In this paper an imaging approach for non-intrusive evaluation of civil structures is discussed. The approach is based on the inversion of scattering data measured in near field. Cylindrical geometries are considered under transverse magnetic (TM) illumination conditions. The integral relationships of the inverse scattering problem are discretized and solved by an Inexact-Newton method, which has been found to be very effective in solving ill-posed inverse problems. The approach takes into account the nonlinear nature of the electromagnetic inverse scattering problem, since no approximations are applied (except the ones related to the discretization of the continuous model). After the inversion of the measured data, the imaging method provides images of the dielectric properties of the cross section of the civil structures under test. The mathematical formulation of the method is briefly discussed and the results of numerical simulations are reported. Simplified geometrical configurations are considered, but with dielectric properties close to those of real materials employed in the field of civil engineering.
{"title":"Electromagnetic Imaging for Non-Intrusive Evaluation in Civil Engineering","authors":"G. Bozza, C. Estatico, M. Pastorino, A. Randazzo","doi":"10.1109/IST.2007.379581","DOIUrl":"https://doi.org/10.1109/IST.2007.379581","url":null,"abstract":"In this paper an imaging approach for non-intrusive evaluation of civil structures is discussed. The approach is based on the inversion of scattering data measured in near field. Cylindrical geometries are considered under transverse magnetic (TM) illumination conditions. The integral relationships of the inverse scattering problem are discretized and solved by an Inexact-Newton method, which has been found to be very effective in solving ill-posed inverse problems. The approach takes into account the nonlinear nature of the electromagnetic inverse scattering problem, since no approximations are applied (except the ones related to the discretization of the continuous model). After the inversion of the measured data, the imaging method provides images of the dielectric properties of the cross section of the civil structures under test. The mathematical formulation of the method is briefly discussed and the results of numerical simulations are reported. Simplified geometrical configurations are considered, but with dielectric properties close to those of real materials employed in the field of civil engineering.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114581847","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}
Capacitance-based tomographic imaging, which is commonly called electrical capacitance tomography (ECT), has been developed for two decades. This paper briefly introduces ECT sensors, capacitance measuring circuits, image reconstruction algorithms, and a wide range of challenging applications, including multi-phase measurement of oil pipelines, wet gas pipelines, wet gas separators, milk production lines, pneumatic conveyors, cyclone separators and fluidized beds. A recent development is tomography-based control of oil separators and fluidized bed dryers.
{"title":"Tomographic Imaging based on Capacitance Measurement and Industrial Applications","authors":"Wuqiang Yang","doi":"10.1109/IST.2007.379587","DOIUrl":"https://doi.org/10.1109/IST.2007.379587","url":null,"abstract":"Capacitance-based tomographic imaging, which is commonly called electrical capacitance tomography (ECT), has been developed for two decades. This paper briefly introduces ECT sensors, capacitance measuring circuits, image reconstruction algorithms, and a wide range of challenging applications, including multi-phase measurement of oil pipelines, wet gas pipelines, wet gas separators, milk production lines, pneumatic conveyors, cyclone separators and fluidized beds. A recent development is tomography-based control of oil separators and fluidized bed dryers.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126501232","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}
In the paper image compression algorithm suitable for wireless capsule endoscopy is proposed. In general, image compression is the best way to decrease the communication bandwidth and save the transmitting power. However due to power limitation and small size conditions traditional image compression techniques are not appropriate and dedicated ones are necessary. The proposed algorithm is based on integer version of discrete cosine transform (DCT) and entropy Huffman coder. Thanks to integer DCT application it has low complexity and power consumption. Additionally, the algorithm can provide lossless compression as well as high-quality lossy compression.
{"title":"Low-Power Image Compression for Wireless Capsule Endoscopy","authors":"P. Turcza, M. Duplaga","doi":"10.1109/IST.2007.379586","DOIUrl":"https://doi.org/10.1109/IST.2007.379586","url":null,"abstract":"In the paper image compression algorithm suitable for wireless capsule endoscopy is proposed. In general, image compression is the best way to decrease the communication bandwidth and save the transmitting power. However due to power limitation and small size conditions traditional image compression techniques are not appropriate and dedicated ones are necessary. The proposed algorithm is based on integer version of discrete cosine transform (DCT) and entropy Huffman coder. Thanks to integer DCT application it has low complexity and power consumption. Additionally, the algorithm can provide lossless compression as well as high-quality lossy compression.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129486133","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}
Dimitrios Alexios Karras, Basil G. Mertzios, C. Alexopoulos, D. Mitzias
A novel methodology is herein presented for combining the decisions of different feedforward neural network classifiers. Instead of the usual approach of applying voting schemes on the decisions of their output layer neurons, the proposed methodology integrates the higher order features extracted by their upper hidden layer units through a second stage feedforward neural network having as inputs all such higher order features. Therefore, an hierarchical neural system for pattern recognition has been developed with improved classification performance. The validity of this novel combination approach has been investigated when the first stage neural classifiers involved correspond to different Feature Extraction Methodologies (FEM) for shape classification. The experimental study illustrates that such an approach, integrating higher order features into a second stage feedforward neural classifier, outperforms other combination methods, like voting combination schemes as well as single neural network classifiers having as inputs all FEMs derived features.
