J. Turan

Invariant image recognition experiment with Trace transform

This paper presents the deals with the problem of invariant image recognition. The design of invariant image recognition system based on the Trace transform is presented. The basics of Trace transform, functional and triple features is briefly presented. Developed invariant image recognition system performance was evaluated in experiments with recognition of original images and their different modifications.

Parameter estimation based on Hough transform

Although the Hough transform is mainly used in image processing for its robustness to impulsive noise, it can be applied to nonimage data. This technique with the new modification of Hough transform - continuous Kernel Hough transform - has been applied to parameter estimation for linear models. The experimental results confirm the efficiency of the proposed estimation algorithm also its comparison with the known technique of estimation - the least square method.

Web- based multimedia courseware: applied photonics

Distance education and nontraditional classrooms have the capability to reach more students using specialised instruction, self-paced learning and virtual laboratories (and/or virtual instruments). While a good learning experience can be obtained from such a purely simulation systems, in many situations, it is commonly recognised that effective and complete learning, especially in engineering and science, requires a mixture of theoretical and practical sessions. This paper presents development work to design multimedia courseware: applied photonics. This courseware is based on: 1) multimedia document about the basic theory of applied photonics; 2) simulation and measurement supporting multimedia programme package able solving selected CAD and CAE problems in applied photonics. As special application of practical session web-based interactive fiber optic instrument is described in details.

Multimedia courseware: applied photonics

The proposed paper presents development work related to create distance education courseware: applied photonics. In order to minimize the cost at the end-user domain, simple WWW browser with fundamental plug-in (Java applets, HTML pages and LabWindows applets) to support the remote control and video transmission functionality of the system is proposed. The proposed system was tested with remote teaching of MSc and PhD students

Invariant Image Recognition Using Trace Transform and Function of Autocorrelation

The objective of this paper is to present model of invariant image recognition system based on the Trace transform. Due to possible variability of used functional, the properties of function of autocorrelation were examined. Developed invariant image recognition system performance was evaluated in experiments with recognition of original images and their different modifications

Development parameter estimation using continuous Kernel Hough transform method

The paper suggests parameter estimation development of linear systems using new approach - continuous Kernel Hough transform. Definition of continuous Kernel Hough transform, system identification and basics of parameter estimation are presented. Parameters of linear models have been estimated in experiments and the experimental results have been compared with the well-known technique of estimation - the least square method.

WWW-based remote access to engineering laboratory

This paper introduces development work to create Web-controlled laboratory modules (equipments) in applied photonics distance education courseware. The users can select and configure module parameters to investigate the behaviour of Web-controlled fiber optic refractometer and optical fiber connection test bench.

Experiments with new system identification tool based on Continuous Kernel Hough Transform

The paper describes parameter estimation of linear systems using a new approach - continuous kernel Hough transform. Definition of continuous kernel Hough transform, basics of parameter estimation and the system identification tool are presented. Parameters of linear models have been estimated in experiments and the experimental results have been compared with the well-known technique of estimation - the least square method.