Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)最新文献

{"title":"Morphological Processing of Electromagnetic Scattering Data for Enhancing the Reconstruction Accuracy of the Iterative Multi-Scaling Approach","authors":"D. Franceschini, A. Rosani, M. Donelli, A. Massa, M. Pastorino","doi":"10.1109/IST.2006.1650795","DOIUrl":"https://doi.org/10.1109/IST.2006.1650795","url":null,"abstract":"This work presents a methodology to locate and characterize multiple unknown scatterers exploiting the scattered electromagnetic radiation collected on a measurement region outside the area under investigation. In many practical cases, an accurate quantitative imaging of the scenario under test is required and it can be reached by using a high resolution representation of the dielectric profile of the scatterers. Towards this aim, an enhanced iterative multi-resolution procedure that exploits a morphological processing for detecting and focusing on different non-connected regions-of-interest has been developed. A suitable set of representative numerical results will demonstrate that the proposed approach is able to efficiently detect the objects in the imaging scenario and to enhance the accuracy in reconstructing multiple scatterers. This is the author's version of the final version available at IEEE.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115135560","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}

{"title":"Comparative Study of Adaptive Segmentation Techniques for Gesture Analysis in Unconstrained Environments","authors":"M. Côté, P. Payeur, G. Comeau","doi":"10.1109/IST.2006.1650770","DOIUrl":"https://doi.org/10.1109/IST.2006.1650770","url":null,"abstract":"This paper discusses the importance of providing non- invasive techniques in the analysis of the complex movements performed by musicians and athletes. Current gesture analysis systems are insufficient and do not succeed in providing quality performance measurements without imposing strict environmental and operational constraints on individuals. Computer vision offers the means with which such techniques can be made possible without impeding the performance of musicians or compromising the integrity of the measurements. The following study compares some of the modern image segmentation techniques and discusses their shortcomings with respect to the stated context. A novel statistical method is also introduced in an attempt to improve the resilience of vision-based gesture segmentation. I. INTRODUCTION With the advent of more powerful computing facilities and advances in artificial intelligence, few techniques have been proposed in the evaluation of the complex movements inherent in the performances of musicians and athletes. Such techniques are highly desirable in order to detect problematic situations which often lead to chronic injuries and to provide the capacity with which professors and trainers may measure the evolution and habits of individuals. Gesture analysis provides the means with which quantitative measurements may be obtained with respect to the physical performances of musicians and athletes. Modern gesture analysis methodologies employed by professionals fail to obtain an exhaustive evaluation or a complete comparison between gestures. Current techniques in this type of analysis are not robust enough to operate in the unconstrained environments in which these performances must be evaluated. Many techniques today still rely on the use of encumbering sensor technologies and require the use of cabling or attaching markers on an individual. The techniques also often require a very controlled environment and involve tedious, expensive and complex operating methodologies. The imposed environments are usually foreign to the musicians or athletes resulting in an impeded performance and corruption to the exactitude of the measurements. The undertaken study aims to research and develop new vision-based methodologies suitable for the analysis of musician gestures. Specifically the context being explored consists of analyzing the gestures and postures of pianists with applications to piano pedagogy. Computer vision techniques offer the ideal means for this type of evaluation. Due to their non-invasive nature they do not interfere with the performance of pianists. Computer vision techniques are put to the test in a context where the imposed constraints on the environment and individuals must remain minimal.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128936019","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}

