Pub Date : 2023-10-18DOI: 10.1080/13682199.2023.2263278
Tong Shao Li, Wen Bang Sun, Xin Wei Bai, Di Wu, Zhen Hai Chen, Jia Yu Zhang
ABSTRACTFilter array multispectral cameras are influenced by imaging mechanism and process characteristics, spliced images have edge interference fringes and greyscale differences. Aiming at the problems of inconsistent greyscale of filter array multispectral camera, a new method of greyscale correction algorithm is proposed in this paper. First, the mechanism and adjustment principle of edge interference streaks and stripe greyscale difference are thoroughly analyzed; Second, the greyscale of interference area is adjusted by using greyscale of adjacent image non-interference area; Third, the greyscale of whole image is adjusted by using proportional relationship between the adjacent overlap area greyscale; Finally, sequence images are spliced to obtain single-band image with same greyscale. Theoretical analysis and experimental results show that this method can not only effectively solve the problem of inconsistent greyscale due to the influence of imaging mechanism and process characteristics, but also can maximally preserve spectral information characteristics in different wavelength bands.KEYWORDS: Filter arraymultispectral imagegreyscale correctionedge interference streakgreyscale differenceimage stitchingsingle bandgreyscale consistency Additional informationNotes on contributorsTong Shao LiTong Shao Li, born in 1998, male, Master's Degree. Research Interests: Digital Image Processing.Wen Bang SunWen Bang Sun, born in 1976, male, PhD Degree, associate professor. Research interests: digital image processing and information security theory.Xin Wei BaiXin Wei Bai, female. Research interests: digital image processing.Di WuDi Wu, female. Research interests: digital image processing.Zhen Hai ChenZhen Hai Chen, male. Research direction: digital image processing.Jia Yu ZhangJia Yu Zhang, male. Research interests: digital image processing.
{"title":"Greyscale correction algorithm of aerial filter array multispectral image","authors":"Tong Shao Li, Wen Bang Sun, Xin Wei Bai, Di Wu, Zhen Hai Chen, Jia Yu Zhang","doi":"10.1080/13682199.2023.2263278","DOIUrl":"https://doi.org/10.1080/13682199.2023.2263278","url":null,"abstract":"ABSTRACTFilter array multispectral cameras are influenced by imaging mechanism and process characteristics, spliced images have edge interference fringes and greyscale differences. Aiming at the problems of inconsistent greyscale of filter array multispectral camera, a new method of greyscale correction algorithm is proposed in this paper. First, the mechanism and adjustment principle of edge interference streaks and stripe greyscale difference are thoroughly analyzed; Second, the greyscale of interference area is adjusted by using greyscale of adjacent image non-interference area; Third, the greyscale of whole image is adjusted by using proportional relationship between the adjacent overlap area greyscale; Finally, sequence images are spliced to obtain single-band image with same greyscale. Theoretical analysis and experimental results show that this method can not only effectively solve the problem of inconsistent greyscale due to the influence of imaging mechanism and process characteristics, but also can maximally preserve spectral information characteristics in different wavelength bands.KEYWORDS: Filter arraymultispectral imagegreyscale correctionedge interference streakgreyscale differenceimage stitchingsingle bandgreyscale consistency Additional informationNotes on contributorsTong Shao LiTong Shao Li, born in 1998, male, Master's Degree. Research Interests: Digital Image Processing.Wen Bang SunWen Bang Sun, born in 1976, male, PhD Degree, associate professor. Research interests: digital image processing and information security theory.Xin Wei BaiXin Wei Bai, female. Research interests: digital image processing.Di WuDi Wu, female. Research interests: digital image processing.Zhen Hai ChenZhen Hai Chen, male. Research direction: digital image processing.Jia Yu ZhangJia Yu Zhang, male. Research interests: digital image processing.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135889762","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 : 2023-10-10DOI: 10.1080/13682199.2023.2266308
Libing Zhou, Xiaojing Chen, Baisong Ye, Xueli Jiang, Sheng Zou, Liang Ji, Zhengqian Yu, Jianjian Wei, Yexin Zhao, Tianyu Wang
ABSTRACTTo enhance the visual performance of low-illumination images, many low-illumination images are analyzed. Based on this, a low-light image enhancement method based on HSV space and semi-implicit ROF model is proposed. First, the low-illumination image is decomposed into HSV space for saturation denoising and brightness enhancement. Then, the Bayesian rules are applied to fuse the saturation and value. The three components in HSV space are converted to the RGB space and obtain a rough enhanced image. Finally, the semi-implicit ROF model is introduced to denoise the global noise and obtain the enhanced image. Such a comprehensive method can improve the low illumination image more clearly. The experimental results show that the algorithm has a PSNR score of 26.48, 6.29, 0.8947, and 28.4124, and the PSNR score is the highest in the comparison algorithm. The experiments on the Low-Light image data set also show that the proposed method can effectively improve the visibility of low-light images, and can provide a simple and effective method for low-light image enhancement.KEYWORDS: Image enhancementDeep learningHSV color spaceBayesian ruleROFGaussian noiseStructure SimilarityPeak Signal Noise Ratio Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsLibing ZhouLibing Zhou received master's degree from Hefei University of Technology, Hefei, China. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include mine electromechanical system intelligent, intelligent detection and control.Xiaojing ChenXiaojing Chen is an associate research fellow. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include coal mine industrial control, Internet of Things and intelligent technology.Baisong YeBaisong Ye received PhD degree from the University of Science and Technology of China, Hefei, China, in 2013. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests includecoal mine photoelectric detection system and intelligent application technology.Xueli JiangXueli Jiang received PhD degreefrom the University of Science and Technology of China, Hefei,China, in 2021. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research focuses on motor control.Sheng ZouZhengqian Yu received master's degree from the Stevens Institute of Technology, New Jersey,USA, in 2020. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include positioning, object detection and obstacle perception.Liang JiJianjian Wei received master's degree from Xi'an University of Science and Technology, Xi'an,China, in 2022. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include positioning, object detection.Zhengqian YuSheng Zou received master's degree from University of South China, Hengyang,China, in 2019. Now he works at Tiandi(Changzhou)
