|
|
Impact of color models on performance of convolutional neural networks
Šimunský, Martin ; Doležel, Petr (referee) ; Škrabánek, Pavel (advisor)
Current knowledge about impact of colour models on performance of convolutional neural network is investigated in the first part of this thesis. The experiment based on obtained knowledge is conducted in the second part. Six colour models HSV, CIE 1931 XYZ, CIE 1976 L*a*b*, YIQ a YCbCr and deep convolutional neural network ResNet-101 are used. RGB colour model achieved the highest classification accuracy, whereas HSV color model has the lowest accuracy in this experiment.
|
|
|
An application for color coordinate transforms and color mixing
Jurzykowski, Michal ; Štukavec, Radim (referee) ; Slanina, Martin (advisor)
The most important human sense is sight. We can see thanks to eyes, which are very sensitive on small part of electromagnetic wave. White sunlight contents all the spectrum visible. By decomposition of white sunlight we get colour spectrum. We recognize colours by cones, which are sensitive on red, green and blue spectrum of white light. Informer times it was denited many colour models, which have been using additive and subtractive method od mixing colours. One of the first models which were matemacily defined was CIE 1931, also known as XYZ. Together with this model was created xy chromatic diagram for displaying of colour space. Best known colour models are RGB and CMY. In TV technics is used model YUV. Models HSV and HSL are more intuitiv. This models have three basic parameters: hue, saturation and brightness.
|
|
|
Impact of color models on performance of convolutional neural networks
Šimunský, Martin ; Doležel, Petr (referee) ; Škrabánek, Pavel (advisor)
Current knowledge about impact of colour models on performance of convolutional neural network is investigated in the first part of this thesis. The experiment based on obtained knowledge is conducted in the second part. Six colour models HSV, CIE 1931 XYZ, CIE 1976 L*a*b*, YIQ a YCbCr and deep convolutional neural network ResNet-101 are used. RGB colour model achieved the highest classification accuracy, whereas HSV color model has the lowest accuracy in this experiment.
|
|
|
An application for color coordinate transforms and color mixing
Jurzykowski, Michal ; Štukavec, Radim (referee) ; Slanina, Martin (advisor)
The most important human sense is sight. We can see thanks to eyes, which are very sensitive on small part of electromagnetic wave. White sunlight contents all the spectrum visible. By decomposition of white sunlight we get colour spectrum. We recognize colours by cones, which are sensitive on red, green and blue spectrum of white light. Informer times it was denited many colour models, which have been using additive and subtractive method od mixing colours. One of the first models which were matemacily defined was CIE 1931, also known as XYZ. Together with this model was created xy chromatic diagram for displaying of colour space. Best known colour models are RGB and CMY. In TV technics is used model YUV. Models HSV and HSL are more intuitiv. This models have three basic parameters: hue, saturation and brightness.
|
guest ::