{"title":"Robust Defect Detection Using Improved Higher Order Wavelet Descriptors and Support Vector Machines for Visual Inspection Systems.","authors":"Dimitrios Alexios Karras","doi":"10.1109/IST.2006.1650799","DOIUrl":"https://doi.org/10.1109/IST.2006.1650799","url":null,"abstract":"This paper aims at investigating a novel solution to the problem of defect detection from textile images using the Discrete Wavelet Transform (DWT) Analysis, involving multiple wavelet bases, and the Support Vector Machines (SVM) classification approach, that can find applications in the design of robust quality control systems for the textile industry. The suggested solution focuses on detecting defects in textile manufacturing applications from the corresponding images DWT and higher order vector quantization related properties of the associated wavelet coefficients. More specifically, a novel methodology is investigated for discriminating defects by applying a supervised neural classification technique, namely SVM, to innovative multidimensional multi-wavelet based feature vectors. These vectors are extracted from the multi-wavelet bases K-Level 2-D DWT (Discrete Wavelet Transform) transformed original image using higher order Vector Quantization techniques and correlation analysis applied to these wavelet domain quantization vectors. The results of the proposed methodology are illustrated in defective textile images where the defective areas are recognized with higher accuracy than the one obtained by applying two rival defect detection methodologies. The first one of them uses all the wavelet coefficients derived from the k-Level 2-D DWT and involves SVM again in the classification stage, while the second one uses again all the wavelet coefficients derived from the k-Level 2-D DWT but involves a Multilayer Perceptron (MLP) neural network in the classification stage. The promising results herein shown outline the importance of judicious selection and processing of 2-D DWT wavelet coefficients for industrial pattern recognition applications as well as the generalization performance benefits obtained by involving SVM neural networks instead of other ANN models.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124056583","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}

{"title":"Image Restoration for Security Cameras with Dirty Lens under Oblique Illumination","authors":"Y. Fujii, N. Ohta, T. Ito, S. Saitoh, T. Matsuura, T. Yamamoto","doi":"10.1109/IST.2006.1650784","DOIUrl":"https://doi.org/10.1109/IST.2006.1650784","url":null,"abstract":"An approach for restoring the images of a suspected person taken by a security camera with dirty lens is proposed. In the approach, the peculiar facts concerning the security camera system that all the things in the image except the suspected person itself are usually preserved and that can be used for investigations are to be used as fully as possible. As the first trial for realizing the proposed approach, a method of restoring an image of a person's face taken by a camera with dirty lens under strong oblique illumination is proposed and its practical application is demonstrated experimentally. The importance of pursuing the proposed approach is discussed from the viewpoints of not only the novelty in image processing technology but also the viewpoints of the efficiency in criminal investigation and social security.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126148735","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}

{"title":"Efficient Computation of Orthogonal Moments by Suppressing the Factorial Terms","authors":"G. Papakostas, Y. Boutalis, Dimitrios Alexios Karras, Basil G. Mertzios","doi":"10.1109/IST.2006.1650769","DOIUrl":"https://doi.org/10.1109/IST.2006.1650769","url":null,"abstract":"A Modified Direct Method for the computation of the Zernike moments is presented in this paper. The presence of many factorial terms, in the direct method for computing the Zernike moments, makes their computation process a very time consuming task. Although the computational power of the modern computers is impressively increasing, the calculation of the factorial of a big number is still an inaccurate numerical procedure. The main concept of the present paper is that, by using Stirling's Approximation formula for the factorial and by applying some suitable mathematical properties, a novel, factorial-free direct method can be developed. The resulted moments are not equal to those computed by the original direct method, but they are a sufficiently accurate approximation of them. The proposed methodology is generic and can be successfully applied to any orthogonal moments having kernel moment functions consisted of factorial terms. Keywords-Zernike moments, direct method, pattern classification, Stirling's approximation","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133152093","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}

{"title":"Inverse Electromagnetic Scattering by Using a Semi-analytical Approach. First Step: Reconstruction of the Radiating Currents.","authors":"M. Chiappe, G. Gragnani","doi":"10.1109/IST.2006.1650767","DOIUrl":"https://doi.org/10.1109/IST.2006.1650767","url":null,"abstract":"In the present paper a semi-analytical approach to solve the problem of inverse electromagnetic scattering is proposed. The importance of such problem refers to the tomographic reconstruction of dielectric objects. The considered configuration is two-dimensional so that the scattering objects can be assumed to be cylindrical structures along the z axis. The proposed method, based on the inverse \"scattering theory\", deals with the use of the electromagnetic waves to inspect the dielectric structures. The approach is based on the reconstruction of the radiating (or, in general, the measurable) components of the equivalent current density, by means of a singular value decomposition of the scattering integral operator. By such derived components the scatterers' position has been clearly localized. Furthermore, they will be used to compute the total electrical field in the domain of investigation as well as the dielectric features of the body under test. The method seems to perform well and a notable improvement in the reconstruction is demonstrated by numerical simulations. Finally, it is worthy noting that such tests have been appreciated for the very short computational time.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"49 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132184011","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}