{"title":"A low-light image enhancement method based on HSV space","authors":"Libing Zhou, Xiaojing Chen, Baisong Ye, Xueli Jiang, Sheng Zou, Liang Ji, Zhengqian Yu, Jianjian Wei, Yexin Zhao, Tianyu Wang","doi":"10.1080/13682199.2023.2266308","DOIUrl":"https://doi.org/10.1080/13682199.2023.2266308","url":null,"abstract":"ABSTRACTTo enhance the visual performance of low-illumination images, many low-illumination images are analyzed. Based on this, a low-light image enhancement method based on HSV space and semi-implicit ROF model is proposed. First, the low-illumination image is decomposed into HSV space for saturation denoising and brightness enhancement. Then, the Bayesian rules are applied to fuse the saturation and value. The three components in HSV space are converted to the RGB space and obtain a rough enhanced image. Finally, the semi-implicit ROF model is introduced to denoise the global noise and obtain the enhanced image. Such a comprehensive method can improve the low illumination image more clearly. The experimental results show that the algorithm has a PSNR score of 26.48, 6.29, 0.8947, and 28.4124, and the PSNR score is the highest in the comparison algorithm. The experiments on the Low-Light image data set also show that the proposed method can effectively improve the visibility of low-light images, and can provide a simple and effective method for low-light image enhancement.KEYWORDS: Image enhancementDeep learningHSV color spaceBayesian ruleROFGaussian noiseStructure SimilarityPeak Signal Noise Ratio Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsLibing ZhouLibing Zhou received master's degree from Hefei University of Technology, Hefei, China. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include mine electromechanical system intelligent, intelligent detection and control.Xiaojing ChenXiaojing Chen is an associate research fellow. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include coal mine industrial control, Internet of Things and intelligent technology.Baisong YeBaisong Ye received PhD degree from the University of Science and Technology of China, Hefei, China, in 2013. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests includecoal mine photoelectric detection system and intelligent application technology.Xueli JiangXueli Jiang received PhD degreefrom the University of Science and Technology of China, Hefei,China, in 2021. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research focuses on motor control.Sheng ZouZhengqian Yu received master's degree from the Stevens Institute of Technology, New Jersey,USA, in 2020. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include positioning, object detection and obstacle perception.Liang JiJianjian Wei received master's degree from Xi'an University of Science and Technology, Xi'an,China, in 2022. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include positioning, object detection.Zhengqian YuSheng Zou received master's degree from University of South China, Hengyang,China, in 2019. Now he works at Tiandi(Changzhou)","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136296277","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 : 2023-10-05DOI: 10.1080/13682199.2023.2262259
S Abirami, B Lanitha
ABSTRACTBrain tumour is a dangerous disease and it harms health. This research develops a productive model to categorize brain tumours exploiting an Adam Bald Eagle optimization-based Shepard Convolutional Neural Network (ABEO-ShCNN). Initially, the preprocessing is done in pre- and post-operative Magnetic resonance imaging (MRI). Then, U-Net++ is exploited to segment, which is tuned by the Bald Border Collie Firefly Optimization Algorithm (BBCFO). The BBCFO is the incorporation of Border Collie Optimization (BCO), the Firefly optimization Algorithm (FA) and Bald Eagle Search (BES). Thereafter, feature extraction is done and then categorization is conducted using ShCNN in which the training is conducted by ABEO. The ABEO is the integration of Adam and BES. The ABEO-ShCNN model has acquired better accuracy, Positive Predictive Value (PPV), True Negative Rate (TNR), True Positive Rate (TPR) and Negative Predictive Value (NPV) for pre-operative MRI, with values of 92.70%, 92.90%, 91.30%, 89.60% and 89.50%, respectively.KEYWORDS: Shepard convolutional neural networkbald eagle search algorithmborder collie optimizationmagnetic resonance imagingfirefly optimization algorithmU-Net++Shepard Convolutional Neural Networkfeature extraction Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsS AbiramiMrs. Abirami S obtained her Bachelor and Master's degrees in computer science and engineering from Anna University, Chennai in 2005 and 2013, respectively. She has worked in various reputed engineering institutions and software industries in and around India. Currently, she is working as an assistant professor in the department of computer science and engineering at Sri Krishna College of Engineering and Technology in Coimbatore, Tamilnadu, India. Her area of interest is Machine Learning and Deep learning.B LanithaDr. Lanitha B received her Bachelor and Master's degrees in computer science and engineering from Bharathiyar University and Karpagam University in 1989 and 1993, respectively. She earned her Ph.D. at Anna University in 2021. Currently, she is working as an associate professor at Karpagam Academy of Higher Education. She has worked in various reputed engineering institutions and software industries. She has published many papers in international journals and conferences.
