|
|
Neural Network Based Edge Detection
Janda, Miloš ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
Aim of this thesis is description of neural network based edge detection methods that are substitute for classic methods of detection using edge operators. First chapters generally discussed the issues of image processing, edge detection and neural networks. The objective of the main part is to show process of generating synthetic images, extracting training datasets and discussing variants of suitable topologies of neural networks for purpose of edge detection. The last part of the thesis is dedicated to evaluating and measuring accuracy values of neural network.
|
|
|
Evaluation of Object Detection in Image
Černošek, Bedřich ; Behúň, Kamil (referee) ; Zemčík, Pavel (advisor)
The main goal of this bachelor's thesis was to propose the evaluation method of object detection. Result of this work was to create a program which performs the evaluation of object detection on suitable data sample and intuitively displays result to user. The task was to propose suitable experiments and dataset for proving correctness of evaluation. Part of this work was to find optimal parameters for face detection and optimal photo preprocessing before the face detection.
|
|
|
The role of sentinel lymph node biopsy in the management of patients with early-stage cervical cancer
Kocián, Roman ; Cibula, David (advisor) ; Roztočil, Aleš (referee) ; Špaček, Jiří (referee)
The sentinel lymph node biopsy is part of recommended surgical staging guidelines in patients with early stages of cervical cancer. High success rates of bilateral detection of SLN are achieved in sites with adequate experience with this procedure. The sentinel lymph node biopsy without systematic pelvic lymph node dissection is currently considered inadequate procedure for stages IB to IIA of the disease. One of the benefits of sentinel lymph node detection is extensive histopathological examination using the ultrastaging protocol enabling detection of small metastases (i.e. micrometastases). At the moment, there is lack of evidence about oncological safety of sentinel lymph node biopsy which might replace systematic lymph node dissection in the future. Prognostic significance of micrometastases is also controversial due to the lack of data about their potential presence in non-sentinel lymph nodes in cases with negative sentinel lymph nodes. This dissertation deals with the concept of sentinel lymph node biopsy in the cervical cancer and focuses on several topics. We have shown that the presence of micrometastasis is associated with significant negative impact on patients' prognosis on the largest retrospective cohort of patients ever published. Only 67% of patients with micrometastasis have...
|
|
|
Neural Network Based Edge Detection
Janda, Miloš ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
Aim of this thesis is description of neural network based edge detection methods that are substitute for classic methods of detection using edge operators. First chapters generally discussed the issues of image processing, edge detection and neural networks. The objective of the main part is to show process of generating synthetic images, extracting training datasets and discussing variants of suitable topologies of neural networks for purpose of edge detection. The last part of the thesis is dedicated to evaluating and measuring accuracy values of neural network.
|
|
|
Evaluation of Object Detection in Image
Černošek, Bedřich ; Behúň, Kamil (referee) ; Zemčík, Pavel (advisor)
The main goal of this bachelor's thesis was to propose the evaluation method of object detection. Result of this work was to create a program which performs the evaluation of object detection on suitable data sample and intuitively displays result to user. The task was to propose suitable experiments and dataset for proving correctness of evaluation. Part of this work was to find optimal parameters for face detection and optimal photo preprocessing before the face detection.
|
guest ::
