Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142077
M. Younus, T. Hasan
DeepFake using Generative Adversarial Networks (GANs) tampered videos reveals a new challenge in today’s life. With the inception of GANs, generating high-quality fake videos becomes much easier and in a very realistic manner. Therefore, the development of efficient tools that can automatically detect these fake videos is of paramount importance. The proposed DeepFake detection method takes the advantage of the fact that current DeepFake generation algorithms cannot generate face images with varied resolutions, it is only able to generate new faces with a limited size and resolution, a further distortion and blur is needed to match and fit the fake face with the background and surrounding context in the source video. This transformation causes exclusive blur inconsistency between the generated face and its background in the outcome DeepFake videos, in turn, these artifacts can be effectively spotted by examining the edge pixels in the wavelet domain of the faces in each frame compared to the rest of the frame. A blur inconsistency detection scheme relied on the type of edge and the analysis of its sharpness using Haar wavelet transform as shown in this paper, by using this feature, it can determine if the face region in a video has been blurred or not and to what extent it has been blurred. Thus will lead to the detection of DeepFake videos. The effectiveness of the proposed scheme is demonstrated in the experimental results where the “UADFV” dataset has been used for the evaluation, a very successful detection rate with more than 90.5% was gained.
{"title":"Effective and Fast DeepFake Detection Method Based on Haar Wavelet Transform","authors":"M. Younus, T. Hasan","doi":"10.1109/CSASE48920.2020.9142077","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142077","url":null,"abstract":"DeepFake using Generative Adversarial Networks (GANs) tampered videos reveals a new challenge in today’s life. With the inception of GANs, generating high-quality fake videos becomes much easier and in a very realistic manner. Therefore, the development of efficient tools that can automatically detect these fake videos is of paramount importance. The proposed DeepFake detection method takes the advantage of the fact that current DeepFake generation algorithms cannot generate face images with varied resolutions, it is only able to generate new faces with a limited size and resolution, a further distortion and blur is needed to match and fit the fake face with the background and surrounding context in the source video. This transformation causes exclusive blur inconsistency between the generated face and its background in the outcome DeepFake videos, in turn, these artifacts can be effectively spotted by examining the edge pixels in the wavelet domain of the faces in each frame compared to the rest of the frame. A blur inconsistency detection scheme relied on the type of edge and the analysis of its sharpness using Haar wavelet transform as shown in this paper, by using this feature, it can determine if the face region in a video has been blurred or not and to what extent it has been blurred. Thus will lead to the detection of DeepFake videos. The effectiveness of the proposed scheme is demonstrated in the experimental results where the “UADFV” dataset has been used for the evaluation, a very successful detection rate with more than 90.5% was gained.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120993648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/csase48920.2020.9142106
{"title":"CSASE 2020 Table of Contents","authors":"","doi":"10.1109/csase48920.2020.9142106","DOIUrl":"https://doi.org/10.1109/csase48920.2020.9142106","url":null,"abstract":"","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132332469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142086
H. M. Azzawi, A. Ali, S. Gitaffa, S. Kadhim, Hussain Ali Azawi
The Underwater Wireless Optical Communication (UWOC) has recently been a unique opportunity for high data rate and moderate submarine distance communication compared with the most common choice such as acoustic wave communications technique. This paper proposes and simulates the design and performance evaluation of the new UWOC system under various conditions of water turbulence. The work has led to an advanced UWOC system which has been presented with appropriate theoretical, analysis and simulation. For the requirement of this target, Coherent Detection Optical Orthogonal Frequency Division Multiplexing (CO-OFDM) and Dual Polarisation technique have been proposed for enabling the next-generation underwater communication systems for to its ability to transmit high data rate and its ability to overcome underwater impairments (absorption, scattering and multipath). The results show significant improvement in Bit error rate (BER) performance of UWOC.
