Pub Date : 2015-12-28DOI: 10.1109/SPA.2015.7365141
Paweł Karczmarek, Adam Kiersztyn, Przemyslaw Rutka, W. Pedrycz
People are highly efficient in recognizing faces. However, it is almost impossible for them to cope with huge datasets of facial images without any computational support. On the other hand, the way people describe the facial features using quite commonly encountered descriptors such as “long nose”, “small eyes” and also allude to their feelings according to a specific person like “seems to be nice”, may be utilized to enhance automatic face recognition systems. This offers an interesting possibility to incorporate human perception of faces and relations between facial features into machine-made computations. To address this aspect, one can engage the linguistic descriptors and the linguistic modeling. In this study, we present a comprehensive survey of the state-of-the-art studies and elaborate on some promising perspectives of the developments in this area.
{"title":"Linguistic descriptors in face recognition: A literature survey and the perspectives of future development","authors":"Paweł Karczmarek, Adam Kiersztyn, Przemyslaw Rutka, W. Pedrycz","doi":"10.1109/SPA.2015.7365141","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365141","url":null,"abstract":"People are highly efficient in recognizing faces. However, it is almost impossible for them to cope with huge datasets of facial images without any computational support. On the other hand, the way people describe the facial features using quite commonly encountered descriptors such as “long nose”, “small eyes” and also allude to their feelings according to a specific person like “seems to be nice”, may be utilized to enhance automatic face recognition systems. This offers an interesting possibility to incorporate human perception of faces and relations between facial features into machine-made computations. To address this aspect, one can engage the linguistic descriptors and the linguistic modeling. In this study, we present a comprehensive survey of the state-of-the-art studies and elaborate on some promising perspectives of the developments in this area.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131494683","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 : 2015-12-28DOI: 10.1109/SPA.2015.7365110
J. Blumenfeld, M. Kociński, A. Materka
Two approaches to Hessian-based estimation of tubular blood-vessel radius from 3D raster images are compared. In the proposed approach, binary skeleton is found for each tubular vessel-tree branch by thresholding the Hessian-derived vesselness image. Coordinates of the binary skeleton are approximated with smooth 3D spline functions. Their derivatives with respect to arc length give local tangent vectors, and thus planes normal to the vessel centerline. A proposed image intensity profile model is then least-squares fitted to the vessel cross-section by those planes, at each skeleton point. The circular vessel local radius is one of the model parameters. In the reference method, the vessel centerline direction is defined by the local Hessian eigenvector corresponding to the smallest eigenvalue. The radius is estimated using a square root of the vessel cross-section area (as obtained by an adaptive thresholding), divided by π. The impact of Frangi Hessian filter parameters and scale selection on the methods' performance is examined. Higher accuracy, precision and robustness to image noise and artifacts is demonstrated for the proposed method. Example of the method suitability for modeling of brain vasculature magnetic resonance images is also presented in this paper.
{"title":"A centerline-based algorithm for estimation of blood vessels radii from 3D raster images","authors":"J. Blumenfeld, M. Kociński, A. Materka","doi":"10.1109/SPA.2015.7365110","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365110","url":null,"abstract":"Two approaches to Hessian-based estimation of tubular blood-vessel radius from 3D raster images are compared. In the proposed approach, binary skeleton is found for each tubular vessel-tree branch by thresholding the Hessian-derived vesselness image. Coordinates of the binary skeleton are approximated with smooth 3D spline functions. Their derivatives with respect to arc length give local tangent vectors, and thus planes normal to the vessel centerline. A proposed image intensity profile model is then least-squares fitted to the vessel cross-section by those planes, at each skeleton point. The circular vessel local radius is one of the model parameters. In the reference method, the vessel centerline direction is defined by the local Hessian eigenvector corresponding to the smallest eigenvalue. The radius is estimated using a square root of the vessel cross-section area (as obtained by an adaptive thresholding), divided by π. The impact of Frangi Hessian filter parameters and scale selection on the methods' performance is examined. Higher accuracy, precision and robustness to image noise and artifacts is demonstrated for the proposed method. Example of the method suitability for modeling of brain vasculature magnetic resonance images is also presented in this paper.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128985543","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 : 2015-12-28DOI: 10.1109/SPA.2015.7365157
P. Pawlowski, Karol Piniarski, A. Dabrowski
This paper presents a test of pedestrian detection in low resolution night vision infrared images. An image feature extractor based on histograms of oriented gradients followed by a Support Vector Machine (SVM) classifier are evaluated, optimized and used. Tests performed on three different night vision infrared datasets show that the classification quality of the proposed method is very high even in very low resolutions of images. In practice, large frame size for analysis not always improves the classification effectiveness, but always requires more time for processing.
