Pub Date : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965622
Yi Zhang, Guangtao Zhai, Jing Liu, Xinlin Weng, Yuanchun Chen
This paper introduces a new information display system that can prevent the on-screen contents from being taken by cameras or camcorders without sacrificing visual qualities. The system is designed based on the idea of temporal psychovisual modulation (TPVM) with guidance from the concept of ‘window of visibility (WoV)’. TPVM utilizes the redundancy (in terms of spatiotemporal resolutions and etc.) of modern display devices over those perception limits of the human visual system (HVS). The WoV theory asserts that the perceivable spatiotemporal frequency of the HVS is different from that of those cameras. Therefore, using a properly measured or estimated WoV we can determine how to select or design the display devices and contents to achieve the goal of security protection, i.e. preventing on-screen contents from being recorded by imaging devices, while not affecting the pictorial quality. We have built a prototype of WoV inspired TPVM security display system.
{"title":"‘Window of visibility’ inspired security lighting system","authors":"Yi Zhang, Guangtao Zhai, Jing Liu, Xinlin Weng, Yuanchun Chen","doi":"10.1109/IWSSIP.2017.7965622","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965622","url":null,"abstract":"This paper introduces a new information display system that can prevent the on-screen contents from being taken by cameras or camcorders without sacrificing visual qualities. The system is designed based on the idea of temporal psychovisual modulation (TPVM) with guidance from the concept of ‘window of visibility (WoV)’. TPVM utilizes the redundancy (in terms of spatiotemporal resolutions and etc.) of modern display devices over those perception limits of the human visual system (HVS). The WoV theory asserts that the perceivable spatiotemporal frequency of the HVS is different from that of those cameras. Therefore, using a properly measured or estimated WoV we can determine how to select or design the display devices and contents to achieve the goal of security protection, i.e. preventing on-screen contents from being recorded by imaging devices, while not affecting the pictorial quality. We have built a prototype of WoV inspired TPVM security display system.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115496185","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965580
P. Biernacki
The article proposes the use of a downsampling process, and a parametric spectral estimation method to determine the velocity of the liquid in the pipe. The estimation is based on measuring the Doppler shift amount derived by the reflection of the transmitted sine wave by moving air bubbles in the liquid. The simulation results for plastic and steel pipes show that it is possible to accurately measure liquid flow without the installation of sensors inside the tube.
{"title":"Doppler measurement of liquid flow in pipe using decimation and parametric spectral estimation method","authors":"P. Biernacki","doi":"10.1109/IWSSIP.2017.7965580","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965580","url":null,"abstract":"The article proposes the use of a downsampling process, and a parametric spectral estimation method to determine the velocity of the liquid in the pipe. The estimation is based on measuring the Doppler shift amount derived by the reflection of the transmitted sine wave by moving air bubbles in the liquid. The simulation results for plastic and steel pipes show that it is possible to accurately measure liquid flow without the installation of sensors inside the tube.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126657454","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965598
A. Dziembowski, Adam Grzelka, Dawid Mieloch, O. Stankiewicz, M. Domański
In the paper we present a method for increasing the quality of views synthesized with typical Depth-Image-Based Rendering (DIBR) view synthesis algorithms. In the proposed idea the resolution of input real views and corresponding depth maps is doubled before the view synthesis. After the synthesis, the resolution of a synthesized view is downsampled back to the original resolution. This approach is transparent for the view synthesis algorithms, thus can be used with any DIBR method. In the paper, tests for two synthesis algorithms (the state-of-the-art MPEG reference software and our view synthesis method) are presented. For both algorithms, the proposed upsampling improves objective and subjective quality of synthesized views.
本文提出了一种提高基于深度图像渲染(deep - image - based Rendering, DIBR)视图合成算法合成的视图质量的方法。该方法在视图合成前将输入的真实视图和相应深度图的分辨率提高了一倍。在合成之后，合成视图的分辨率被降采样回原始分辨率。这种方法对于视图合成算法是透明的，因此可以与任何DIBR方法一起使用。本文介绍了两种合成算法(最先进的MPEG参考软件和我们的视图合成方法)的测试。对于这两种算法，所提出的上采样提高了合成视图的客观和主观质量。
{"title":"Enhancing view synthesis with image and depth map upsampling","authors":"A. Dziembowski, Adam Grzelka, Dawid Mieloch, O. Stankiewicz, M. Domański","doi":"10.1109/IWSSIP.2017.7965598","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965598","url":null,"abstract":"In the paper we present a method for increasing the quality of views synthesized with typical Depth-Image-Based Rendering (DIBR) view synthesis algorithms. In the proposed idea the resolution of input real views and corresponding depth maps is doubled before the view synthesis. After the synthesis, the resolution of a synthesized view is downsampled back to the original resolution. This approach is transparent for the view synthesis algorithms, thus can be used with any DIBR method. In the paper, tests for two synthesis algorithms (the state-of-the-art MPEG reference software and our view synthesis method) are presented. For both algorithms, the proposed upsampling improves objective and subjective quality of synthesized views.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126460827","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965573
O. Lézoray
The extension of mathematical morphology to multivariate data has been an active research topic in recent years. In this paper we propose an approach that relies on the consensus combination of several stochastic permutation orderings. The latter are obtained by searching for a smooth shortest path on a graph representing an image. The construction of the graph can be based on both spatial and spectral information and naturally enables patch-based nonlocal processing.
