[MGV logo]   Vol. 25 (2016):
  Abstracts and Contents of Papers

No. 1/4.

24 (2015) main forthcoming papers

Machine GRAPHICS & VISION, Vol. 25 (2016), No. 1/4

This number is not closed yet. The papers are published within the "Accepted papers online" policy.

Janowicz M., Kaleta J., Wrzeciono P., Zembrzuski A.:
Acoustic Carpets      Open Access    Accepted paper online
MGV vol. 25, no. 1/4, 2016, pp. 3-12.
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.
Key words: acoustics, Euler equations, split-operator method, visualization of physical fields.

Janowicz M., Kaleta J., Wrzeciono P., Zembrzuski A., Or³owski A.:
Visualization of Nonlocality in Coupled Map Latices      Open Access    Accepted paper online
MGV vol. 25, no. 1/4, 2016, pp. 13-25.
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.
Key words: coupled map lattices, nonlocality, density matrix, visualization.

Walczak J., Wojciechowski A.:
Improved Gender Classification Using Discrete Wavelet Transform and Hybrid Support Vector Machine      Open Access    Accepted paper online
MGV vol. 25, no. 1/4, 2016, pp. 27-34.
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.
Key words: computer vision, gender recognition, DWT, SVM.

Zeler W., Rohleder P.:
Particle Effect System for the Needs of a Modern Video Game Using the GPU      Open Access    Accepted paper online
MGV vol. 25, no. 1/4, 2016, pp. 35-44.
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.
Key words: GPU, particles, FX, compute, shader, real time, graphics.

Kumar M., Jindal M. K., Sharma R. K., Jindal S. R.:
Offline Handwritten Pre-Segmented Character Recognition of Gurmukhi Script      Open Access    Accepted paper online
MGV vol. 25, no. 1/4, 2016, pp. 45-55.
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.
Key words: feature extraction, classification, PCA, k-NN, SVM, MLP.


24 (2015) main forthcoming papers

Last updated October 11, 2017