|
|
Effect of Noise on Image Compression
Pavlík, Jiří ; Svoboda, Pavel (referee) ; Bařina, David (advisor)
This thesis examines effect of different types of noise on performance of significant image compression formats. Three different types of noise are examined, Gaussian noise, Gaussian noise with bigger granularity and shot noise. Two older loosy image compression formats JPEG and JPEG 2000 are compared with newer format WebP. This examination is based on results of experiments with images, which are intentionally degraded by noise, then compressed to examined formats and compared with result of experiments for original images without noise. The effect of noise on performance of comparised formats is based on image quality metric SSIM. From results of experiments, Gaussian noise with bigger granularity seems to be the least distruptive from all types of noises. The other two types of noise have much more dwindling effect on quality of images.
|
|
|
Neural Network Based Edge Detection
Jamborová, Soňa ; Grézl, František (referee) ; Švub, Miroslav (advisor)
This work is about suggestion and implementation of the software for detection of edges in images using neurons network. It defines basic terms for this topic and focusing mainly at preperation imaging imformation for detection using nerons network. Describing and comparing different aproachings for using implemented software on synthetic and real set of images, including experiments.
|
|
|
Subjective quality evaluation of video sequences
Krmela, Tomáš ; Fliegel, Karel (referee) ; Polák, Ladislav (advisor)
This master´s work is focused on the comparison of subjective assessment of the quality of video sequences. In this study, data are obtained by hardware and sofware techniques and they are compared. In the introduction, methods of video compressions are described. The main part of this work deals wtih the exploring of different methods of subjective assessment of the quality of video sequences. Finally, obtained results from different methods, are evaluated and discussed.
|
|
|
Implementation of edge detector using wavelet transform
Pálka, Zbyněk ; Rášo, Ondřej (referee) ; Růčka, Lukáš (advisor)
This thesis is focused on edge detection in image. In theoretical part are contained genarally used methods of edge detection using first and second-order derivate and both of mentioned methods are described here. Further it’s deiscribed here continuous, descrete and two dimensional descrete wavelet transform and process of noise removing in image by descrete wavelet transform. In next part are analysed two methods of edge detection using wavelet transform and their possible realizations in program Matlab. In practical part of thesis is in detail described algorithm of program on edge detection using wavelet transform and it‘s described here individual functions of program. The main content of practical part are visual results of wavelet edge detector and their comparison with Canny, Prewitt and Sobel edge detector.
|
|
|
Neural Network Based Image Segmentation
Jamborová, Soňa ; Řezníček, Ivo (referee) ; Žák, Pavel (advisor)
This work is about suggestion of the software for neural network based image segmentation. It defines basic terms for this topics. It is focusing mainly at preperation imaging information for image segmentation using neural network. It describes and compares different aproaches for image segmentation.
|
|
|
Effect of Noise on Image Compression
Pavlík, Jiří ; Svoboda, Pavel (referee) ; Bařina, David (advisor)
This thesis examines effect of different types of noise on performance of significant image compression formats. Three different types of noise are examined, Gaussian noise, Gaussian noise with bigger granularity and shot noise. Two older loosy image compression formats JPEG and JPEG 2000 are compared with newer format WebP. This examination is based on results of experiments with images, which are intentionally degraded by noise, then compressed to examined formats and compared with result of experiments for original images without noise. The effect of noise on performance of comparised formats is based on image quality metric SSIM. From results of experiments, Gaussian noise with bigger granularity seems to be the least distruptive from all types of noises. The other two types of noise have much more dwindling effect on quality of images.
|
|
|
Neural Network Based Edge Detection
Jamborová, Soňa ; Grézl, František (referee) ; Švub, Miroslav (advisor)
This work is about suggestion and implementation of the software for detection of edges in images using neurons network. It defines basic terms for this topic and focusing mainly at preperation imaging imformation for detection using nerons network. Describing and comparing different aproachings for using implemented software on synthetic and real set of images, including experiments.
|
|
|
Neural Network Based Image Segmentation
Jamborová, Soňa ; Řezníček, Ivo (referee) ; Žák, Pavel (advisor)
This work is about suggestion of the software for neural network based image segmentation. It defines basic terms for this topics. It is focusing mainly at preperation imaging information for image segmentation using neural network. It describes and compares different aproaches for image segmentation.
|
|
|
Implementation of edge detector using wavelet transform
Pálka, Zbyněk ; Rášo, Ondřej (referee) ; Růčka, Lukáš (advisor)
This thesis is focused on edge detection in image. In theoretical part are contained genarally used methods of edge detection using first and second-order derivate and both of mentioned methods are described here. Further it’s deiscribed here continuous, descrete and two dimensional descrete wavelet transform and process of noise removing in image by descrete wavelet transform. In next part are analysed two methods of edge detection using wavelet transform and their possible realizations in program Matlab. In practical part of thesis is in detail described algorithm of program on edge detection using wavelet transform and it‘s described here individual functions of program. The main content of practical part are visual results of wavelet edge detector and their comparison with Canny, Prewitt and Sobel edge detector.
|
|
|
Subjective quality evaluation of video sequences
Krmela, Tomáš ; Fliegel, Karel (referee) ; Polák, Ladislav (advisor)
This master´s work is focused on the comparison of subjective assessment of the quality of video sequences. In this study, data are obtained by hardware and sofware techniques and they are compared. In the introduction, methods of video compressions are described. The main part of this work deals wtih the exploring of different methods of subjective assessment of the quality of video sequences. Finally, obtained results from different methods, are evaluated and discussed.
|
guest ::