{"title":"Stochastic spectral-spatial permutation ordering combination for nonlocal morphological processing","authors":"O. Lézoray","doi":"10.1109/IWSSIP.2017.7965573","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965573","url":null,"abstract":"The extension of mathematical morphology to multivariate data has been an active research topic in recent years. In this paper we propose an approach that relies on the consensus combination of several stochastic permutation orderings. The latter are obtained by searching for a smooth shortest path on a graph representing an image. The construction of the graph can be based on both spatial and spectral information and naturally enables patch-based nonlocal processing.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131284910","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965611
Robert Wielgat, Lukasz Mik, Anita Lorenc, Artur Truchan, Michal Szostek
Electromagnetic articulography (EMA) is a novel method of speech articulators assessment. By correlating signals from articulograph and video camera one can determine dependencies between internal and external speech articulators. This in turn is important for visual to articulatory speech inversion — the method allowing to estimate inner articulators movement without using aticulograph. This paper presents correlation analysis between video markers and EMA sensors placed on upper and lower lip. Optimal measurement conditions for calculating the correlation are also determined.
{"title":"Choice of optimal measurement conditions for calculating the correlation between EMA sensor and video marker position coordinates in electromagnetic articulography","authors":"Robert Wielgat, Lukasz Mik, Anita Lorenc, Artur Truchan, Michal Szostek","doi":"10.1109/IWSSIP.2017.7965611","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965611","url":null,"abstract":"Electromagnetic articulography (EMA) is a novel method of speech articulators assessment. By correlating signals from articulograph and video camera one can determine dependencies between internal and external speech articulators. This in turn is important for visual to articulatory speech inversion — the method allowing to estimate inner articulators movement without using aticulograph. This paper presents correlation analysis between video markers and EMA sensors placed on upper and lower lip. Optimal measurement conditions for calculating the correlation are also determined.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116634060","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965621
Hak-Yeol Choi, Han-Ul Jang, Dongkyu Kim, Jeongho Son, Seung-Min Mun, Sunghee Choi, Heung-Kyu Lee
In this paper, we propose a composite manipulation detection method based on convolutional neural networks (CNNs). To our best knowledge, this is the first work applying deep learning for composite forgery detection. The proposed technique defines three types of attacks that occurred frequently during image forging and detects when they are concurrently applied to images. To do this, we learn the statistical change due to the manipulation through the proposed CNN architecture and classify the manipulated image. The proposed technique is effective since it learns integrated image of composite manipulation and extracts characteristic distinguished from original image. Since most attacks are applied in a composite way in real environment, the approach of the proposed technique has practical advantages compared to traditional forensics scheme. In addition, the experimental results demonstrate the reliability of the proposed method through results of high performance.
{"title":"Detecting composite image manipulation based on deep neural networks","authors":"Hak-Yeol Choi, Han-Ul Jang, Dongkyu Kim, Jeongho Son, Seung-Min Mun, Sunghee Choi, Heung-Kyu Lee","doi":"10.1109/IWSSIP.2017.7965621","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965621","url":null,"abstract":"In this paper, we propose a composite manipulation detection method based on convolutional neural networks (CNNs). To our best knowledge, this is the first work applying deep learning for composite forgery detection. The proposed technique defines three types of attacks that occurred frequently during image forging and detects when they are concurrently applied to images. To do this, we learn the statistical change due to the manipulation through the proposed CNN architecture and classify the manipulated image. The proposed technique is effective since it learns integrated image of composite manipulation and extracts characteristic distinguished from original image. Since most attacks are applied in a composite way in real environment, the approach of the proposed technique has practical advantages compared to traditional forensics scheme. In addition, the experimental results demonstrate the reliability of the proposed method through results of high performance.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125237151","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965594
T. Kossowski, R. Stasinski
In the paper a spectroscopic multi-wavelength non-invasive measurement of substances levels in human body is analyzed. It is assumed that measurements can be done in any part of body. Three different techniques are compared: one using single wavelength of light, and two multi-wavelength ones: using two wavelength with and without additional data for white light. Concentration levels of two compounds are predicted: glucose and ethanol. Results are then interpolated by a fourth order polynomial equation. Two-wavelength analysis gives better results than that when only one wavelength is measured, but even better approach consists of result tuning using wide spectrum data.
