713-724, 2003.
[5] G. Tirumala Vasu and P. Palanisamy , "Multi-focus image fusion using anisotropic diffusion filter,"
Soft Computing, vol. 26, no. 20, p. 14029–14040, 2022.
[6] S. Fiza, "IMAGE FUSION," in Application of Encoding Systems, COUNCIL OF INDUSTRIAL
INNOVATION AND RESEARCH (CIIR), 2023, pp. 23-25.
[7] S. Fiza and S. S, "MULTI-SENSOR MEDICAL IMAGE FUSION USING COMPUTATIONAL HARMONIC
ANALYSIS WITH WAVE ATOMS". INDIA Patent 27192, 17 3 2023.
[8] G. Tirumala Vasu; P. Palanisamy, "CT and MRI multi-modal medical image fusion using weight-
optimized anisotropic diffusion filtering," Soft Computing, vol. 27, no. 13, p. 9105–9117, 2023.
[9] G. Tirumala Vasu; P. Palanisamy, "Gradient-based multi-focus image fusion using foreground and
background pattern recognition with weighted anisotropic diffusion filter," Signal, Image and
Video Processing, vol. 17, no. 5, p. 2531–2543, 2023.
[10] S. Fiza, G. T. Vasu, A. Kubra, A. K. Kumar and K. Seelam, "MACHINE LEARNING ALGORITHMS BASED
SUBCLINICAL KERATOCONUS DETECTION," NeuroQuantology, vol. 20, no. 20, pp. 1825-1837, 2022.
[11] S. Fiza, "IMAGE PROCESSING METHODS," in INNOVATIVE SYSTEMS DESIGN & APPLICATION, CIIR
Books and Publications, 2023, pp. 7-9.
[12] S. Fiza, "PROBLEM RECOGNITION," in Feature Extraction and Gesture Recognition, COUNCIL OF
INDUSTRIAL INNOVATION AND RESEARCH (CIIR), 2023, p. 4.
[13] G. Tirumala Vasu, Samreen Fiza, Sandhya Tatekalva and Kishore Kumar, "Deep Learning Model
based Object Detection and Image Classification," Solid State Technology, vol. 61, no. 3, pp. 15-25,
2018.
[14] Sandhya Tatekalva, Kishore Kumar, G. Tirumala Vasu and Samreen Fiza, "Pneumonia Detection
Using Deep Learning Model," Solid State Technology, vol. 61, no. 4, pp. 184-191, 2018.
[15] T. V. G, S. Fiza, A. K. Kumar, V. S. Devi, C. N. Kumar and A. Kubra, "Improved chimp optimization
algorithm (ICOA) feature selection and deep neural network framework for internet of things (IOT)
based android malware detection," Measurement: Sensors, vol. 28, p. 100785, 2023.
[16] G. T. VASU, "CLASSIFICATIONS OF IMAGE CONVERSION," in Feature Extraction and Gesture
Recognition, COUNCIL OF INDUSTRIAL INNOVATION AND RESEARCH (CIIR), 2023, pp. 7-9.
3. [17] G. T. VASU, "DIFFERENT FEATURES EXTRACTION," in Feature Extraction and Gesture Recognition,
COUNCIL OF INDUSTRIAL INNOVATION AND RESEARCH (CIIR), pp. 13-15.
[18] G. T. VASU, "CLASSIFICATIONS OF IMAGE CONVERSION," in Feature Extraction and Gesture
Recognition, COUNCIL OF INDUSTRIAL INNOVATION AND RESEARCH (CIIR), 2023.
[19] K. He, J. Sun and X. Tang, "Guided Image Filtering," IEEE Transactions on Pattern Analysis and
Machine Intelligence, vol. 35, no. 6, pp. 1397-1409, 2013.
[20] K. He, J. Sun and X. Tang, "Single image haze removal using dark channel prior," IEEE Transactions
on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, p. 2341–2353, 2011.
[21] M. Sulami, I. Glatzer, R. Fattal and M. Werman, "Automatic recovery of the atmospheric light in
hazy images," in IEEE International Conference on Computational Photography (ICCP), 2014.
[22] F. Fang, F. Li and T. Zeng, "Single image dehazing and denoising: a fast variational approach," SIAM
Journal on Imaging Sciences, vol. 7, no. 2, p. 969–996, 2014.
[23] X. Fu, Y. Huang, D. Zeng, X.-P. Zhang and X. Ding, "A fusion based enhancing approach for single
sandstorm image," in IEEE 16th International Workshop on Multimedia Signal Processing (MMSP),
2014.
[24] C. Li, S. Anwar and F. Porikli, "Underwater scene prior inspired deep underwater image and video
enhancement," Pattern Recognition, vol. 98, p. 107038, 2020.
[25] B. Cai, X. Xu, K. Jia, C. Qing and D. Tao, "Dehazenet: An end-to-end system for single image haze
removal," IEEE Transactions on Image Processing, vol. 25, no. 11, p. 5187–5198, 2016.
[26] Y. Y. Schechner and Y. Averbuch, "Regularized image recovery in scattering media," IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 9, p. 1655–1660, 2007.
[27] B. Li, X. Peng, Z. Wang, J. Xu and D. Feng, "Aod-net: All-in-one dehazing network," in Proceedings of
the IEEE International Conference on Computer Vision, 2017.
[28] D. Yang and J. Sun, "Proximal dehaze-net: A prior learning-based deep network for single image
dehazing," in Proceedings of the European Conference on Computer Vision (ECCV), 2018.
[29] A. Jamadandi and U. Mudenagudi, "Exemplar-based underwater image enhancement augmented
by wavelet corrected transforms," in IEEE Conference on Computer Vision and Pattern Recognition
Workshops, 2019.
[30] C. Li, S. Anwar and F. Porikli., "Underwater scene prior inspired deep underwater image and video
enhancement," Pattern Recognition, vol. 98, p. 107038, 2020.