{"title":"A Robust Hierarchical Neural Network Methodology for Improved Image Classification Performance","authors":"Dimitrios Alexios Karras, Basil G. Mertzios, C. Alexopoulos, D. Mitzias","doi":"10.1109/IST.2007.379611","DOIUrl":"https://doi.org/10.1109/IST.2007.379611","url":null,"abstract":"A novel methodology is herein presented for combining the decisions of different feedforward neural network classifiers. Instead of the usual approach of applying voting schemes on the decisions of their output layer neurons, the proposed methodology integrates the higher order features extracted by their upper hidden layer units through a second stage feedforward neural network having as inputs all such higher order features. Therefore, an hierarchical neural system for pattern recognition has been developed with improved classification performance. The validity of this novel combination approach has been investigated when the first stage neural classifiers involved correspond to different Feature Extraction Methodologies (FEM) for shape classification. The experimental study illustrates that such an approach, integrating higher order features into a second stage feedforward neural classifier, outperforms other combination methods, like voting combination schemes as well as single neural network classifiers having as inputs all FEMs derived features.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130289780","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}
In the paper the new possibilities for making semantic interpretations of medical structure visualizations with the use of AI linguistic formalisms and especially graph grammar of edNLC type have been presented. Discussed in detail are methods of computational intelligence to the development of a syntactic semantic description of spatial visualizations of the heart's coronary vessels. The methodology can be used for both smart ordering of images while archiving them and for their semantic searches. The latter is especially significant in the context of searching multimedia medical databases (also those accessible online) for such spatial visualizations of those coronary arteries that meet specific medical conditions formulated in a query or presented through a sample image included as an element of the query. The IT methodology described in this work makes it possible to find, for each biological 3D structure considered, its semantic description whose elements make reference to the medical significance of the entire structure described, while at the same time refrain from the formal differences (i.e. appearance and shape) of individual visualizations.
{"title":"Graph-based Linguistic Formalisms in Spatial Modelling of 3D Coronary Vessels","authors":"M. Ogiela, R. Tadeusiewicz, M. Trzupek","doi":"10.1109/IST.2007.379567","DOIUrl":"https://doi.org/10.1109/IST.2007.379567","url":null,"abstract":"In the paper the new possibilities for making semantic interpretations of medical structure visualizations with the use of AI linguistic formalisms and especially graph grammar of edNLC type have been presented. Discussed in detail are methods of computational intelligence to the development of a syntactic semantic description of spatial visualizations of the heart's coronary vessels. The methodology can be used for both smart ordering of images while archiving them and for their semantic searches. The latter is especially significant in the context of searching multimedia medical databases (also those accessible online) for such spatial visualizations of those coronary arteries that meet specific medical conditions formulated in a query or presented through a sample image included as an element of the query. The IT methodology described in this work makes it possible to find, for each biological 3D structure considered, its semantic description whose elements make reference to the medical significance of the entire structure described, while at the same time refrain from the formal differences (i.e. appearance and shape) of individual visualizations.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134116626","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}
This paper presents a new collaborative computer-aided diagnosis system for skin lesions malignancy tracking composed of two modules for lesion description and decision. The decision module incorporates classification and content-based image retrieval schemes (CBIR). The final decision of lesion malignancy will be obtained by merging the two decisions while using the Dempster-Shafer theory in order to improve the accuracy of the final produced decisions. Indeed, after the preprocessing of the studied image and the extraction of the skin lesions by the segmentation process, the lesion description stage defines a set of descriptive features reflecting the clinical signs of the considered lesions malignancy. In fact, 21 features representing shape and radiometric properties are calculated. The quality of these features is evaluated by applying principal components analysis (PCA) and ROC assessment criteria. The results show that the feature set can be reduced to dimension 16. Then, the proposed system estimates the preliminary lesions class with the classification scheme, while using a perceptron neural network technique preceded by a training step. Moreover, given a database of skin lesions, CBIR of the images belonging to this database which gather with the studied image and whose lesions malignancy states are known, permits to have another preliminary idea on the type of the eventual skin lesion. Finally, the results of classification and retrieval schemes are combined while using the Dempster-Shafer theory. This consists to consider the results produced separately by each technique as being dubious sources of information on the lesions malignity with an aim of combining their respective opinions. The proposed architecture allows the production of a viable cost-effective set of opinions on skin lesions malignancy. Besides, since the decision can never be perfect, the CBIR subsystem displays also visually similar images with known pathologies, to provide an intuitive aid to the dermatologist to improve the diagnosis accuracy.
