Pub Date : 2012-01-16DOI: 10.22630/mgv.2016.25.1.2
M. Janowicz, J. Kaleta, A. Orłowski, P. Wrzeciono, A. Zembrzuski
Numerical simulations of coupled map lattices with various degree of nonlocality have been performed. Quantitative characteristics of recently introduced for local coupling have been applied in the nonlocal case. It has been attempted to draw qualitative conclusions about nonlocality from the emerging pictures.
{"title":"Visualization of nonlocality in coupled map lattices","authors":"M. Janowicz, J. Kaleta, A. Orłowski, P. Wrzeciono, A. Zembrzuski","doi":"10.22630/mgv.2016.25.1.2","DOIUrl":"https://doi.org/10.22630/mgv.2016.25.1.2","url":null,"abstract":"Numerical simulations of coupled map lattices with various degree of nonlocality have been performed. Quantitative characteristics of recently introduced for local coupling have been applied in the nonlocal case. It has been attempted to draw qualitative conclusions about nonlocality from the emerging pictures.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"73 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86260734","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 : 2012-01-16DOI: 10.22630/mgv.2016.25.1.5
Munish Kumar, M. Jindal, R. Sharma, S. Jindal
In this paper, we have proposed a feature extraction technique for recognition of segmented handwritten characters of Gurmukhi script. The experiments have been performed with 7000 specimens of segmented offline handwritten Gurmukhi characters collected from 200 different writers. We have considered the set of 35 basic characters of the Gurmukhi script and have proposed the feature extraction technique based on boundary extents of the character image. PCA based feature selection technique has also been implemented in this work to reduce the dimension of data. We have used k-NN, SVM and MLP classifiers. SVM has been used with four different kernels. In this work, we have achieved maximum recognition accuracy of 93.8% for the 35-class problem when SVM with RBF kernel and 5-fold cross validation technique were employed.
{"title":"Offline handwritten pre-segmented character recognition of Gurmukhi script","authors":"Munish Kumar, M. Jindal, R. Sharma, S. Jindal","doi":"10.22630/mgv.2016.25.1.5","DOIUrl":"https://doi.org/10.22630/mgv.2016.25.1.5","url":null,"abstract":"In this paper, we have proposed a feature extraction technique for recognition of segmented handwritten characters of Gurmukhi script. The experiments have been performed with 7000 specimens of segmented offline handwritten Gurmukhi characters collected from 200 different writers. We have considered the set of 35 basic characters of the Gurmukhi script and have proposed the feature extraction technique based on boundary extents of the character image. PCA based feature selection technique has also been implemented in this work to reduce the dimension of data. We have used k-NN, SVM and MLP classifiers. SVM has been used with four different kernels. In this work, we have achieved maximum recognition accuracy of 93.8% for the 35-class problem when SVM with RBF kernel and 5-fold cross validation technique were employed.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83643530","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 : 2012-01-16DOI: 10.22630/mgv.2016.25.1.3
Jakub Walczak, A. Wojciechowski
Gender recognition, across different races and regardless of age, is becoming an increasingly important technology in the domains of marketing, human-computer interaction and security. Most state-of-the-art systems consider either highly constrained conditions or relatively large databases. In either case, often not enough attention is paid to cross-racial age-invariant applications. This paper proposes a~method of hybrid classification, which performs well even with a small training set. The design of the classifier enables the construction of reliable decision boundaries insensitive to an aging model as well as to race variation. For a training set consisting of one hundred images, the proposed method reached an accuracy level of 90%, whereas the best method known from the literature, tested under the restrictions imposed on the database, achieved only 78% accuracy.
