A Multi-Objective Enhanced Fruit Fly Optimization (MO-EFOA) Framework for Despeckling SAR Images using DTCWT based Local Adaptive Thresholding

Kumar, Bibek; Ranjan, Ranjeet Kumar; Husain, Arshad

doi:10.1080/01431161.2021.1921875

Cited by 11 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The scope of this problem is focused on detecting geological features over the SAR imagery, which can be noisy and thus challenging. Due to the nature of SAR images, they are affected by multiplicative noise, which is also known as speckle noise [ 11 ]. This kind of noise is one of the main things that affect the overall performance of any classification methodology.…”

Section: Introductionmentioning

confidence: 99%

Localization and Classification of Venusian Volcanoes Using Image Detection Algorithms

Đuranović

Šegota

Lorencin

et al. 2023

Sensors

View full text Add to dashboard Cite

Imaging is one of the main tools of modern astronomy—many images are collected each day, and they must be processed. Processing such a large amount of images can be complex, time-consuming, and may require advanced tools. One of the techniques that may be employed is artificial intelligence (AI)-based image detection and classification. In this paper, the research is focused on developing such a system for the problem of the Magellan dataset, which contains 134 satellite images of Venus’s surface with individual volcanoes marked with circular labels. Volcanoes are classified into four classes depending on their features. In this paper, the authors apply the You-Only-Look-Once (YOLO) algorithm, which is based on a convolutional neural network (CNN). To apply this technique, the original labels are first converted into a suitable YOLO format. Then, due to the relatively small number of images in the dataset, deterministic augmentation techniques are applied. Hyperparameters of the YOLO network are tuned to achieve the best results, which are evaluated as mean average precision (mAP@0.5) for localization accuracy and F1 score for classification accuracy. The experimental results using cross-vallidation indicate that the proposed method achieved 0.835 mAP@0.5 and 0.826 F1 scores, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Localization and Classification of Venusian Volcanoes Using Image Detection Algorithms

Đuranović

Šegota

Lorencin

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Literature [15] discussed the correlation between noise reduction processing and image quality and analyzed clinical CT imaging as an example, and the results showed that noise reduction could be effective by wavelet transform, thus improving image quality. The literature [16] proposed a noise-reduction optimization framework based on wavelet transform and performed experimental analysis, which showed that the framework could preserve high edges while pursuing high-quality denoised images. Kotte S et al analyzed medical image processing methods and concluded that adaptive multilevel thresholding could be used to segment brain images of MRI images, which in turn improves image segmentation efficiency.…”

Section: Introductionmentioning

confidence: 99%

Optimization of image processing methods based on wavelet transform and adaptive thresholding

Chen

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper first classifies the image noise and evaluates the image quality by means of the correlation function, mean square error value, and fidelity. Secondly, an image adaptive threshold denoising system based on wavelet transform is constructed, and the image processing is realized by using the wavelet transform principle and the selection of threshold value. Finally, the image is optimized by using the modulo-maximum denoising method and the threshold denoising method for empirical analysis. The results show that the signal-to-noise ratio of the noisy signal is 6.2315dB, and the signal-to-noise ratio of the modulo-maximum processing is 12.7024 dB. The peak signal-to-noise ratio of the noisy image is 20.1258dB, the peak signal-to-noise ratio of the soft threshold denoising method is 26.4831dB, and the peak signal-to-noise ratio of the hard threshold denoising method is 22.5864dB. This shows that the wavelet transform and adaptive thresholding can effectively denoise and ensure image quality. Image quality.

show abstract

A SAR ATR Using a New Convolutional Neural Network Framework

Kumar

Ranjan

Husain

2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

A Multi-Objective Enhanced Fruit Fly Optimization (MO-EFOA) Framework for Despeckling SAR Images using DTCWT based Local Adaptive Thresholding

Cited by 11 publications

References 46 publications

Localization and Classification of Venusian Volcanoes Using Image Detection Algorithms

Localization and Classification of Venusian Volcanoes Using Image Detection Algorithms

Optimization of image processing methods based on wavelet transform and adaptive thresholding

A SAR ATR Using a New Convolutional Neural Network Framework

Contact Info

Product

Resources

About