{"title":"Pedestrian detection in low resolution night vision images","authors":"P. Pawlowski, Karol Piniarski, A. Dabrowski","doi":"10.1109/SPA.2015.7365157","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365157","url":null,"abstract":"This paper presents a test of pedestrian detection in low resolution night vision infrared images. An image feature extractor based on histograms of oriented gradients followed by a Support Vector Machine (SVM) classifier are evaluated, optimized and used. Tests performed on three different night vision infrared datasets show that the classification quality of the proposed method is very high even in very low resolutions of images. In practice, large frame size for analysis not always improves the classification effectiveness, but always requires more time for processing.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128576083","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 : 2015-12-28DOI: 10.1109/SPA.2015.7365107
Nader Alexan, Hisham Othman, P. Montag
Software has become a part of almost every device around us, from mobile phones to medical systems; Failure within such devices can have fatal consequences. Thus, the need for eliminating these failures is inevitable. This study attempts to find a correlation - using Pearson and Spearman correlation coefficients - between code failures and software metrics with the goal of enhancing failure predictors. The results show statistically significant correlations between software metrics and code failures. This study is unique in testing certain combinations of metrics that are highly correlated with code failures.
{"title":"An enhancement of software metrics as failure predictors","authors":"Nader Alexan, Hisham Othman, P. Montag","doi":"10.1109/SPA.2015.7365107","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365107","url":null,"abstract":"Software has become a part of almost every device around us, from mobile phones to medical systems; Failure within such devices can have fatal consequences. Thus, the need for eliminating these failures is inevitable. This study attempts to find a correlation - using Pearson and Spearman correlation coefficients - between code failures and software metrics with the goal of enhancing failure predictors. The results show statistically significant correlations between software metrics and code failures. This study is unique in testing certain combinations of metrics that are highly correlated with code failures.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116963438","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 : 2015-09-01DOI: 10.1109/SPA.2015.7365134
M. Strąkowska, R. Strąkowski, M. Strzelecki
This paper presents the use of active thermography as the tool of medical imaging technique. The cold stress method is used to stimulate human skin and measure its temperature change in time. Image and data processing techniques are applied to calculate response parameters and plot theirs spatial distribution. The preliminary results are presented which reveal different vascularization under the skin.
{"title":"Thermal-time constant imaging in cold-stress screening","authors":"M. Strąkowska, R. Strąkowski, M. Strzelecki","doi":"10.1109/SPA.2015.7365134","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365134","url":null,"abstract":"This paper presents the use of active thermography as the tool of medical imaging technique. The cold stress method is used to stimulate human skin and measure its temperature change in time. Image and data processing techniques are applied to calculate response parameters and plot theirs spatial distribution. The preliminary results are presented which reveal different vascularization under the skin.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116185314","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 : 2015-09-01DOI: 10.1109/SPA.2015.7365146
Ireneusz Gawlik, Tomasz Pedzimaz, S. Palka, B. Ziółko
The Feedback Delay Network (FDN) is used as artificial digital reverberation algorithm. Being one of the most naturally sounding approaches it became widely implemented in many sound processing software products. Although FDN is a very potent tool in regards to artificial reverberation, achieving proper perceptual quality of acoustic simulation usually demands additional modifications to signal processing algorithms within delay lines, as well as on the input/output of FDN. This paper discusses efficient vectorized Architecture for FDN reverberator with policy based design to achieve modular implementation, allowing for compile time construction the FDN, without sacrificing top performance requirements.