{"title":"Adam bald eagle optimization-based Shepard CNN for classification and pixel change detection of brain tumour using post and pre-operative brain MRI images","authors":"S Abirami, B Lanitha","doi":"10.1080/13682199.2023.2262259","DOIUrl":"https://doi.org/10.1080/13682199.2023.2262259","url":null,"abstract":"ABSTRACTBrain tumour is a dangerous disease and it harms health. This research develops a productive model to categorize brain tumours exploiting an Adam Bald Eagle optimization-based Shepard Convolutional Neural Network (ABEO-ShCNN). Initially, the preprocessing is done in pre- and post-operative Magnetic resonance imaging (MRI). Then, U-Net++ is exploited to segment, which is tuned by the Bald Border Collie Firefly Optimization Algorithm (BBCFO). The BBCFO is the incorporation of Border Collie Optimization (BCO), the Firefly optimization Algorithm (FA) and Bald Eagle Search (BES). Thereafter, feature extraction is done and then categorization is conducted using ShCNN in which the training is conducted by ABEO. The ABEO is the integration of Adam and BES. The ABEO-ShCNN model has acquired better accuracy, Positive Predictive Value (PPV), True Negative Rate (TNR), True Positive Rate (TPR) and Negative Predictive Value (NPV) for pre-operative MRI, with values of 92.70%, 92.90%, 91.30%, 89.60% and 89.50%, respectively.KEYWORDS: Shepard convolutional neural networkbald eagle search algorithmborder collie optimizationmagnetic resonance imagingfirefly optimization algorithmU-Net++Shepard Convolutional Neural Networkfeature extraction Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsS AbiramiMrs. Abirami S obtained her Bachelor and Master's degrees in computer science and engineering from Anna University, Chennai in 2005 and 2013, respectively. She has worked in various reputed engineering institutions and software industries in and around India. Currently, she is working as an assistant professor in the department of computer science and engineering at Sri Krishna College of Engineering and Technology in Coimbatore, Tamilnadu, India. Her area of interest is Machine Learning and Deep learning.B LanithaDr. Lanitha B received her Bachelor and Master's degrees in computer science and engineering from Bharathiyar University and Karpagam University in 1989 and 1993, respectively. She earned her Ph.D. at Anna University in 2021. Currently, she is working as an associate professor at Karpagam Academy of Higher Education. She has worked in various reputed engineering institutions and software industries. She has published many papers in international journals and conferences.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135483945","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 : 2023-10-03DOI: 10.1080/13682199.2023.2257539
P. Gopinath, R. Shivakumar
ABSTRACTIn information and security, the personal identification of individuals becomes much more important. For improving security, several biometric recognition techniques are implemented. However, in finger vein recognition, it faces the critical problem of fake finger vein images, security and less accuracy. To conquer this problem, Hybrid Feature Extraction with Linear Local Tangent Space Alignment-based dimension reduction and Support Vector Machine classifier (HFE–LLTSA–SVM) is proposed. In this hybrid, FE is considered as the combination of histogram of oriented gradients (HOG), grey-level co-occurrence matrix (GLCM), stationary wavelet transform (SWT), and local binary pattern (LBP) for extracting the hybrid feature. LLTSA perform dimension reduction in the outputs of HFE from HOG, GLCM, and LBP. Furthermore, SVM is used for classification which gives authentication based on error-correcting code. Finally, the performance parameters were calculated and the proposed method achieved better accuracy of 99.75%, when compared with existing methods.KEYWORDS: Grey-level co-occurrence matrixhistogram of oriented gradientlocal binary patternstationary wavelet transformsupport vector machine Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsP. GopinathDr P. Gopinath is working as an Assistant Professor in the department of Electronics and Communication Engineering at Sengunthar Engineering College, Tiruchengode. He obtained his Ph. D in Digital Image Processing from Anna University Chennai in 2023. M.E. (Applied Electronics) from Anna University Chennai in 2011. B.E. (Electronics and Communication Engineering) from Anna University Chennai in 2008.He has a 13 years of teaching experience. His research interest includes Digital Image processing, Signal processing, Biometrics, Machine learning, and Artificial Intelligence. He has published more than 12 research article and 2 patent.R. ShivakumarDr R. Shivakumar is working as a Professor in Department of Electrical and Electronics Engineering at Sona College of Technology, Salem. He obtained his Ph. D in Electrical Engineering from Anna University Chennai in November 2012.M.E. (Power System Engg) -First class with Distinction in 1998 from Annamalai University, Chidambaram. B.E. (Electrical and Electronics Engineering) with I Class in 1997, from Shanmugha College of Engineering, Tanjore, Bharadhidasan University. His research interest includes Power System Stability and Control, Bio Inspired Optimization algorithms, Renewable energy conversion systems, and Digital Technology applications in Power Engineering. He has published more than 40 research article and 60 International and National Conference Papers. He won BEST RESEARCHER Award for academic contribution in Electrical and Electronics Engineering specialization under National Faculty Award 2021-2022 awarded by Novel Research Academy, Puducherry, India on 4.5.2022.
