G. Papakostas, Dimitrios Alexios Karras, Basil G. Mertzios, Y. Boutalis
A new method for extracting feature sets with improved classification performance in image recognition applications is presented in this paper. The main idea is to propose a procedure for obtaining surrogates of the compressed versions of reliable and denoised feature sets without affecting significantly their reconstruction and recognition properties. The surrogate feature vector is of lower dimensionality and thus more appropriate for pattern recognition tasks. The proposed feature extraction method (FEM) combines the advantages of the multiresolution analysis, which is based on the wavelet theory, with the high discriminative nature of Zernike moment sets and the denoising features of Self Organized Topological Maps (SOM). The resulted feature vector is used as a classification feature, in order to achieve high recognition rates in a typical pattern recognition system. The results of the experimental study support the validity and the strength of the proposed method.
{"title":"An Efficient Invariant Image Recognition Methodology using Wavelet Compressed Zernike Moments Denoised through Self Organizing Maps","authors":"G. Papakostas, Dimitrios Alexios Karras, Basil G. Mertzios, Y. Boutalis","doi":"10.1109/IST.2007.379603","DOIUrl":"https://doi.org/10.1109/IST.2007.379603","url":null,"abstract":"A new method for extracting feature sets with improved classification performance in image recognition applications is presented in this paper. The main idea is to propose a procedure for obtaining surrogates of the compressed versions of reliable and denoised feature sets without affecting significantly their reconstruction and recognition properties. The surrogate feature vector is of lower dimensionality and thus more appropriate for pattern recognition tasks. The proposed feature extraction method (FEM) combines the advantages of the multiresolution analysis, which is based on the wavelet theory, with the high discriminative nature of Zernike moment sets and the denoising features of Self Organized Topological Maps (SOM). The resulted feature vector is used as a classification feature, in order to achieve high recognition rates in a typical pattern recognition system. The results of the experimental study support the validity and the strength of the proposed method.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"13 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":"127089938","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}
Magnetic flux leakage testing (MFLT), which measures the distribution of a magnetic field on the magnetized specimen by using a magnetic sensor such as the Hall sensor, is an effective nondestructive testing (NDT) method for detecting surface crack on magnetized ferromagnetic materials. A scan type magnetic camera, based on the principle of MFLT, uses inclined Hall sensors array on the printed circuit board (PCB) to detect small cracks in high speed. However, the waveforms appear in the direction perpendicular to the scan, because the sensors are bonded at different gradients and heights on a PCB in spite of careful soldering. In this paper, the linearly integrated Hall sensors (LIHS) on a wafer are proposed to minimize these waves and to improve the probability of crack detection. The specimen took from a billet is used to determine the effectiveness of the LIHS in the multiple cracks detection.
{"title":"Scan Type Magnetic Camera Images with a High Spatial Resolution for NDT Obtained By Using a Linearly Integrated Hall Sensors Array","authors":"Jiseong Hwang, Jinyi Lee, Jongwoo Jun, Renliang Wang, Seho Choi, Seong-Pyo Hong","doi":"10.1109/IST.2007.379591","DOIUrl":"https://doi.org/10.1109/IST.2007.379591","url":null,"abstract":"Magnetic flux leakage testing (MFLT), which measures the distribution of a magnetic field on the magnetized specimen by using a magnetic sensor such as the Hall sensor, is an effective nondestructive testing (NDT) method for detecting surface crack on magnetized ferromagnetic materials. A scan type magnetic camera, based on the principle of MFLT, uses inclined Hall sensors array on the printed circuit board (PCB) to detect small cracks in high speed. However, the waveforms appear in the direction perpendicular to the scan, because the sensors are bonded at different gradients and heights on a PCB in spite of careful soldering. In this paper, the linearly integrated Hall sensors (LIHS) on a wafer are proposed to minimize these waves and to improve the probability of crack detection. The specimen took from a billet is used to determine the effectiveness of the LIHS in the multiple cracks detection.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"91 8 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":"128016187","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}
D. Franceschini, P. Rocca, M. Benedetti, M. Pastorino, A. Massa
The reconstruction of unknown regions through active microwave imaging techniques requires the retrieval of a large amount of unknown parameters if one aims at fully characterize the electromagnetic properties of the targets under test. Unfortunately, a limited number of independent measurements is available, especially when the scattered field is undersampled because of intrinsic limitations of the imaging setup. In this context, the paper investigates the potentialities of a methodology based on a multi-source illumination as a possible strategy for compensating the reduction of informative field measures and improving the imaging accuracy with respect to single-source experiments.