{"title":"Performance Evaluation of Dual Polarization Coherent Detection Optical for Next Generation of UWOC Systems","authors":"H. M. Azzawi, A. Ali, S. Gitaffa, S. Kadhim, Hussain Ali Azawi","doi":"10.1109/CSASE48920.2020.9142086","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142086","url":null,"abstract":"The Underwater Wireless Optical Communication (UWOC) has recently been a unique opportunity for high data rate and moderate submarine distance communication compared with the most common choice such as acoustic wave communications technique. This paper proposes and simulates the design and performance evaluation of the new UWOC system under various conditions of water turbulence. The work has led to an advanced UWOC system which has been presented with appropriate theoretical, analysis and simulation. For the requirement of this target, Coherent Detection Optical Orthogonal Frequency Division Multiplexing (CO-OFDM) and Dual Polarisation technique have been proposed for enabling the next-generation underwater communication systems for to its ability to transmit high data rate and its ability to overcome underwater impairments (absorption, scattering and multipath). The results show significant improvement in Bit error rate (BER) performance of UWOC.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114533197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142068
Hassan Jabar, R. Hassan, Abdulrahman Sameer Sadeq
The continuous growth of the generated volumes of waste and garbage grasps the attention of researchers and experts in various fields. The collection and management process of this massive and distributed amount of waste presents a challenge, as it needs to be collected and processed as fast as possible. The accumulated amounts of waste can be a fundamental source for emitting poisonous gases and producing toxic material to the soil which leads to deadly consequences for the environment and causes serious health issues for humans so it is critical to collect it as fast as possible. To handle this scenario, this study proposed an online waste management system to monitor the status of generated trash all-around smart cities then distribute and schedule available garbage trucks accordingly. The proposed solution provides a web-based system and a mobile application to manage the organization of these wastes and facilitate the garbage collection by the drivers. The proposed solution provides an 80% faster convergence system in comparison with traditional garbage collecting method. The mobile application makes the waste pick up easier for the drivers and enable them to use better roads. Therefore, garbage collection costs and efforts have been saved, while less consumed energy is required.
{"title":"A New Smart Waste Managing System","authors":"Hassan Jabar, R. Hassan, Abdulrahman Sameer Sadeq","doi":"10.1109/CSASE48920.2020.9142068","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142068","url":null,"abstract":"The continuous growth of the generated volumes of waste and garbage grasps the attention of researchers and experts in various fields. The collection and management process of this massive and distributed amount of waste presents a challenge, as it needs to be collected and processed as fast as possible. The accumulated amounts of waste can be a fundamental source for emitting poisonous gases and producing toxic material to the soil which leads to deadly consequences for the environment and causes serious health issues for humans so it is critical to collect it as fast as possible. To handle this scenario, this study proposed an online waste management system to monitor the status of generated trash all-around smart cities then distribute and schedule available garbage trucks accordingly. The proposed solution provides a web-based system and a mobile application to manage the organization of these wastes and facilitate the garbage collection by the drivers. The proposed solution provides an 80% faster convergence system in comparison with traditional garbage collecting method. The mobile application makes the waste pick up easier for the drivers and enable them to use better roads. Therefore, garbage collection costs and efforts have been saved, while less consumed energy is required.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134096180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142065
Meaad Hussein Abdul-Hadi, Jumana Waleed
Human Speech and Facial are the most significant information carriers for human cognitive-communication and recognizing human’s identity and emotional status. With the further growth of computer processing capability and the increase of demand for intelligent living, recognition of emotion based on face and speech became the most significant in the applications of Human-Computer Interaction (HCI). In this paper, Human Speech and Facial based emotion recognition technique using a support vector machine (SVM) has been proposed for improving the performance of detection with multi-emotions effectively. The obtained results of the proposed technique show that the average rate of recognition is higher than other recently existing techniques, and the obtained accuracy is 92.88% for facial model and 85.72 % for speech model with low time-consuming.