摘要在信息安全领域,个人身份识别变得越来越重要。为了提高安全性,采用了几种生物特征识别技术。然而,在手指静脉识别中,它面临着假手指静脉图像、安全性和准确性不高的关键问题。为了解决这一问题,提出了基于线性局部切线空间对齐的混合特征提取和支持向量机分类器(HFE-LLTSA-SVM)。在该混合特征中,FE被认为是结合定向梯度直方图(HOG)、灰度共生矩阵(GLCM)、平稳小波变换(SWT)和局部二值模式(LBP)来提取混合特征。LLTSA在HOG、GLCM和LBP的HFE输出中执行降维。在此基础上,采用支持向量机进行分类,基于纠错码进行认证。最后对性能参数进行了计算,与现有方法相比,该方法的准确率达到了99.75%。关键词:灰度共现矩阵定向梯度直方图局部二值模式平稳小波变换支持向量机披露声明作者未报告潜在利益冲突。附加信息:贡献者说明Gopinath博士是Tiruchengode Sengunthar工程学院电子与通信工程系的助理教授。他于2023年获得金奈安娜大学数字图像处理博士学位。2011年毕业于金奈安娜大学应用电子学硕士。2008年毕业于金奈安娜大学电子与通信工程学士学位。他有13年的教学经验。主要研究方向为数字图像处理、信号处理、生物识别、机器学习、人工智能等。发表学术论文12篇,专利2项。R. Shivakumar博士是塞勒姆Sona理工学院电气和电子工程系的教授。他于2012年11月获得Anna University Chennai电气工程博士学位。(电力系统工程)- 1998年毕业于印度奇丹巴拉姆的安纳玛莱大学,获一等优异成绩。1997年毕业于印度Bharadhidasan大学Shanmugha工程学院,获电气与电子工程学士学位。主要研究方向为电力系统稳定性与控制、生物优化算法、可再生能源转换系统、数字技术在电力工程中的应用。发表研究论文40余篇,国际国内会议论文60余篇。他于2022年5月4日获得了由印度普杜切里新颖研究学院颁发的2021-2022年国家教师奖的电气和电子工程专业学术贡献奖。
{"title":"Hybrid feature extraction and LLTSA-based dimension reduction for vein pattern recognition","authors":"P. Gopinath, R. Shivakumar","doi":"10.1080/13682199.2023.2257539","DOIUrl":"https://doi.org/10.1080/13682199.2023.2257539","url":null,"abstract":"ABSTRACTIn information and security, the personal identification of individuals becomes much more important. For improving security, several biometric recognition techniques are implemented. However, in finger vein recognition, it faces the critical problem of fake finger vein images, security and less accuracy. To conquer this problem, Hybrid Feature Extraction with Linear Local Tangent Space Alignment-based dimension reduction and Support Vector Machine classifier (HFE–LLTSA–SVM) is proposed. In this hybrid, FE is considered as the combination of histogram of oriented gradients (HOG), grey-level co-occurrence matrix (GLCM), stationary wavelet transform (SWT), and local binary pattern (LBP) for extracting the hybrid feature. LLTSA perform dimension reduction in the outputs of HFE from HOG, GLCM, and LBP. Furthermore, SVM is used for classification which gives authentication based on error-correcting code. Finally, the performance parameters were calculated and the proposed method achieved better accuracy of 99.75%, when compared with existing methods.KEYWORDS: Grey-level co-occurrence matrixhistogram of oriented gradientlocal binary patternstationary wavelet transformsupport vector machine Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsP. GopinathDr P. Gopinath is working as an Assistant Professor in the department of Electronics and Communication Engineering at Sengunthar Engineering College, Tiruchengode. He obtained his Ph. D in Digital Image Processing from Anna University Chennai in 2023. M.E. (Applied Electronics) from Anna University Chennai in 2011. B.E. (Electronics and Communication Engineering) from Anna University Chennai in 2008.He has a 13 years of teaching experience. His research interest includes Digital Image processing, Signal processing, Biometrics, Machine learning, and Artificial Intelligence. He has published more than 12 research article and 2 patent.R. ShivakumarDr R. Shivakumar is working as a Professor in Department of Electrical and Electronics Engineering at Sona College of Technology, Salem. He obtained his Ph. D in Electrical Engineering from Anna University Chennai in November 2012.M.E. (Power System Engg) -First class with Distinction in 1998 from Annamalai University, Chidambaram. B.E. (Electrical and Electronics Engineering) with I Class in 1997, from Shanmugha College of Engineering, Tanjore, Bharadhidasan University. His research interest includes Power System Stability and Control, Bio Inspired Optimization algorithms, Renewable energy conversion systems, and Digital Technology applications in Power Engineering. He has published more than 40 research article and 60 International and National Conference Papers. He won BEST RESEARCHER Award for academic contribution in Electrical and Electronics Engineering specialization under National Faculty Award 2021-2022 awarded by Novel Research Academy, Puducherry, India on 4.5.2022.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135740530","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 : 2023-09-24DOI: 10.1080/13682199.2023.2260663
G. R. Vishalakshi, A. Shobharani, M. C. Hanumantharaju
