Vol. 26 (2017):
  Abstracts and Contents of Papers

25 (2016)	main	27 (2018)

No. 1/4.

Machine GRAPHICS & VISION, Vol. 26 (2017), No. 1/4

This number as one file
MGV vol. 26, no. 1/4, 2017

Burdka Ł., Rohleder P.:
Applied Inverse Kinematics for Bipedal Characters Moving on the Diverse Terrain
MGV vol. 26, no. 1/4, 2017, pp. 3-11.

A solution to the problem of adjusting the pose of an animated video game character to the diverse terrain and surroundings is proposed. It is an important task in every modern video game where there is a focus on animated characters. Not addressing this issue leads to major visual glitches such as legs hovering above the ground surface, or penetrating the obstacles while moving. As presented in this work, the described problem can be effectively solved by examining the surroundings in real-time and applying Inverse Kinematics (IK) as a procedural post process to the currently used animation.
Key words: inverse kinematics, animations, visual improvements, physics, game systems.

Martinel N., Piciarelli C., Micheloni C.:
An Ensemble Feature Method for Food Classification
MGV vol. 26, no. 1/4, 2017, pp. 13-39.

In the last years, several works on automatic image-based food recognition have been proposed, often based on texture feature extraction and classification. However, there is still a lack of proper comparisons to evaluate which approaches are better suited for this specific task. In this work, we adopt a Random Forest classifier to measure the performances of different texture filter banks and feature encoding techniques on three different food image datasets. Comparative results are given to show the performance of each considered approach, as well as to compare the proposed Random Forest classifiers with other feature-based state-of-the-art solutions.
Key words: food recognition, texture filter banks, feature encoding, Random Forest classifier.

25 (2016)	main	27 (2018)

Last updated: November 25, 2021 (DOIs added)