{"title":"Human Speech and Facial Emotion Recognition Technique Using SVM","authors":"Meaad Hussein Abdul-Hadi, Jumana Waleed","doi":"10.1109/CSASE48920.2020.9142065","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142065","url":null,"abstract":"Human Speech and Facial are the most significant information carriers for human cognitive-communication and recognizing human’s identity and emotional status. With the further growth of computer processing capability and the increase of demand for intelligent living, recognition of emotion based on face and speech became the most significant in the applications of Human-Computer Interaction (HCI). In this paper, Human Speech and Facial based emotion recognition technique using a support vector machine (SVM) has been proposed for improving the performance of detection with multi-emotions effectively. The obtained results of the proposed technique show that the average rate of recognition is higher than other recently existing techniques, and the obtained accuracy is 92.88% for facial model and 85.72 % for speech model with low time-consuming.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122311757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142073
Wassim M. Jassim, A. E. Abdelkareem
In the last two decades, underwater acoustic sensor networks have begun to be used for commercial and noncommercial purposes. In this paper, the focus will be on improving the monitoring performance system of oil pipelines. Linear wireless sensor networks are a model of underwater applications for which many solutions have been developed through several research studies in previous years for data collection research. In underwater environments, there are certain inherent limitations, like large propagation delays, high error rate, limited bandwidth capacity, and communication with short-range. Many deployment algorithms and routing algorithms have been used in this field. In this work a new hierarchical network model proposed by mean adding new nodes to the parents/ child relationship of the hierarchal linear structure with improvement to Smart Redirect or Jump algorithm (SRJ) which supports this type of network in underwater. This improved algorithm is used in an underwater linear wireless sensor network for data transfer to reduce the complexity in routing algorithms for relay nodes and minimize overall delay in network communication. This work is implemented using OMNET++ and MATLAB based on their integration. The results obtained based on throughput, energy consumption, and end to the end delay.
{"title":"Performance Enhancement of Oil Pipeline Monitoring for Underwater Wireless Sensor Network","authors":"Wassim M. Jassim, A. E. Abdelkareem","doi":"10.1109/CSASE48920.2020.9142073","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142073","url":null,"abstract":"In the last two decades, underwater acoustic sensor networks have begun to be used for commercial and noncommercial purposes. In this paper, the focus will be on improving the monitoring performance system of oil pipelines. Linear wireless sensor networks are a model of underwater applications for which many solutions have been developed through several research studies in previous years for data collection research. In underwater environments, there are certain inherent limitations, like large propagation delays, high error rate, limited bandwidth capacity, and communication with short-range. Many deployment algorithms and routing algorithms have been used in this field. In this work a new hierarchical network model proposed by mean adding new nodes to the parents/ child relationship of the hierarchal linear structure with improvement to Smart Redirect or Jump algorithm (SRJ) which supports this type of network in underwater. This improved algorithm is used in an underwater linear wireless sensor network for data transfer to reduce the complexity in routing algorithms for relay nodes and minimize overall delay in network communication. This work is implemented using OMNET++ and MATLAB based on their integration. The results obtained based on throughput, energy consumption, and end to the end delay.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"263 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122531920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142092
Harman Y. Ibrahim, Parishan M. Ismael, A. A. Albabawat, A. Al-Khalil
Conventional networks had several security problems, some of them solved using Software Defined Networking SDN and some others still exist such as Address Resolution Protocol ARP spoofing. In this paper, the SDN controller has been extended by a module which checks every ARP packet in the network to detect and stop the possible spoofed ones. The drawback of this mechanism begging to appear when the network gets larger and the traffic increase. As a result, this will increase the controller’s CPU load and Roundtrip time. As a solution to this problem, the extended module has been modified to handle ARP traffic to reduce ARP overhead in the network via giving the proxy ARP functionality to the controller. The emulation results showed that the proposed mechanism is robust against ARP spoofing attack and successfully prevented ARP broadcast messages in large networks and improved the response time by centrally responding to ARP requests.