{"title":"Adjustment of Computer Input Device for Patient with Tetraplegia by using the Mouse Cursor Locus Image","authors":"Y. Tanimoto, Y. Rokumyo, K. Furusawa, A. Tokuhiro, H. Ukida, H. Yamamoto","doi":"10.1109/IST.2006.1650788","DOIUrl":"https://doi.org/10.1109/IST.2006.1650788","url":null,"abstract":"In rehabilitation medicine, it is necessary for medical staff members to recommend a suitable computer input device and adjust the device for each patient with spinal cord injury (SCI). We can select the suitable computer input device for each patient using the evaluation system that we have developed. In this paper, we deal with the adjustment of the device. After selecting the device, the adjustment is carried out by setting the suitable speed parameter on the operating system. We proposed the software system that can calculate the suitable speed parameter from the mouse cursor image when the patient operates the computer. The value of the speed parameter calculated by our software system was adequate for the patient.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132337717","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}

{"title":"Fast Face Recognition Technique for Small and Portable Devices","authors":"N. Zaeri, F. Mokhtarian, A. Cherri","doi":"10.1109/IST.2006.1650787","DOIUrl":"https://doi.org/10.1109/IST.2006.1650787","url":null,"abstract":"Face recognition finds many important applications in many life sectors and in particular in commercial and law enforcement applications. Face recognition systems which are constrained by limited memory size and computational resources, are under deep investigation from researchers. The rapid progress in multimedia hardware technology has motivated us to explore new and practical methods in face recognition that could be implemented and loaded on small and portable devices. In this paper, we describe a new approach for face recognition where device's size and memory are limited. The proposed approach has two main features: (a) it extracts the most important and discriminant features of the face space represented by the MPEG- 7 Fourier Feature Descriptor (FFD) and (b) it applies the Principal Component Analysis (PCA) to it. The proposed method achieves substantial savings in the computation time needed by the recognition system besides keeping the recognition rate as high as possible. Therefore, the proposed method could be considered to be a good candidate that can accommodate the mobile's memory constraints.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"159 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116212329","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}

{"title":"Enhancement in Defect Detection, Location and Sizing in Hollow Axis Rotors, an Innovative Method to Improve Ultrasonic Image Quality: the Multi-SAFT & Multi-Probe Approach.","authors":"E. Pignone, P. Stanchi","doi":"10.1109/IST.2006.1650796","DOIUrl":"https://doi.org/10.1109/IST.2006.1650796","url":null,"abstract":"In this work an innovative system for the non- destructive testing of rotors of turbine is proposed. It allows to identify, to size and to classify discontinuities located inside the volume of the inspectable material. Starting by a data set acquired by UT probes with different angle beams and from different measurement points, the defects of the inspected material are detected and the relative acoustic images are created by applying the multi-SAFT technique. The advantages of this technique lies in the increasing of the detection capability for small discontinuities and in a great precision in the defect location and sizing. By means of this approach, acoustic images representing the detected defects are obtained with high quality. This improvement is mainly due to the spatial and temporal correlations of the measures. The evaluation of the capability of the new system are assessed by means of several experimental results. In particular, the accuracy of the detection is evaluated in terms of the signal-to-noise ratio and of the obtained azimuth/range spatial resolution.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122832493","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}

{"title":"Enhanced Detectability of Targets in Opaque Media","authors":"G. Giakos, S. Sukumar, P. Bathini, S. Paturi, K. Ambadipudi, D. Wagenar, V. Adya, M. Reddy, S. Sumrain, L. Fraiwan, D. Sheffer","doi":"10.1109/IST.2006.1650797","DOIUrl":"https://doi.org/10.1109/IST.2006.1650797","url":null,"abstract":"The novelty of this study consists in a series of experimental observations, indicating an improvement of the detectability of targets immersed in scattered solutions, by obtaining enhanced DOLP backscattered images over non-polarized backscattered images, with increasing the concentration of the scattering agent, therefore, the opacity of the medium.","PeriodicalId":175808,"journal":{"name":"Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (IST 2006)","volume":"12 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132803956","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}