{"title":"A Collaborative System for Pigmented Skin Lesions Malignancy Tracking","authors":"W. Barhoumi, S. Dhahbi, E. Zagrouba","doi":"10.1109/IST.2007.379576","DOIUrl":"https://doi.org/10.1109/IST.2007.379576","url":null,"abstract":"This paper presents a new collaborative computer-aided diagnosis system for skin lesions malignancy tracking composed of two modules for lesion description and decision. The decision module incorporates classification and content-based image retrieval schemes (CBIR). The final decision of lesion malignancy will be obtained by merging the two decisions while using the Dempster-Shafer theory in order to improve the accuracy of the final produced decisions. Indeed, after the preprocessing of the studied image and the extraction of the skin lesions by the segmentation process, the lesion description stage defines a set of descriptive features reflecting the clinical signs of the considered lesions malignancy. In fact, 21 features representing shape and radiometric properties are calculated. The quality of these features is evaluated by applying principal components analysis (PCA) and ROC assessment criteria. The results show that the feature set can be reduced to dimension 16. Then, the proposed system estimates the preliminary lesions class with the classification scheme, while using a perceptron neural network technique preceded by a training step. Moreover, given a database of skin lesions, CBIR of the images belonging to this database which gather with the studied image and whose lesions malignancy states are known, permits to have another preliminary idea on the type of the eventual skin lesion. Finally, the results of classification and retrieval schemes are combined while using the Dempster-Shafer theory. This consists to consider the results produced separately by each technique as being dubious sources of information on the lesions malignity with an aim of combining their respective opinions. The proposed architecture allows the production of a viable cost-effective set of opinions on skin lesions malignancy. Besides, since the decision can never be perfect, the CBIR subsystem displays also visually similar images with known pathologies, to provide an intuitive aid to the dermatologist to improve the diagnosis accuracy.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129752224","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}
One of the most important issues in the field of contrast agents-based echographic imaging is the development of techniques able to separate the echoes of such contrast media from the echoes of the biological tissue: in particular in literature could be found various solutions concerning the use of multiple transmitted signals and the combination of related echoes. These techniques may undergo a reduction of performance, due to some undesired effects normally not taken into account, such as non-linearities introduced by hardware equipment and tissue propagation, thermal and electronic noise and body motion between successive pulses. Here we introduce a simulation tool that we developed, able to calculate the backscattered echo from a contrast agents population immersed in biological tissue, considering all the previous effects. By means of this tool, we performed a comparative analysis of the various multi-pulse techniques on the basis of the contrast to tissue ratio (CTR) and the signal to noise ratio (SNR) before and after the echoes summation. The results show the potentially strong impact of the undesired effects on these techniques and may provide useful hints on the choice of the particular technique to be applied, regarding the specific diagnostic application addressed and the hardware characteristics.