{"title":"A Secure Mechanism to Prevent ARP Spoofing and ARP Broadcasting in SDN","authors":"Harman Y. Ibrahim, Parishan M. Ismael, A. A. Albabawat, A. Al-Khalil","doi":"10.1109/CSASE48920.2020.9142092","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142092","url":null,"abstract":"Conventional networks had several security problems, some of them solved using Software Defined Networking SDN and some others still exist such as Address Resolution Protocol ARP spoofing. In this paper, the SDN controller has been extended by a module which checks every ARP packet in the network to detect and stop the possible spoofed ones. The drawback of this mechanism begging to appear when the network gets larger and the traffic increase. As a result, this will increase the controller’s CPU load and Roundtrip time. As a solution to this problem, the extended module has been modified to handle ARP traffic to reduce ARP overhead in the network via giving the proxy ARP functionality to the controller. The emulation results showed that the proposed mechanism is robust against ARP spoofing attack and successfully prevented ARP broadcast messages in large networks and improved the response time by centrally responding to ARP requests.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115484744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142119
B. H. Mahdi, K. Yousif, Luqman MS. Dosky
The amount of solar radiation received at the Earth’s surface is influenced by local weather conditions. This paper investigates the effects of meteorological parameters on daily average solar radiation (DASR) in Duhok city, Iraq. Artificial Neural Networks (ANNs) based on multilayer preceptor feed-forward (MLP-FF) techniques are used to predict daily average solar radiation (DASR). The input variables used are a daily average of the relative humidity (RH), minimum temperature (Tmin), maximum temperature (Tmax), wind speed (WS), cloud layer (CL), atmospheric pressure (AP) and ultraviolet (UV) levels to estimate DASR. To identify and evaluate the effects of various input parameters on solar radiation, eight ANN-based models have been developed. To obtain the best estimation results, the number of neurons in the hidden layer has been varied. The best values of the Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and correlation coefficient (R) have been calculated. For some models, the results obtained show good and better predictive accuracy than others. The present study indicates that various of the meteorological parameters can have a significant effect on the forecasting of solar radiation.
{"title":"Using Artificial Neural Networks to Predict Solar Radiation for Duhok City, Iraq","authors":"B. H. Mahdi, K. Yousif, Luqman MS. Dosky","doi":"10.1109/CSASE48920.2020.9142119","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142119","url":null,"abstract":"The amount of solar radiation received at the Earth’s surface is influenced by local weather conditions. This paper investigates the effects of meteorological parameters on daily average solar radiation (DASR) in Duhok city, Iraq. Artificial Neural Networks (ANNs) based on multilayer preceptor feed-forward (MLP-FF) techniques are used to predict daily average solar radiation (DASR). The input variables used are a daily average of the relative humidity (RH), minimum temperature (Tmin), maximum temperature (Tmax), wind speed (WS), cloud layer (CL), atmospheric pressure (AP) and ultraviolet (UV) levels to estimate DASR. To identify and evaluate the effects of various input parameters on solar radiation, eight ANN-based models have been developed. To obtain the best estimation results, the number of neurons in the hidden layer has been varied. The best values of the Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and correlation coefficient (R) have been calculated. For some models, the results obtained show good and better predictive accuracy than others. The present study indicates that various of the meteorological parameters can have a significant effect on the forecasting of solar radiation.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"187 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132329845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142123
Jwad Ali Ridha, J. H. Saud
Researchers have proposed several approaches to provide processing methodologies for iris images captured in unconstrained mediums to leverage the level of accuracy for iris recognition systems. Segmentation is the most critical stage which considered a challenging area to researchers. In this paper, we propose an iris segmentation approach to handle the problem of low contrast iris images, in which the iris boundary is undetected. It uses the pupil boundary to define a search space for automatically finding an appropriate threshold value to extract the iris region, and then uses the thresholded image to create binary edge map with strong iris edge. Circular Hough Transform (CHT) is adopted to localize pupil/iris boundaries, and Rubber Sheet Model (RSM) of lower half of iris is used in normalization stage to eliminate upper eyelashes and eyelid. Contrast-Limited Adaptive Histogram Equalization (CLAHE) technique is adopted to overcome the low contrast problem of iris image. Finally, a region of interest without the impact of lower eyelashes and eyelid is selected to obtain noise free iris template. The proposed approach is tested on CASIA Iris Image Dataset Version 2.0.