ABSTRACTOur paper presents an adaptive multiscale retinex algorithm and a new wavelet energy metric to improve low-light video captured on mobile devices. Initially, we extract RGB frames from the video and convert them to hue-saturation-value (HSV) format, preserving the hue channel to prevent common RGB colour shifting issues. Saturation channel enhancement is achieved through histogram equalization (HE), extending the dynamic range. The adaptive retinex algorithm enhances the value channel, quantified by our new wavelet energy metric. Combining the modified value and saturation channels improves the contrast of the reconstructed image. As a final step, we transform the HSV video back to RGB and restore naturalness using a modified colour restoration technique. The proposed approach has been tested on over 300 images and videos. It is evident from the experimental results presented that the proposed method lowers noise and halo artifacts more effectively than existing methods.KEYWORDS: Low light enhancementmobile videoHSV colour spaceadaptive multiscale retinexwavelet energy Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsG. R. VishalakshiVishalakshi G. R. completed a Bachelor of Engineering (B. E) in Electronics and Communication and a Masters of Technology (M. Tech) in Digital Electronics from Visvesvaraya Technological University (VTU), Belagavi, Karnataka, India, in the years 2005 and 2012, respectively and Pursuing Ph.D. in VTU under the guidance of A. Shobharani on video enhancement technique. Her research interest is in subjects like image and video processing, VLSI, and CNN.A. ShobharaniA. Shobha Rani received her B. E (Electronics and Communication Engineering) degree from Bangalore University in the year 2000, M. Tech (Digital Electronics and Communication) Degree from Visveswaraya Technological University (VTU), Belgaum in the year 2005, and Ph. D. (Networking) degree from Kuvempu University, Shimoga, in the year, 2014. She works as an Associate Professor in the Department of ECE at BMS Institute of Technology and Management, Bengaluru, India. She has 23 technical articles in well-reputed journals and conferences. Her research interests include designing and implementing efficient protocols for wireless networks such as Ad hoc, Sensor, and Mesh networks.M. C. HanumantharajuM. C. Hanumantharaju received his B. E (Electronics and Communication Engineering) degree from Bangalore University in the year 2001, M. Tech (Digital Communication and Network Engineering) degree from Visvesvaraya Technological University (VTU), Belagavi in the year 2004, and Ph. D (VLSI Signal and Image Processing) degree from VTU, Belagavi, in the year, 2014. He works as a Professor in the Department of ECE at BMS Institute of Technology and Management, Bengaluru, India. He has authored two books and 50 technical articles in refereed journals and proceedings such as IEEE, Intelligent
摘要:本文提出了一种自适应多尺度retinex算法和一种新的小波能量度量来改善移动设备上低光视频的捕获。最初,我们从视频中提取RGB帧并将其转换为色调饱和值(HSV)格式,保留色调通道以防止常见的RGB颜色移动问题。饱和通道增强是通过直方图均衡化(HE)实现的,扩展了动态范围。自适应retinex算法增强了价值通道,并通过我们的新小波能量度量进行量化。将修正值与饱和通道相结合,提高了重建图像的对比度。作为最后一步,我们将HSV视频转换回RGB,并使用修改的颜色恢复技术恢复自然性。该方法已经在300多张图片和视频上进行了测试。实验结果表明,该方法比现有方法更有效地降低了噪声和光晕伪影。关键词:弱光增强移动视频hsv色彩空间自适应多尺度视网膜小波能量披露声明作者未报告潜在利益冲突。其他资料:捐助者说明R. VishalakshiVishalakshi G. R.分别于2005年和2012年在印度卡纳塔克邦Belagavi的Visvesvaraya Technological University (VTU)获得电子与通信工程学士学位和数字电子学硕士学位,并在a . Shobharani的视频增强技术指导下在VTU攻读博士学位。她的研究兴趣包括图像和视频处理、VLSI和cnn。ShobharaniA。Shobha Rani于2000年在班加罗尔大学获得电子与通信工程学士学位,2005年在Belgaum Visveswaraya理工大学获得数字电子与通信硕士学位,并于2014年在Shimoga Kuvempu大学获得网络博士学位。她是印度班加罗尔BMS技术与管理学院ECE系的副教授。她在知名期刊和会议上发表了23篇技术文章。她的研究兴趣包括设计和实现无线网络的高效协议,如Ad hoc,传感器和Mesh网络。c . HanumantharajuM。C. Hanumantharaju于2001年获得班加罗尔大学(Bangalore University)电子与通信工程学士学位,2004年获得Visvesvaraya Technological University (VTU)数字通信与网络工程硕士学位,2014年获得VTU Belagavi超大集成电路信号与图像处理博士学位。他是印度班加罗尔BMS技术与管理学院ECE系教授。他撰写了两本书,并在IEEE,智能系统,粒子群优化等期刊和会议上发表了50篇技术文章。他目前是IEEE Transactions on Industrial Electronics, Computers and Electrical Engineering Journal, Journal of Microscopy and Ultrastructure等杂志的审稿人。他的研究兴趣包括信号和图像处理算法的硬件架构设计,计算机视觉,寄存器传输电平(RTL) Verilog编码,集成电路(ic)的合成和优化,以及FPGA/ASIC设计。
{"title":"Wavelet energy-based adaptive retinex algorithm for low light mobile video enhancement","authors":"G. R. Vishalakshi, A. Shobharani, M. C. Hanumantharaju","doi":"10.1080/13682199.2023.2260663","DOIUrl":"https://doi.org/10.1080/13682199.2023.2260663","url":null,"abstract":"ABSTRACTOur paper presents an adaptive multiscale retinex algorithm and a new wavelet energy metric to improve low-light video captured on mobile devices. Initially, we extract RGB frames from the video and convert them to hue-saturation-value (HSV) format, preserving the hue channel to prevent common RGB colour shifting issues. Saturation channel enhancement is achieved through histogram equalization (HE), extending the dynamic range. The adaptive retinex algorithm enhances the