Master Degree / Yüksek Lisans Tezleri
Permanent URI for this collectionhttps://hdl.handle.net/11147/3008
Browse
2 results
Search Results
Master Thesis Deep Learning Based Real-Time Sequential Facial Expression Analysisusing Geometric Features(01. Izmir Institute of Technology, 2023) Köksal, Talha Enes; Gümüş, AbdurrahmanIn this thesis, macro and micro facial expression sequences from various datasets are trained using neural networks to classify them in one of the basic emotions. In macro expression experiments, for each frame of the sequences facial landmarks are extracted using MediaPipe FaceMesh solution and geometric features using both spatial and temporal information based on these landmarks are created. To classify the features, ConvLSTM2D followed by multilayer perceptron blocks are used. In order to achieve real time classification performance, all algorithms are implemented compatible to run on GPU. The proposed method for macro expressions is tested with CK+, Oulu-CASIA VIS, Oulu-CASIA NIR and MMI datasets. In micro expression experiments, apart from geometric features also blendshape features provided by MediaPipe are used. In order to improve classification performance, Phase-Based Video Motion Processing technique is used to magnify subtle facial movements of micro expressions. Experiments are conducted separately on same classification layers that consist of ConvLSTM1D followed by multilayer perceptron blocks. The proposed method for micro expressions is tested with SAMM and CASME II datasets. The datasets utilized in this study were accessed upon signing corresponding license agreements. Each dataset is specifically designated for academic purposes and is made available under these agreements. Only data from subjects who provided consent for their information to be used in publications was included in the thesis. The license agreements for each dataset can be found in the appendices section.Master Thesis Development of Real Time Blood Vessel Imaging System for Early Diagnosis of Vascular Diseases(01. Izmir Institute of Technology, 2020) Altay, Ayşe; Gümüş, AbdurrahmanDisorders in the circulatory system may cause various diseases and tissue damage. The early detection of abnormalities in blood circulation has an important role in terms of treatment and also raising awareness of the patient. Vascular imaging methods used by today's technology are invasive, and/ or radiation-based. As an alternative to high-cost near infrared (NIR) vascular imaging devices in the market, a microcomputer-based, real-time, non-contact and safe vascular imaging system has been developed with low- cost. Due to the higher absorption coefficient of blood than skin and fat and also the differences in the spectra of oxy and deoxyhemoglobin in blood, the vascular structures were obtained using light at NIR region. A device, which uses NIR LED light operated at 850 nm, was designed using optical and electronic components. Image and video analysis were performed using OpenCV, which is an open-source software library, and data visualization libraries. Tests were carried out to optimize the best imaging conditions for the device. To be able to show abnormalities in the vascular structures and to test the effectiveness of the device, "diabetes", which can cause various vascular disease complications, was selected. Superficial vascular structures were observed in the near infrared images captured from people at different stages of this disease. As expected, the vessel images captured from the participants revealed deterioration in vascular structures in diabetic patients compared to healthy people. In order to make a clear inference about the accuracy of the images, it is necessary to compare them to the angiography images of the individuals and be interpreted by vascular surgery specialist.