{"title":"Iris Segmentation Approach Based on Adaptive Threshold Value and Circular Hough Transform","authors":"Jwad Ali Ridha, J. H. Saud","doi":"10.1109/CSASE48920.2020.9142123","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142123","url":null,"abstract":"Researchers have proposed several approaches to provide processing methodologies for iris images captured in unconstrained mediums to leverage the level of accuracy for iris recognition systems. Segmentation is the most critical stage which considered a challenging area to researchers. In this paper, we propose an iris segmentation approach to handle the problem of low contrast iris images, in which the iris boundary is undetected. It uses the pupil boundary to define a search space for automatically finding an appropriate threshold value to extract the iris region, and then uses the thresholded image to create binary edge map with strong iris edge. Circular Hough Transform (CHT) is adopted to localize pupil/iris boundaries, and Rubber Sheet Model (RSM) of lower half of iris is used in normalization stage to eliminate upper eyelashes and eyelid. Contrast-Limited Adaptive Histogram Equalization (CLAHE) technique is adopted to overcome the low contrast problem of iris image. Finally, a region of interest without the impact of lower eyelashes and eyelid is selected to obtain noise free iris template. The proposed approach is tested on CASIA Iris Image Dataset Version 2.0.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131093720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.1109/CSASE48920.2020.9142091
Barwar Mela Ferzo, F. Mustafa
An image is often corrupted with noise throughout procurement, compression, transmission, storage and retrieval processes. These effects are leading to distortion and loss of image information. Image denoising used to eliminate the noise in order to reserve all the fine details in the image while retaining as much as possible the vital signal features. Wavelet denoising aims to remove the noise in the signal while maintaining the features of the signal, regardless of its frequency content. In this work, a new approach is introduced to denoising image that has been affected by Additive White Gaussian Noise (AWGN). The proposed system realized using Wiener filter before and after the wavelet transform. To remove noise from pixels in the wavelet domain, discrete wavelet transform (2D-DWT) is applied. Threshold techniques and Wiener filter have been used for denoising. Then, the 2DIDWT inverse discrete wavelet transform applied to remove noise and complete the denoising technique. Also, in this work, the image is denoised using the connotation of Wiener filtering and denoising method in the wavelet domain with multiresolution at three levels. The performance of the proposed methods has been measured by using the Peak Signal to Noise Ratio (PSNR). Experimental evaluation shows that the results of the proposed methods give an improvement with about 17.5% through the comparison with the results of the related works and the essence of images is improved in terms of noise-reducing better than using a wavelet transform or Wiener filter solo as well as edge preservation.
{"title":"Image Denoising in Wavelet Domain Based on Thresholding with Applying Wiener Filter","authors":"Barwar Mela Ferzo, F. Mustafa","doi":"10.1109/CSASE48920.2020.9142091","DOIUrl":"https://doi.org/10.1109/CSASE48920.2020.9142091","url":null,"abstract":"An image is often corrupted with noise throughout procurement, compression, transmission, storage and retrieval processes. These effects are leading to distortion and loss of image information. Image denoising used to eliminate the noise in order to reserve all the fine details in the image while retaining as much as possible the vital signal features. Wavelet denoising aims to remove the noise in the signal while maintaining the features of the signal, regardless of its frequency content. In this work, a new approach is introduced to denoising image that has been affected by Additive White Gaussian Noise (AWGN). The proposed system realized using Wiener filter before and after the wavelet transform. To remove noise from pixels in the wavelet domain, discrete wavelet transform (2D-DWT) is applied. Threshold techniques and Wiener filter have been used for denoising. Then, the 2DIDWT inverse discrete wavelet transform applied to remove noise and complete the denoising technique. Also, in this work, the image is denoised using the connotation of Wiener filtering and denoising method in the wavelet domain with multiresolution at three levels. The performance of the proposed methods has been measured by using the Peak Signal to Noise Ratio (PSNR). Experimental evaluation shows that the results of the proposed methods give an improvement with about 17.5% through the comparison with the results of the related works and the essence of images is improved in terms of noise-reducing better than using a wavelet transform or Wiener filter solo as well as edge preservation.","PeriodicalId":254581,"journal":{"name":"2020 International Conference on Computer Science and Software Engineering (CSASE)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128724651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：