value channel, quantified by our new wavelet energy metric. Combining the modified value and saturation channels improves the contrast of the reconstructed image. As a final step, we transform the HSV video back to RGB and restore naturalness using a modified colour restoration technique. The proposed approach has been tested on over 300 images and videos. It is evident from the experimental results presented that the proposed method lowers noise and halo artifacts more effectively than existing methods.KEYWORDS: Low light enhancementmobile videoHSV colour spaceadaptive multiscale retinexwavelet energy Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsG. R. VishalakshiVishalakshi G. R. completed a Bachelor of Engineering (B. E) in Electronics and Communication and a Masters of Technology (M. Tech) in Digital Electronics from Visvesvaraya Technological University (VTU), Belagavi, Karnataka, India, in the years 2005 and 2012, respectively and Pursuing Ph.D. in VTU under the guidance of A. Shobharani on video enhancement technique. Her research interest is in subjects like image and video processing, VLSI, and CNN.A. ShobharaniA. Shobha Rani received her B. E (Electronics and Communication Engineering) degree from Bangalore University in the year 2000, M. Tech (Digital Electronics and Communication) Degree from Visveswaraya Technological University (VTU), Belgaum in the year 2005, and Ph. D. (Networking) degree from Kuvempu University, Shimoga, in the year, 2014. She works as an Associate Professor in the Department of ECE at BMS Institute of Technology and Management, Bengaluru, India. She has 23 technical articles in well-reputed journals and conferences. Her research interests include designing and implementing efficient protocols for wireless networks such as Ad hoc, Sensor, and Mesh networks.M. C. HanumantharajuM. C. Hanumantharaju received his B. E (Electronics and Communication Engineering) degree from Bangalore University in the year 2001, M. Tech (Digital Communication and Network Engineering) degree from Visvesvaraya Technological University (VTU), Belagavi in the year 2004, and Ph. D (VLSI Signal and Image Processing) degree from VTU, Belagavi, in the year, 2014. He works as a Professor in the Department of ECE at BMS Institute of Technology and Management, Bengaluru, India. He has authored two books and 50 technical articles in refereed journals and proceedings such as IEEE, Intelligent ","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135926188","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 : 2023-09-22DOI: 10.1080/13682199.2023.2254134
Tejaswini Yadav, Rajneeshkaur Sachdeo
ABSTRACTThe main challenge is to automate the model for aged or de-aged face generation. However, there are certain limitations on accuracy for age estimation and identity preservation. To achieve this, a new face age progression and regression is proposed by Hyper-parameter Tuning-Large Scale Generative Adversarial Network (HT-Large Scale GAN) with Pollination Rate-based Sunflower Dolphin Swarm Optimization (PR-SDSO). The input images are collected and fed into the object detection model, where the viola Jones algorithm is utilized. Here, the pre-processing is done by median filtering and contrast enhancement. The face age progression and regression are accomplished by novel HT-Large Scale GAN, where the hyperparameters are optimized by a new algorithm of PR-SDSO. Throughout the result analysis, the proposed model ensures that it provides the appropriate synthesized images for both the progression and regression phases and acquires less error to improve the quality of the image.KEYWORDS: Face age progression and regressionobject detection modelviola-jones algorithmmedian filtering and contrast enhancementdeep learningdolphin swarm algorithmpollination rate-based sunflower dolphin swarm optimizationhyper-parameter tuning-large scale generative adversarial networks Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsTejaswini YadavTejaswini Yadav received master degree from Pune University. She is currently research scholar in MIT-ADT University and her research area includes machine learning and artificial intelligence.Rajneeshkaur SachdeoRajneeshkaur Sachdeo received Ph.D. degree from SGBAU State University, Amravati. She is currently Dean of Engineering and Head of Computer Science and Engineering at MIT-ADT University, Pune. Her research area includes Data Security and privacy, natural language processing and linguistics, machine learning, data mining, and Wireless network. She is a member of ISTE, IACSIT and CSI.