{"title":"Improved gender classification using Discrete Wavelet Transform and hybrid Support Vector Machine","authors":"Jakub Walczak, A. Wojciechowski","doi":"10.22630/mgv.2016.25.1.3","DOIUrl":"https://doi.org/10.22630/mgv.2016.25.1.3","url":null,"abstract":"Gender recognition, across different races and regardless of age, is becoming an increasingly important technology in the domains of marketing, human-computer interaction and security. Most state-of-the-art systems consider either highly constrained conditions or relatively large databases. In either case, often not enough attention is paid to cross-racial age-invariant applications. This paper proposes a~method of hybrid classification, which performs well even with a small training set. The design of the classifier enables the construction of reliable decision boundaries insensitive to an aging model as well as to race variation. For a training set consisting of one hundred images, the proposed method reached an accuracy level of 90%, whereas the best method known from the literature, tested under the restrictions imposed on the database, achieved only 78% accuracy.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73820447","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 : 2012-01-16DOI: 10.22630/mgv.2016.25.1.1
M. Janowicz, J. Kaleta, P. Wrzeciono, A. Zembrzuski
Initial-boundary value problem for linear acoustics has been solved in two spatial dimensions. It has been assumed that the initial acoustic field consists of two Gaussian distributions. Dirichlet boundary conditions with zero acoustic pressure at the boundaries have been imposed. The solution has been obtained with the help of a split-operator technique which resulted in a cellular automaton with uncountably many internal states. To visualize the results, the Python library matplotlib has been employed. It has been shown that attractive graphical output results in both the transient and stationary regimes. The visualization effects are similar to, but different from, the well-known quantum-mechanical carpets.
{"title":"Acoustic carpets","authors":"M. Janowicz, J. Kaleta, P. Wrzeciono, A. Zembrzuski","doi":"10.22630/mgv.2016.25.1.1","DOIUrl":"https://doi.org/10.22630/mgv.2016.25.1.1","url":null,"abstract":"Initial-boundary value problem for linear acoustics has been solved in two spatial dimensions. It has been assumed that the initial acoustic field consists of two Gaussian distributions. Dirichlet boundary conditions with zero acoustic pressure at the boundaries have been imposed. The solution has been obtained with the help of a split-operator technique which resulted in a cellular automaton with uncountably many internal states. To visualize the results, the Python library matplotlib has been employed. It has been shown that attractive graphical output results in both the transient and stationary regimes. The visualization effects are similar to, but different from, the well-known quantum-mechanical carpets.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"412 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79953729","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 : 2012-01-16DOI: 10.22630/mgv.2016.25.1.4
W. Zeler, P. Rohleder
A new system of creation and management of particle effects created for the needs of the future productions of Techland Co. Ltd. is presented. By a proper organisation of memory buffers it provides for maximum data density in the memory. This makes it possible to simplify the calculations and to use a smaller number of threads and less memory readings.
{"title":"Particle effect system for the needs of a modern video game using the GPU","authors":"W. Zeler, P. Rohleder","doi":"10.22630/mgv.2016.25.1.4","DOIUrl":"https://doi.org/10.22630/mgv.2016.25.1.4","url":null,"abstract":"A new system of creation and management of particle effects created for the needs of the future productions of Techland Co. Ltd. is presented. By a proper organisation of memory buffers it provides for maximum data density in the memory. This makes it possible to simplify the calculations and to use a smaller number of threads and less memory readings.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"93 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86741345","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 : 2012-01-15DOI: 10.22630/mgv.2015.24.1.1
A. Wojciechowski, Artur Majewski, P. Napieralski, Przemysław Nowak, Tadeusz Poreda
Gender recognition, across different races and regardless of age, is becoming an increasingly important technology in the domains of marketing, human-computer interaction and security. Most state-of-the-art systems consider either highly constrained conditions or relatively large databases. In either case, often not enough attention is paid to cross-racial age-invariant applications. This paper proposes a~method of hybrid classification, which performs well even with a small training set. The design of the classifier enables the construction of reliable decision boundaries insensitive to an aging model as well as to race variation. For a training set consisting of one hundred images, the proposed method reached an accuracy level of 90%, whereas the best method known from the literature, tested under the restrictions imposed on the database, achieved only 78% accuracy.
