Łukasz Gierz

Design of an effective platform for unmanned aerial vehicles to collect research material in the form of aerial photographs

This thesis presents the process of designing and manufacturing an unmanned aerial vehicle in purpose of collecting research materials in the form of photos from air. Priority of the project was to analyze the available materials and manufacture a low-weight construction, using appropriate electronic components, so that the flight time on a single battery charge was as long as possible. An important aspect was also the reduction of manual operating - automatic flight by use of marked geographical coordinates and automatic shutter-release of camera in very specific points. All of these has been analyzed to verify the assumptions.

Methodology of data processing in the process of neural image analysis of pork half carcasses

This article describes data processing in neural analysis of the images of pork half carcass. Parameters of pork halfcarcass obtained from three-dimensional analysis, was processed into form of 130 files. These files has been used as learning sets for the artificial neural network simulator - STATISTICA. Next, we obtained the set of neural models from which the best was chosen. For all data processing activities in this research process were used applications developed in C # in the Visual Studio 2015 development environment.

Unsupervised neural classification of six chosen apple pests using learned vector quantization agorithm

The aim of this work was a neural identification of selected apple tree orchard pests in Poland. The classification was conducted on the basis of graphical information coded in the form of selected geometric characteristics of agrofags, presented on digital images. A neural classification model is presented in this paper, optimized using learning files acquired on the basis of information contained in digital photographs of pests. There has been identified 6 selected apple pests, the most commonly encountered in Polish orchards, has been addressed. In order to classify the chosen agrofags, neural networks type Self-Organizing Feature Map (SOFM) methods supported Learned Vector Quantization (LVQ) algorithm were utilized, using by digital analysis of image techniques.

Recognition of color changes in strawberry juice powders using self-organizing feature map

Self-Organizing Feature Map (SOFM), has been used for the qualitative identification of strawberry juice powders. The research was based on image recognition using powders obtained through an industrial spray-drying process. Results demonstrated that the color features were able to effectively distinguish the research material consisting of spray-dried powders of strawberry juice. The adequate model in terms of the lowest error value RMS (Root Mean Square) contained 46 neurons in the input layer and neurons in the output layer. The model is an effective tool for classifying wrong color changes in strawberry powders.

Validation of a photogrammetric method for evaluating seed potato cover by a chemical agent

In recent years, requirements on potato tuber quality and minimization of chemical protection measures have steadily increased. Increasingly, the precautionary measures in the protection of potato during its vegetation, using the dressing of seed material, are increasingly taking place. Growing awareness of potato producers and increasingly restrictive plant protection standards force the use of new technologies. The quality of the process of applying chemicals to the surface of tubers of seed potato material affects the subsequent quantity and quality of the crop. The aim of the study was to validate the method of evaluating the quality of seed dressing coverage in the process of spraying tubers with a chemical based on computer image analysis.