{"title":"Enhanced face age progression and regression model using hyper-parameter tuning-large scale GAN by hybrid heuristic improvement","authors":"Tejaswini Yadav, Rajneeshkaur Sachdeo","doi":"10.1080/13682199.2023.2254134","DOIUrl":"https://doi.org/10.1080/13682199.2023.2254134","url":null,"abstract":"ABSTRACTThe main challenge is to automate the model for aged or de-aged face generation. However, there are certain limitations on accuracy for age estimation and identity preservation. To achieve this, a new face age progression and regression is proposed by Hyper-parameter Tuning-Large Scale Generative Adversarial Network (HT-Large Scale GAN) with Pollination Rate-based Sunflower Dolphin Swarm Optimization (PR-SDSO). The input images are collected and fed into the object detection model, where the viola Jones algorithm is utilized. Here, the pre-processing is done by median filtering and contrast enhancement. The face age progression and regression are accomplished by novel HT-Large Scale GAN, where the hyperparameters are optimized by a new algorithm of PR-SDSO. Throughout the result analysis, the proposed model ensures that it provides the appropriate synthesized images for both the progression and regression phases and acquires less error to improve the quality of the image.KEYWORDS: Face age progression and regressionobject detection modelviola-jones algorithmmedian filtering and contrast enhancementdeep learningdolphin swarm algorithmpollination rate-based sunflower dolphin swarm optimizationhyper-parameter tuning-large scale generative adversarial networks Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsTejaswini YadavTejaswini Yadav received master degree from Pune University. She is currently research scholar in MIT-ADT University and her research area includes machine learning and artificial intelligence.Rajneeshkaur SachdeoRajneeshkaur Sachdeo received Ph.D. degree from SGBAU State University, Amravati. She is currently Dean of Engineering and Head of Computer Science and Engineering at MIT-ADT University, Pune. Her research area includes Data Security and privacy, natural language processing and linguistics, machine learning, data mining, and Wireless network. She is a member of ISTE, IACSIT and CSI.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136060649","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 : 2023-09-20DOI: 10.1080/13682199.2023.2248576
C. Anitha Mary, A. Boyed Wesley
ABSTRACTThis paper presents an image demosaicing based on an optimization-driven deep learning model, namely the Autoregressive Water Wave Optimization algorithm (Autoregressive-WWO). The proposed method is devised by assimilating the Wave Optimization algorithm (WWO), and the Conditional autoregressive value at risk (CAViaR) model. Here, the input images are subjected to Autoregressive WWO-based local polynomial approximation and intersection of confidence intervals (LPA-ICI) filter, and Deep Convolution neural network (Deep CNN) in a concurrent manner. The filter coefficients are obtained from the proposed Autoregressive WWO-based LPA-ICI filter and the residual image is obtained from Deep CNN. In order to create the demosaiced image, these two outputs are combined using an entropy measure. The proposed method offered superior performance with the highest Peak signal to noise ratio (PSNR) of 40.049dB, the highest Second derivative measure of enhancement (SDME) of 50.168dB, and highest Structural Index Similarity (SSIM) of 0.9056.KEYWORDS: Image demosaicingentropycolour filter arraydeep convolution neural networkfusion processLPA-ICI filterWWOCAViaR AcknowledgementsI would like to convey my sincere gratitude to the co-authors of this publication for their insightful advice and support throughout the conception and planning of this research project. All authors have made substantial contributions to conception and design, revising the manuscript, and the final approval of the version to be published. Also, all authors agreed to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementMultispectral Image Database: Stuff, ‘https://www.cs.columbia.edu/CAVE/databases/multispectral/stuff/’ Accessed on April 2021.