{"title":"Immersive rehabilitation monitoring system supported with Augmented Reality","authors":"A. Wojciechowski, Artur Majewski, P. Napieralski, Przemysław Nowak, Tadeusz Poreda","doi":"10.22630/mgv.2015.24.1.1","DOIUrl":"https://doi.org/10.22630/mgv.2015.24.1.1","url":null,"abstract":"Gender recognition, across different races and regardless of age, is becoming an increasingly important technology in the domains of marketing, human-computer interaction and security. Most state-of-the-art systems consider either highly constrained conditions or relatively large databases. In either case, often not enough attention is paid to cross-racial age-invariant applications. This paper proposes a~method of hybrid classification, which performs well even with a small training set. The design of the classifier enables the construction of reliable decision boundaries insensitive to an aging model as well as to race variation. For a training set consisting of one hundred images, the proposed method reached an accuracy level of 90%, whereas the best method known from the literature, tested under the restrictions imposed on the database, achieved only 78% accuracy.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82211909","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 : 2012-01-14DOI: 10.22630/mgv.2014.23.3.6
P. Brož, I. Kolingerová, Jakub Szkandera, Michal Zemek
Path planning is a well known problem that has been extensively studied in many scientific disciplines. In general, it defines a task of finding a path between two given spots in an abstract environment so that the path satisfies certain criterion of optimality. Although there are many methods solving this objective, they usually assume the examined space does not change in runtime. Modern applications, however, do not have to meet these requirements, especially in case of virtual reality or computer games. Therefore, we propose a general model for real-time path planning in dynamic environment where the obstacles can nondeterministically appear, disappear, change the position, orientation or even shape. The model uses a triangulation for dynamic space subdivision among bounding spheres of the obstacles and a heuristic algorithm to repair an already found path after any change of the scene. The presented solution is the first one using regular triangulation. At the price of the suboptimal result, it provides an efficient and fast way to plan a path with the maximal clearance among the moving and changing obstacles. In comparison to raster based techniques and methods using the Delaunay triangulation (Voronoi diagram), it requires less time to preprocess and generates paths with a larger clearance.
{"title":"Dynamic Path Planning with Regular Triangulations","authors":"P. Brož, I. Kolingerová, Jakub Szkandera, Michal Zemek","doi":"10.22630/mgv.2014.23.3.6","DOIUrl":"https://doi.org/10.22630/mgv.2014.23.3.6","url":null,"abstract":"Path planning is a well known problem that has been extensively studied in many scientific disciplines. In general, it defines a task of finding a path between two given spots in an abstract environment so that the path satisfies certain criterion of optimality. Although there are many methods solving this objective, they usually assume the examined space does not change in runtime. Modern applications, however, do not have to meet these requirements, especially in case of virtual reality or computer games. Therefore, we propose a general model for real-time path planning in dynamic environment where the obstacles can nondeterministically appear, disappear, change the position, orientation or even shape. The model uses a triangulation for dynamic space subdivision among bounding spheres of the obstacles and a heuristic algorithm to repair an already found path after any change of the scene. The presented solution is the first one using regular triangulation. At the price of the suboptimal result, it provides an efficient and fast way to plan a path with the maximal clearance among the moving and changing obstacles. In comparison to raster based techniques and methods using the Delaunay triangulation (Voronoi diagram), it requires less time to preprocess and generates paths with a larger clearance.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"56 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76134006","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 : 2012-01-14DOI: 10.22630/mgv.2014.23.1.3
A. Baataoui, N. E. Akkad, A. Saaidi, K. Satori, M. Masrar
In this paper we present a self-calibration method for a CCD camera with varying intrinsic parameters based on an unknown planar scene. The advantage of our method is reducing the number of images (two images) needed to estimate the parameters of the camera used. Moreover, self-calibration equations are related to the number of points matched (very numerous and easy to detect) rather than to the number of images, since the use of a large number of images requires high computation time. On the other hand, we base on the points matched, which are numerous, when estimating the projection matrices and homographies between the images. The latter are used with the images of the absolute conic to formulate a system of non-linear equations (self-calibration equations depend on the number of matched pairs). Finally, the intrinsic parameters of the camera can be obtained by minimizing a non-linear cost function in a two-step procedure: initialization and optimization. Experiment results show the robustness of our algorithms in terms of stability and convergence.