{"title":"Efficient vectorized architecture for Feedback Delay Network reverberator with policy based design","authors":"Ireneusz Gawlik, Tomasz Pedzimaz, S. Palka, B. Ziółko","doi":"10.1109/SPA.2015.7365146","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365146","url":null,"abstract":"The Feedback Delay Network (FDN) is used as artificial digital reverberation algorithm. Being one of the most naturally sounding approaches it became widely implemented in many sound processing software products. Although FDN is a very potent tool in regards to artificial reverberation, achieving proper perceptual quality of acoustic simulation usually demands additional modifications to signal processing algorithms within delay lines, as well as on the input/output of FDN. This paper discusses efficient vectorized Architecture for FDN reverberator with policy based design to achieve modular implementation, allowing for compile time construction the FDN, without sacrificing top performance requirements.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133058436","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 : 2015-09-01DOI: 10.1109/SPA.2015.7365156
Agata Chmielewska, Marianna Parzych, T. Marciniak, A. Dabrowski, Przemyslaw Walkowiak
In this paper we address a problem of automatic generation of the so-called density maps (heat maps) using video recordings acquired from surveillance CCTV systems in urban areas (CCTV - closed circuit television). Our software for density map estimation increments the accumulation table only in case of detecting a new moving object, resulting in a count of moving objects density map. We also applied an algorithm for projective transformation of image to achieve better accuracy of the moving object density maps. We analyzed the proposed solution for different angles of camera positions. Next the results were compared with the density maps calculated from the top view camera position.
{"title":"Application of the projective geometry in the density mapping based on CCTV monitoring","authors":"Agata Chmielewska, Marianna Parzych, T. Marciniak, A. Dabrowski, Przemyslaw Walkowiak","doi":"10.1109/SPA.2015.7365156","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365156","url":null,"abstract":"In this paper we address a problem of automatic generation of the so-called density maps (heat maps) using video recordings acquired from surveillance CCTV systems in urban areas (CCTV - closed circuit television). Our software for density map estimation increments the accumulation table only in case of detecting a new moving object, resulting in a count of moving objects density map. We also applied an algorithm for projective transformation of image to achieve better accuracy of the moving object density maps. We analyzed the proposed solution for different angles of camera positions. Next the results were compared with the density maps calculated from the top view camera position.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128139842","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 : 2015-09-01DOI: 10.1109/SPA.2015.7365147
Wassim Alexan, Ahmed El Mahdy
Employing different relaying protocols at a relay node in a wireless cooperative network could improve the overall system performance. The choice of amplify-and-forward (AF) or decode-and-forward (DF) depends on the available set of conditions pertaining to each relay node in the system. In this paper, a hybrid relaying protocol is proposed for systems employing BPSK modulation in Rayleigh fading channels. The hybrid protocol in use exploits the best DF has to offer but at a lower complexity, closer to that of the AF. Based on the log-likelihood ratio (LLR) value of the received signal at a relay node, the node decides whether it should follow the AF or the DF relaying protocols or to remain inactive. The reliability of the LLR allows for better hard-decoding due to its higher sensitivity nature. Maximal ratio combining (MRC) is carried out at the destination node to detect all the received signals. The proposed relaying protocol is tested for wireless systems where the relay nodes are symmetrically distributed or randomly distributed. The system performance is measured in terms of the bit error rate and outage probability curves, comparing it with other hybrid relaying systems.