{"title":"Optimization assisted autoregressive technique with deep convolution neural network-based entropy filter for image demosaicing","authors":"C. Anitha Mary, A. Boyed Wesley","doi":"10.1080/13682199.2023.2248576","DOIUrl":"https://doi.org/10.1080/13682199.2023.2248576","url":null,"abstract":"ABSTRACTThis paper presents an image demosaicing based on an optimization-driven deep learning model, namely the Autoregressive Water Wave Optimization algorithm (Autoregressive-WWO). The proposed method is devised by assimilating the Wave Optimization algorithm (WWO), and the Conditional autoregressive value at risk (CAViaR) model. Here, the input images are subjected to Autoregressive WWO-based local polynomial approximation and intersection of confidence intervals (LPA-ICI) filter, and Deep Convolution neural network (Deep CNN) in a concurrent manner. The filter coefficients are obtained from the proposed Autoregressive WWO-based LPA-ICI filter and the residual image is obtained from Deep CNN. In order to create the demosaiced image, these two outputs are combined using an entropy measure. The proposed method offered superior performance with the highest Peak signal to noise ratio (PSNR) of 40.049dB, the highest Second derivative measure of enhancement (SDME) of 50.168dB, and highest Structural Index Similarity (SSIM) of 0.9056.KEYWORDS: Image demosaicingentropycolour filter arraydeep convolution neural networkfusion processLPA-ICI filterWWOCAViaR AcknowledgementsI would like to convey my sincere gratitude to the co-authors of this publication for their insightful advice and support throughout the conception and planning of this research project. All authors have made substantial contributions to conception and design, revising the manuscript, and the final approval of the version to be published. Also, all authors agreed to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementMultispectral Image Database: Stuff, ‘https://www.cs.columbia.edu/CAVE/databases/multispectral/stuff/’ Accessed on April 2021.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136315342","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 : 2023-09-13DOI: 10.1080/13682199.2023.2255335
Poorni Ramakrishnan, P. Madhavan
The anomaly or abnormality detection in crowded scenes helps in identifying the violence and protecting the people from severe damage. Thus, there is a need to detect the anomalies with the classifier for learning information along with the usage of huge architectures. A new anomaly detection model is implemented in this model. The collected data is fed to optimal ensemble pattern extraction scheme through techniques like Local binary patterns (LBP), Local Gradient Pattern (LGP), and Local Tetra Pattern (LTrP). The weights are tuned by a new hybrid Spiral Search-based Black Widow Glowworm Swarm Optimization (SS-BWGSO) for getting the optimal ensemble patterns. Next, anomaly frame classification is carried out by optimized VGG16+ResNet technique, where the hyperparameters of VGG16 and ResNet are tuned by SS-BWGSO algorithm. Finally, anomaly detection is performed by the YOLOV3 classifier. Throughout the result analysis the higher performance of the designed technique is observed over the classical methods.
{"title":"An implementation of intelligent YOLOv3-based anomaly detection model from crowded video scenarios with optimized ensemble pattern extraction","authors":"Poorni Ramakrishnan, P. Madhavan","doi":"10.1080/13682199.2023.2255335","DOIUrl":"https://doi.org/10.1080/13682199.2023.2255335","url":null,"abstract":"The anomaly or abnormality detection in crowded scenes helps in identifying the violence and protecting the people from severe damage. Thus, there is a need to detect the anomalies with the classifier for learning information along with the usage of huge architectures. A new anomaly detection model is implemented in this model. The collected data is fed to optimal ensemble pattern extraction scheme through techniques like Local binary patterns (LBP), Local Gradient Pattern (LGP), and Local Tetra Pattern (LTrP). The weights are tuned by a new hybrid Spiral Search-based Black Widow Glowworm Swarm Optimization (SS-BWGSO) for getting the optimal ensemble patterns. Next, anomaly frame classification is carried out by optimized VGG16+ResNet technique, where the hyperparameters of VGG16 and ResNet are tuned by SS-BWGSO algorithm. Finally, anomaly detection is performed by the YOLOV3 classifier. Throughout the result analysis the higher performance of the designed technique is observed over the classical methods.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135740744","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}
Brain structure segmentation in 3D Magnetic Resonance Images is crucial for understanding neurodegenerative disorders. Manual segmentation is error-prone, necessitating robust automated techniques. In this paper, we introduce a novel and robust approach for the simultaneous segmentation of multiple brain structures in MRI images. Our method involves the concurrent evolution of 3D surfaces toward predefined anatomical targets, employing an efficient multi-object generalized fast marching method (MOGFMM) for simultaneous object detection. Additionally, we propose an effective evolution function that integrates prior knowledge from anatomical and probabilistic atlases, as well as spatial relationships among the segmented structures. Each deformable surface corresponds to a specific structure. To validate our approach, we conducted experiments on a dataset of real brain images (IBSR) and compared the results with several state-of-the-art methods. The obtained results were promising, demonstrating the effectiveness and superiority of our developed method.
{"title":"Multi-object 3D segmentation of brain structures using a geometric deformable model with a priori knowledge","authors":"Mohamed Baghdadi, Nacéra Benamrane, Mounir Boukadoum, Lakhdar Sais","doi":"10.1080/13682199.2023.2256504","DOIUrl":"https://doi.org/10.1080/13682199.2023.2256504","url":null,"abstract":"Brain structure segmentation in 3D Magnetic Resonance Images is crucial for understanding neurodegenerative disorders. Manual segmentation is error-prone, necessitating robust automated techniques. In this paper, we introduce a novel and robust approach for the simultaneous segmentation of multiple brain structures in MRI images. Our method involves the concurrent evolution of 3D surfaces toward predefined anatomical targets, employing an efficient multi-object generalized fast marching method (MOGFMM) for simultaneous object detection. Additionally, we propose an effective evolution function that integrates prior knowledge from anatomical and probabilistic atlases, as well as spatial relationships among the segmented structures. Each deformable surface corresponds to a specific structure. To validate our approach, we conducted experiments on a dataset of real brain images (IBSR) and compared the results with several state-of-the-art methods. The obtained results were promising, demonstrating the effectiveness and superiority of our developed method.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135938328","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}