{"title":"On the Robustness of Multi-Pulse Techniques Against Undesired Effects in Contrast Enhanced Ultrasound Imaging","authors":"M. Crocco, C. Sciallero, A. Trucco","doi":"10.1109/IST.2007.379571","DOIUrl":"https://doi.org/10.1109/IST.2007.379571","url":null,"abstract":"One of the most important issues in the field of contrast agents-based echographic imaging is the development of techniques able to separate the echoes of such contrast media from the echoes of the biological tissue: in particular in literature could be found various solutions concerning the use of multiple transmitted signals and the combination of related echoes. These techniques may undergo a reduction of performance, due to some undesired effects normally not taken into account, such as non-linearities introduced by hardware equipment and tissue propagation, thermal and electronic noise and body motion between successive pulses. Here we introduce a simulation tool that we developed, able to calculate the backscattered echo from a contrast agents population immersed in biological tissue, considering all the previous effects. By means of this tool, we performed a comparative analysis of the various multi-pulse techniques on the basis of the contrast to tissue ratio (CTR) and the signal to noise ratio (SNR) before and after the echoes summation. The results show the potentially strong impact of the undesired effects on these techniques and may provide useful hints on the choice of the particular technique to be applied, regarding the specific diagnostic application addressed and the hardware characteristics.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115100364","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}
The purpose of this study is to clarify the side-approach transfer ability of spinal cord injury (SCI) patients. We have proposed the measurement system that consists of four force plates and two CCD cameras in order to analyze the transfer motion. The system measures the three-dimensional floor reaction forces and the side-view and the front-view images during each patient's transfer motion. We understood that the force patterns and the force direction of the left hand are different among SCI patients by analyzing the floor reaction forces. In side-approach transfer, SCI patients diagonally move their wheelchair close to the platform and the wheelchair position is different among SCI patients. In this study, we estimate the wheelchair position by detecting the center position of the wheelchair wheel using the images and by calculating the wheelchair degree (gap angle between the wheelchair and the platform) using side-view image.
{"title":"Measurement of Wheelchair Position for Analyzing Transfer Motion for SCI Patient","authors":"Y. Tanimoto, K. Nanba, H. Ukida, H. Yamamoto","doi":"10.1109/IST.2007.379605","DOIUrl":"https://doi.org/10.1109/IST.2007.379605","url":null,"abstract":"The purpose of this study is to clarify the side-approach transfer ability of spinal cord injury (SCI) patients. We have proposed the measurement system that consists of four force plates and two CCD cameras in order to analyze the transfer motion. The system measures the three-dimensional floor reaction forces and the side-view and the front-view images during each patient's transfer motion. We understood that the force patterns and the force direction of the left hand are different among SCI patients by analyzing the floor reaction forces. In side-approach transfer, SCI patients diagonally move their wheelchair close to the platform and the wheelchair position is different among SCI patients. In this study, we estimate the wheelchair position by detecting the center position of the wheelchair wheel using the images and by calculating the wheelchair degree (gap angle between the wheelchair and the platform) using side-view image.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115026265","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}
G. Giakos, K. Valluru, S. Paturi, V. Adya, K. Ambadipudi, P. Bathini, M. Reddy, S. Sukumar
The results of this novel study, based on multipixel and single-pixel detection geometries, indicate that, significantly higher contrast target detection images have been obtained by doping the surrounding medium with active optical molecules, in conjunction to efficient polarimetric techniques, yielding to an enhanced contract and specificity of the target.
{"title":"Enhanced Detection and Imaging based on Novel Molecular NanoPhotonics Principles","authors":"G. Giakos, K. Valluru, S. Paturi, V. Adya, K. Ambadipudi, P. Bathini, M. Reddy, S. Sukumar","doi":"10.1109/IST.2007.379579","DOIUrl":"https://doi.org/10.1109/IST.2007.379579","url":null,"abstract":"The results of this novel study, based on multipixel and single-pixel detection geometries, indicate that, significantly higher contrast target detection images have been obtained by doping the surrounding medium with active optical molecules, in conjunction to efficient polarimetric techniques, yielding to an enhanced contract and specificity of the target.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122063341","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}
Inverse pattern design for profilometric measurement methods based upon the inversion of a distorted fringe pattern caused by a reference object is a common technique for both mirror-like surfaces and surfaces with diffuse reflection behavior. This paper proposes the calculation of an inverted pattern for analytically known reference objects based upon ray tracing techniques. Thus, a manufactured reference object with an associated reference fringe pattern is no longer required to fully reconstruct object shapes.
{"title":"Inverse Patterns - A Ray Tracing Approach","authors":"V. Putz, B. R. Arminger, B. Zagar","doi":"10.1109/IST.2007.379595","DOIUrl":"https://doi.org/10.1109/IST.2007.379595","url":null,"abstract":"Inverse pattern design for profilometric measurement methods based upon the inversion of a distorted fringe pattern caused by a reference object is a common technique for both mirror-like surfaces and surfaces with diffuse reflection behavior. This paper proposes the calculation of an inverted pattern for analytically known reference objects based upon ray tracing techniques. Thus, a manufactured reference object with an associated reference fringe pattern is no longer required to fully reconstruct object shapes.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124994862","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：