{"title":"A hybrid relaying protocol for wireless cooperative networks based on the log-likelihood ratio","authors":"Wassim Alexan, Ahmed El Mahdy","doi":"10.1109/SPA.2015.7365147","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365147","url":null,"abstract":"Employing different relaying protocols at a relay node in a wireless cooperative network could improve the overall system performance. The choice of amplify-and-forward (AF) or decode-and-forward (DF) depends on the available set of conditions pertaining to each relay node in the system. In this paper, a hybrid relaying protocol is proposed for systems employing BPSK modulation in Rayleigh fading channels. The hybrid protocol in use exploits the best DF has to offer but at a lower complexity, closer to that of the AF. Based on the log-likelihood ratio (LLR) value of the received signal at a relay node, the node decides whether it should follow the AF or the DF relaying protocols or to remain inactive. The reliability of the LLR allows for better hard-decoding due to its higher sensitivity nature. Maximal ratio combining (MRC) is carried out at the destination node to detect all the received signals. The proposed relaying protocol is tested for wireless systems where the relay nodes are symmetrically distributed or randomly distributed. The system performance is measured in terms of the bit error rate and outage probability curves, comparing it with other hybrid relaying systems.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114421644","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 : 2015-09-01DOI: 10.1109/SPA.2015.7365145
C. Cabirol, W. Sauer-Greff, A. Bisplinghoff, R. Urbansky
In case of unknown carrier phase and/or imperfect channel estimation in communication systems using QPSK it is well known that phase and channel uncertainty can be resolved by differential modulation at the expense of doubling the bit error ratio. Such a differentially modulated QPSK approach has to be applied in wavelength division multiplexing (WDM) fiber optical communication systems using coherent transmission due to the phase ambiguity of carrier phase estimation (CPE) and potential cycle slips. However, this penalty can be diminished by using an iterative decoding procedure which passes information between the differential decoder and the decoder of a low-density parity-check (LDPC) code, a powerful state-of-the art forward error correction (FEC) code. In addition, it is shown that by applying a layered decoding schedule in the LDPC decoder, the number of required iterations can be reduced by up to 50%.
{"title":"Complexity reduced turbo differential decoding based on layered LDPC decoding","authors":"C. Cabirol, W. Sauer-Greff, A. Bisplinghoff, R. Urbansky","doi":"10.1109/SPA.2015.7365145","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365145","url":null,"abstract":"In case of unknown carrier phase and/or imperfect channel estimation in communication systems using QPSK it is well known that phase and channel uncertainty can be resolved by differential modulation at the expense of doubling the bit error ratio. Such a differentially modulated QPSK approach has to be applied in wavelength division multiplexing (WDM) fiber optical communication systems using coherent transmission due to the phase ambiguity of carrier phase estimation (CPE) and potential cycle slips. However, this penalty can be diminished by using an iterative decoding procedure which passes information between the differential decoder and the decoder of a low-density parity-check (LDPC) code, a powerful state-of-the art forward error correction (FEC) code. In addition, it is shown that by applying a layered decoding schedule in the LDPC decoder, the number of required iterations can be reduced by up to 50%.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116246047","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 : 2015-09-01DOI: 10.1109/SPA.2015.7365158
J. Balcerek, P. Pawlowski, A. Dabrowski, A. Konieczka
This paper presents the use of relations between features, which describe a caller for automatic recognition of abnormal cases in emergency telephone call systems. The proposed correlation based procedure, as an integral part of the authors' advanced database search mechanism dedicated to emergency notification centers, extends the record matching procedures and takes into account dependences between features. Illustrative examples and experiments show that the presented procedure significantly improves recognition of impossible cases, e.g. those reported by cheaters.
{"title":"Relations between features for automatic recognition of abnormal cases in emergency telephone call systems","authors":"J. Balcerek, P. Pawlowski, A. Dabrowski, A. Konieczka","doi":"10.1109/SPA.2015.7365158","DOIUrl":"https://doi.org/10.1109/SPA.2015.7365158","url":null,"abstract":"This paper presents the use of relations between features, which describe a caller for automatic recognition of abnormal cases in emergency telephone call systems. The proposed correlation based procedure, as an integral part of the authors' advanced database search mechanism dedicated to emergency notification centers, extends the record matching procedures and takes into account dependences between features. Illustrative examples and experiments show that the presented procedure significantly improves recognition of impossible cases, e.g. those reported by cheaters.","PeriodicalId":423880,"journal":{"name":"2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134629488","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：