{"title":"Robust method for camera self-calibration by an unkown planar scene","authors":"A. Baataoui, N. E. Akkad, A. Saaidi, K. Satori, M. Masrar","doi":"10.22630/mgv.2014.23.1.3","DOIUrl":"https://doi.org/10.22630/mgv.2014.23.1.3","url":null,"abstract":"In this paper we present a self-calibration method for a CCD camera with varying intrinsic parameters based on an unknown planar scene. The advantage of our method is reducing the number of images (two images) needed to estimate the parameters of the camera used. Moreover, self-calibration equations are related to the number of points matched (very numerous and easy to detect) rather than to the number of images, since the use of a large number of images requires high computation time. On the other hand, we base on the points matched, which are numerous, when estimating the projection matrices and homographies between the images. The latter are used with the images of the absolute conic to formulate a system of non-linear equations (self-calibration equations depend on the number of matched pairs). Finally, the intrinsic parameters of the camera can be obtained by minimizing a non-linear cost function in a two-step procedure: initialization and optimization. Experiment results show the robustness of our algorithms in terms of stability and convergence.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85014949","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 : 2012-01-14DOI: 10.22630/mgv.2014.23.3.4
P. Flasinski
A novel hybrid structural-parametric model for ECG diagnostic justification is presented in the paper. In order to distinguish between specific subclasses of heart dysfunction phenomena both grammars and automata are enhanced with a formalism of dynamic programming. It allows one to construct a system, which is feasible for aiding a process of teaching and evaluating medical students' diagnostic reasoning in the area of electrocardiography.
{"title":"Syntactic pattern recognition of ECG for diagnostic justification","authors":"P. Flasinski","doi":"10.22630/mgv.2014.23.3.4","DOIUrl":"https://doi.org/10.22630/mgv.2014.23.3.4","url":null,"abstract":"A novel hybrid structural-parametric model for ECG diagnostic justification is presented in the paper. In order to distinguish between specific subclasses of heart dysfunction phenomena both grammars and automata are enhanced with a formalism of dynamic programming. It allows one to construct a system, which is feasible for aiding a process of teaching and evaluating medical students' diagnostic reasoning in the area of electrocardiography.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"112 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90986915","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 : 2012-01-14DOI: 10.22630/mgv.2014.23.3.1
W. Nowinski
Our ultimate objective is to create a holistic and reference atlas of the whole adult human brain along with the head and neck. Several techniques have been employed to create atlases. Here we discuss the atlas design and use from a point of view of two key techniques, visualization and interaction. For visualization, surface rendering of a geometrical model of the brain, head and neck is employed. Geometrical model ensures anatomic parcellability, high (sub-pixel) resolution, editibility, extendibility, structure separability, structure-to-structure conflict detection, and integration a knowledge-based content with the atlas. Interaction allows the user to create and explore any region of interest along with its surroundings just with a few clicks, taking into account that the atlas provides a rich set of functions and the number of atlas components is about 3,000. There are seven types of interaction enabling to: select and deselect tissue classes/groups/individual structures, do real-time manipulation, do virtual dissections, select and scroll the original scans, query a structure to get its label or location, get stereotactic coordinates and measure distances, and support other functionality. This design of visualization and interaction provides a fast and easy to use solution, and allows the atlas to run on desktop and mobile iPad and Android-based platforms.
{"title":"Visualization and interaction in the atlas of the human brain, head and neck","authors":"W. Nowinski","doi":"10.22630/mgv.2014.23.3.1","DOIUrl":"https://doi.org/10.22630/mgv.2014.23.3.1","url":null,"abstract":"Our ultimate objective is to create a holistic and reference atlas of the whole adult human brain along with the head and neck. Several techniques have been employed to create atlases. Here we discuss the atlas design and use from a point of view of two key techniques, visualization and interaction. For visualization, surface rendering of a geometrical model of the brain, head and neck is employed. Geometrical model ensures anatomic parcellability, high (sub-pixel) resolution, editibility, extendibility, structure separability, structure-to-structure conflict detection, and integration a knowledge-based content with the atlas. Interaction allows the user to create and explore any region of interest along with its surroundings just with a few clicks, taking into account that the atlas provides a rich set of functions and the number of atlas components is about 3,000. There are seven types of interaction enabling to: select and deselect tissue classes/groups/individual structures, do real-time manipulation, do virtual dissections, select and scroll the original scans, query a structure to get its label or location, get stereotactic coordinates and measure distances, and support other functionality. This design of visualization and interaction provides a fast and easy to use solution, and allows the atlas to run on desktop and mobile iPad and Android-based platforms.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88728680","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：