{"title":"Ensored marginal a posteriori bayesian inference for signal models","authors":"A. Quinn","doi":"10.1109/NDSP.1993.767750","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767750","url":null,"abstract":"Using a strongly Bayesian formalism, it is shown that integration over the space spanned by the basis functions of a systematic hypothesis admits an objective complexity measure of the hypothesis. This results in the objective embodiment of Ockham's Razor within the marginal inference, via the Ockham Parameter Inference (OPI). The insight leads to a new Censored Marginal a Posteriori (CMaAP) estimation procedure which returns accurate estimates well be low the thresholds inherent in conventional Maximum Likelihood (ML) estimation. The procedure tests the status of an alternative-free hypothesis, unifying the detection and estimation tasks. The framework is readily extended to a multi-hypothesis environment where the OPI penalizes overly complex models. The selection and estimation tasks are unified into a consistent procedure which may be implemented without the need for numerical approximations. This confers a major computational saving over current approaches.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117107795","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":"Multichannel L-filters based on M-ordering","authors":"Constantine Kotropoulos, I. Pitas","doi":"10.1109/NDSP.1993.767685","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767685","url":null,"abstract":"The extension of single-channel nonlinear filters whose output is a linear combination of the order statistics of the input samples to the multichannel case is presented in this paper. The subordering principle of marginal ordering (M-ordering) is used for multivariate data or dering. A unified framework for a discrete calculation of the moments of the bivariate order statistics required for the design of the multichannel marginal L-filters is outlined. The derivation of a bivariate distribution, namely the Laplacian (bi-exponential) distribution which belongs to Morgenstern's family is discussed. It is shown by simulations that the proposed multichannel L-filters perform better than other multi channel nonlinear filters such as the marginal median and the vector median proposed elsewhere as well as their single-channel counterparts.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"62 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120889173","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":"Non-linear processing of signals for fast feature extraction further results","authors":"V. Buzuloiu, D. Coltuc","doi":"10.1109/NDSP.1993.767752","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767752","url":null,"abstract":"In [1] we have presented a new method for computing some geometrical features of a pulse from a few samples. Here we present a more general setting of the method in view of potential applications in image processing and we report on a particular implementation (simulation results) of the initial algorithm using DataWave ITT Intermetall processor chip.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125326847","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":"Design of weighted order statistic filters using the perceptron algorithm","authors":"Byeongjang Jeong, Y. Lee","doi":"10.1109/NDSP.1993.767706","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767706","url":null,"abstract":"In this paper, we observe that the design of optimal weighted order statistic(WOS) filters under the mean absolute error criterion can be thought of as a two-class linear classification problem. Based on this observation, the perceptron algorithm is applied to design WOS filters. It is shown, through experiments, that the perceptron algorithm can find optimal or near optimal WOS filters in practical situations.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114392413","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":"A stability condition for certain bilinear systems","authors":"Junghsi Lee, V. J. Mathews","doi":"10.1109/NDSP.1993.767739","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767739","url":null,"abstract":"This paper derives a simple sufficient condition for the output of a discrete-time, time-invariant bilinear system to be bounded whenever the input signal to the system is bounded by a finite constant.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121999914","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":"Properties of analog median filters","authors":"S. Paul, K. Huper, J. Nossek","doi":"10.1109/NDSP.1993.767713","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767713","url":null,"abstract":"Recently, a new system for analog median (rank) filtering (AMF), based on a nonlinear dynamical system, was proposed. The data to be sorted are used as initial conditions for the ordinary differential equation. The performance of this system, e.g. convergence time, precision, can be estimated. The AMF requires a design parameter to obtain a well defined behaviour as opposed to a digital median filter. This parameter controls the speed and correctness of the filter. The admissible range for this parameter is much larger than the theory predicts. By the way it can be used for smoothing the picture.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117032319","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":"Morphological data fusion in medical imaging","authors":"S. Marshall, G. Matsopoulos","doi":"10.1109/NDSP.1993.767735","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767735","url":null,"abstract":"A hierarchical image fusion scheme is presented which preserves the details of the input images of most relevance for visual perception. The technique is demonstrated by fusing images derived from magnetic resonance (MR) and computed tomography (CT) scanners. The fusion scheme has been applied to both phantoms of the above modalities, and also to pairs of MR images of the human brain. Results are given to show that fused images preserve a more detailed representation of the scene and provide information that cannot be obtained by viewing the input images separately.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129179800","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 compression with affine transformations","authors":"H. Raittinen, K. Kaski","doi":"10.1109/NDSP.1993.767697","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767697","url":null,"abstract":"As the needs for information transfer and storage increase the importance of data coding and compression becomes increasingly important in applications like digital HDTV, tel efax, ISDN and image data bases. Fractal based coding is a new, very promising image compression method. We have developed a fractal image compression method and tested it with binary (black and white) images. The decoded results are close to the original images with the relative Hamming distance of the order of one percent. The compression ratios are found to be extremely high.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"238 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131270726","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":"On the statistical properties of tomlinson filters","authors":"T. Trump, U. Forssén","doi":"10.1109/NDSP.1993.767769","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767769","url":null,"abstract":"This paper investigates the statistical properties of Tomlinson filtered sequences. The input to the Tomlinson filter consists of i.i.d. stochastic variables. Uniform and point-distributed inputs are treated. Conditions under which the output sequence consists of independent variables are given together with examples of correlated outputs.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124591272","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":"A new motion compensated field rate upconversion algorithm","authors":"J. Salonen, T. Koivunen","doi":"10.1109/NDSP.1993.767755","DOIUrl":"https://doi.org/10.1109/NDSP.1993.767755","url":null,"abstract":"This paper describes a new algorithm for motion compensated field rate upconversion (FRU). Motion estimation is done on the block matching basis using pixel difference classification approach (PDC). Two-stage non-linear vector postprocessing is used to obtain a consistent and uniform vector field.","PeriodicalId":337667,"journal":{"name":"IEEE Winter Workshop on Nonlinear Digital Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117251953","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}