{"title":"On the Effects of the Exploitation of Source Diversity in Aspect Limited Multi-View Microwave Imaging Systems","authors":"D. Franceschini, P. Rocca, M. Benedetti, M. Pastorino, A. Massa","doi":"10.1109/IST.2007.379583","DOIUrl":"https://doi.org/10.1109/IST.2007.379583","url":null,"abstract":"The reconstruction of unknown regions through active microwave imaging techniques requires the retrieval of a large amount of unknown parameters if one aims at fully characterize the electromagnetic properties of the targets under test. Unfortunately, a limited number of independent measurements is available, especially when the scattered field is undersampled because of intrinsic limitations of the imaging setup. In this context, the paper investigates the potentialities of a methodology based on a multi-source illumination as a possible strategy for compensating the reduction of informative field measures and improving the imaging accuracy with respect to single-source experiments.","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":"133371861","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 electrical power generation there are many problems that may be solved through the application of image analysis. The presence of non ore gangue materials mixed with coal can have an impact on the combustion efficiency and emissions of power plants. Also known as tailings, often these materials are a hazardous byproduct of mining. Differentiation between coal and gangue is desirable for fuel quality control and yield analysis. This research aims to develop a digital imaging and image analysis technique for this purpose. Material samples are analysed through a process of image acquisition and digital processing. Differentiation is found possible between varieties of bituminous coal and associated gangue and stone materials using intensity values and a range of surface texture properties.
{"title":"Differentiation between Coal and Stone through Image Analysis of Texture Features","authors":"D. M. Hobson, R. Carter, Yong Yan, Zhixin Lv","doi":"10.1109/IST.2007.379597","DOIUrl":"https://doi.org/10.1109/IST.2007.379597","url":null,"abstract":"In electrical power generation there are many problems that may be solved through the application of image analysis. The presence of non ore gangue materials mixed with coal can have an impact on the combustion efficiency and emissions of power plants. Also known as tailings, often these materials are a hazardous byproduct of mining. Differentiation between coal and gangue is desirable for fuel quality control and yield analysis. This research aims to develop a digital imaging and image analysis technique for this purpose. Material samples are analysed through a process of image acquisition and digital processing. Differentiation is found possible between varieties of bituminous coal and associated gangue and stone materials using intensity values and a range of surface texture properties.","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":"130790708","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}
Mammographic X-ray equipment uses the radiographic grid in order to remove the scatter radiation and to improve image contrast. The gridlines cause striped lines to appear on the film and may impair diagnostic information. In this study, we propose a new method which reduces noise caused by the gridlines of the mammographic film using digital image processing techniques. We exposed the phantom and chose the region of micro calcifications. We performed the V-filtering and median filtering to reduce noises. By using image filtering, we could increase the signal to noise ratio. The results suggested that the accuracy of the mammographic diagnosis could be improved by proposed method.
{"title":"Detection of micro calcifications of mammographic images","authors":"T. Maruyama, H. Yamamoto","doi":"10.1109/IST.2007.379574","DOIUrl":"https://doi.org/10.1109/IST.2007.379574","url":null,"abstract":"Mammographic X-ray equipment uses the radiographic grid in order to remove the scatter radiation and to improve image contrast. The gridlines cause striped lines to appear on the film and may impair diagnostic information. In this study, we propose a new method which reduces noise caused by the gridlines of the mammographic film using digital image processing techniques. We exposed the phantom and chose the region of micro calcifications. We performed the V-filtering and median filtering to reduce noises. By using image filtering, we could increase the signal to noise ratio. The results suggested that the accuracy of the mammographic diagnosis could be improved by proposed method.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"28 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":"114295838","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 this paper, we propose new shape and color reconstruction methods using image scanner equipped with multiple illuminations. Here, we show three reconstruction algorithms in case of two, three and four light sources. These algorithms are based on the nonlinear least squares using the photometric models and color image intensities. And we estimate optimal number and positions of light sources for a shape reconstruction. As the experimental results, using four light sources which are located symmetrically under the scanning line can be recovered object shape and color accurately, and it is suitable for the actual shape scanner.
{"title":"3D Shape Reconstructions Using Image Scanner under Various Number of Illuminations","authors":"H. Ukida, Y. Tanimoto, T. Sano, H. Yamamoto","doi":"10.1109/IST.2007.379593","DOIUrl":"https://doi.org/10.1109/IST.2007.379593","url":null,"abstract":"In this paper, we propose new shape and color reconstruction methods using image scanner equipped with multiple illuminations. Here, we show three reconstruction algorithms in case of two, three and four light sources. These algorithms are based on the nonlinear least squares using the photometric models and color image intensities. And we estimate optimal number and positions of light sources for a shape reconstruction. As the experimental results, using four light sources which are located symmetrically under the scanning line can be recovered object shape and color accurately, and it is suitable for the actual shape scanner.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"52 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":"130959143","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 this paper there will be explained what automatic image understanding is and how it can be applied to understand the medical image content. Especially the attention will be focused to show how to solve the automatic interpretation problem for selected class of medical images by application of linguistic approach using special kind picture description languages. A possibility to conduct such an analysis will be presented on the examples of analysis of patterns received during the examinations of wrist bones, but presented methodology is more general and may be used in interpretation task for many other classes of medical visualisation. Further there will be presented both the general description of methodology join with the tasks of machine automatic understanding using linguistic formalism, as well as some detailed examples showing applicability of presented approach to various kind of medical pattern obtained during medical examinations.