{"title":"Multi-wavelength analysis of substances levels in human blood","authors":"T. Kossowski, R. Stasinski","doi":"10.1109/IWSSIP.2017.7965594","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965594","url":null,"abstract":"In the paper a spectroscopic multi-wavelength non-invasive measurement of substances levels in human body is analyzed. It is assumed that measurements can be done in any part of body. Three different techniques are compared: one using single wavelength of light, and two multi-wavelength ones: using two wavelength with and without additional data for white light. Concentration levels of two compounds are predicted: glucose and ethanol. Results are then interpolated by a fourth order polynomial equation. Two-wavelength analysis gives better results than that when only one wavelength is measured, but even better approach consists of result tuning using wide spectrum data.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124597488","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965577
Zhen Xu, Zongqing Lu, Weifeng Li, Q. Liao
Recently low-rank matrix decomposition (LR) and sparse representation classification (SRC) have been successfully applied to address the problem of face recognition. Low-rank matrix decomposition is employed as the first step of robust principal component analysis (RPCA), it is robust to illumination-contaminated image data. In this paper, we propose a novel method based on low-rank decomposition and sparse representation classification which is more robust to illumination-contaminated data. This method is a kind of test-data-drive illumination-robust face recognition. Our experimental results demonstrate the effectiveness of our proposed method.
{"title":"Removing contaminated data for illumination-robust face recognition","authors":"Zhen Xu, Zongqing Lu, Weifeng Li, Q. Liao","doi":"10.1109/IWSSIP.2017.7965577","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965577","url":null,"abstract":"Recently low-rank matrix decomposition (LR) and sparse representation classification (SRC) have been successfully applied to address the problem of face recognition. Low-rank matrix decomposition is employed as the first step of robust principal component analysis (RPCA), it is robust to illumination-contaminated image data. In this paper, we propose a novel method based on low-rank decomposition and sparse representation classification which is more robust to illumination-contaminated data. This method is a kind of test-data-drive illumination-robust face recognition. Our experimental results demonstrate the effectiveness of our proposed method.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121279337","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965603
Piotr Zasinski, M. Kociński, A. Materka
This paper explores the subject of extracting skeletons from 3D binary images. It draws attention to the flaws found in the available skeletonization implementations. The most popular algorithm devised by Lee, Kashyap and Chu is analyzed. It is shown that despite good results, some aspects of said algorithm can be further improved upon. An own implementation, with some modifications is made and compared against the existing ones.
{"title":"On extracting skeletons from binary 3D images","authors":"Piotr Zasinski, M. Kociński, A. Materka","doi":"10.1109/IWSSIP.2017.7965603","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965603","url":null,"abstract":"This paper explores the subject of extracting skeletons from 3D binary images. It draws attention to the flaws found in the available skeletonization implementations. The most popular algorithm devised by Lee, Kashyap and Chu is analyzed. It is shown that despite good results, some aspects of said algorithm can be further improved upon. An own implementation, with some modifications is made and compared against the existing ones.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127495539","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 : 2017-05-01DOI: 10.1109/IWSSIP.2017.7965596
S. Ubik, Z. Trávníček
Video walls are useful to display large visualizations. The SAGE2 web-based system allows easy programming of scalable visualization applications. However, it is not easy to stream high resolution video to SAGE2 powered video walls. We proposed several methods of high resolution video streaming to LCD walls, evaluated their performance and discuss their scalability and properties.
{"title":"Towards scalable streaming to SAGE2 video walls","authors":"S. Ubik, Z. Trávníček","doi":"10.1109/IWSSIP.2017.7965596","DOIUrl":"https://doi.org/10.1109/IWSSIP.2017.7965596","url":null,"abstract":"Video walls are useful to display large visualizations. The SAGE2 web-based system allows easy programming of scalable visualization applications. However, it is not easy to stream high resolution video to SAGE2 powered video walls. We proposed several methods of high resolution video streaming to LCD walls, evaluated their performance and discuss their scalability and properties.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121487982","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：