{"title":"Automatic Understanding of Medical Images Based on Grammar Approach","authors":"M. Ogiela","doi":"10.1109/IST.2007.379568","DOIUrl":"https://doi.org/10.1109/IST.2007.379568","url":null,"abstract":"In this paper there will be explained what automatic image understanding is and how it can be applied to understand the medical image content. Especially the attention will be focused to show how to solve the automatic interpretation problem for selected class of medical images by application of linguistic approach using special kind picture description languages. A possibility to conduct such an analysis will be presented on the examples of analysis of patterns received during the examinations of wrist bones, but presented methodology is more general and may be used in interpretation task for many other classes of medical visualisation. Further there will be presented both the general description of methodology join with the tasks of machine automatic understanding using linguistic formalism, as well as some detailed examples showing applicability of presented approach to various kind of medical pattern obtained during medical examinations.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"150 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":"115894598","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}
Images become very important source of information. Very often when we have both text and image part in a document, the image contains most important part of information. Example of such situation can be medical documentation of some patient. Medical images (e.g. MRI or PET presentations) are more informative for diagnosis and for therapy control than descriptions given in text form. Therefore when we have to find proper document in multimedial database as well as we must made some analysis (eg. statistical) based on stored material -we must go into the image merit content. Searching and analysis methods based on figure captions and another descriptions given in text form are definitely not enough for such purposes. Moreover the typical or traditional forms of computer vision methods, like image processing, analysis and also pattern recognition are not sufficient, because all of them are based on image forms (shapes, textures etc.) when we must in fact go to the image merit content. In the paper the problem of automatic understanding of the images is formulated, discussed, and solved.
{"title":"What Does It Means Automatic Understanding of the Images?","authors":"R. Tadeusiewicz","doi":"10.1109/IST.2007.379566","DOIUrl":"https://doi.org/10.1109/IST.2007.379566","url":null,"abstract":"Images become very important source of information. Very often when we have both text and image part in a document, the image contains most important part of information. Example of such situation can be medical documentation of some patient. Medical images (e.g. MRI or PET presentations) are more informative for diagnosis and for therapy control than descriptions given in text form. Therefore when we have to find proper document in multimedial database as well as we must made some analysis (eg. statistical) based on stored material -we must go into the image merit content. Searching and analysis methods based on figure captions and another descriptions given in text form are definitely not enough for such purposes. Moreover the typical or traditional forms of computer vision methods, like image processing, analysis and also pattern recognition are not sufficient, because all of them are based on image forms (shapes, textures etc.) when we must in fact go to the image merit content. In the paper the problem of automatic understanding of the images is formulated, discussed, and solved.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"53 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":"132276111","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}
An analytical approach to inverse electromagnetic scattering is proposed. Inverse electromagnetic scattering problems deal with the reconstruction of the actual position, the shape, the dimensions and dielectric properties of a dielectric object inside a bounded space region. The technique is based on the use of a known incident field illuminating the space region containing the object. By using a set of measurements of the electrical field scattered by the object under test, an analytical solution can be derived. The solution method makes use of an equivalent source as scattered field's support. Such a source is considered a combination of non-radiating and radiating currents. Analytical results can be achieved by means of the singular system of the scattering operator in a very short computation time.
{"title":"Analytical Solution to Inverse Electromagnetic Scattering: Shape and Position Reconstruction of Dielectric Objects","authors":"M. Chiappe, G. Gragnani","doi":"10.1109/IST.2007.379589","DOIUrl":"https://doi.org/10.1109/IST.2007.379589","url":null,"abstract":"An analytical approach to inverse electromagnetic scattering is proposed. Inverse electromagnetic scattering problems deal with the reconstruction of the actual position, the shape, the dimensions and dielectric properties of a dielectric object inside a bounded space region. The technique is based on the use of a known incident field illuminating the space region containing the object. By using a set of measurements of the electrical field scattered by the object under test, an analytical solution can be derived. The solution method makes use of an equivalent source as scattered field's support. Such a source is considered a combination of non-radiating and radiating currents. Analytical results can be achieved by means of the singular system of the scattering operator in a very short computation time.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"41 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":"124876923","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 framework of nondestructive testing and evaluation (NDE/NDT), this paper deals with the problem of the detection of unknown anomalies in dielectric materials. The proposed inverse scattering approach consists of a two-step procedure aimed at firstly estimating the region-of-interest where the defect is supposed to be located and then improving the qualitative imaging (i.e., the shape and position) of the crack. In order to assess the effectiveness of the proposed approach, an illustrative result from representative numerical test cases is presented and discussed.
{"title":"Improving the Reconstruction Accuracy of GAs-Based NDE/NDT Methods through a Level Set Approach","authors":"M. Donelli, M. Benedetti, P. Rocca, M. Pastorino","doi":"10.1109/IST.2007.379572","DOIUrl":"https://doi.org/10.1109/IST.2007.379572","url":null,"abstract":"In the framework of nondestructive testing and evaluation (NDE/NDT), this paper deals with the problem of the detection of unknown anomalies in dielectric materials. The proposed inverse scattering approach consists of a two-step procedure aimed at firstly estimating the region-of-interest where the defect is supposed to be located and then improving the qualitative imaging (i.e., the shape and position) of the crack. In order to assess the effectiveness of the proposed approach, an illustrative result from representative numerical test cases is presented and discussed.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"77 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":"127931854","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：