|
|
Deep learning based face recognition in real conditions
Horňáková, Veronika ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This bachelor thesis explores the area of face recognition using deep learning technique. Face recognition is used for two main reasons: verification and identification. In this thesis we describe the techniques of deep learning, mostly the convolutional neural networks, which are the most significant method for processing images - detection, classification and segmentation of the image. The process of face recognition is divided into four main steps: face detection, face selection, face extraction and face classification. We chosen three of the existing programs for face recognition (OpenFace, FaceNet and Face_Recognition), which are described in this thesis, in particular the principle of the human face recognition. Thanks to the tests with the data set of Labeled Faces in the Wild (LFW) we could specify the accuracy and the time requirement of each application. Testing of FaceNet and Face_Recognition ran on real data with face detection in video with complicated conditions. The test compares two images and tries to determine if is the same person. The test results are show in graph and table.
|
|
|
Image based flower recognition
Jedlička, František ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This paper is focus on flowers recognition in an image and class classification. Theoretical part is focus on problematics of deep convolutional neural networks. The practical part if focuse on created flowers database, with which it is further worked on. The database conteins it total 13000 plant pictures of 26 spicies as cornflower, violet, gerbera, cha- momile, cornflower, liverwort, hawkweed, clover, carnation, lily of the valley, marguerite daisy, pansy, poppy, marigold, daffodil, dandelion, teasel, forget-me-not, rose, anemone, daisy, sunflower, snowdrop, ragwort, tulip and celandine. Next is in the paper described used neural network model Inception v3 for class classification. The resulting accuracy has been achieved 92%.
|
|
|
Viewpoints of German classical idealism used, not used and misused in social theory
Kříž, Petr ; Balon, Jan (advisor) ; Císař, Ondřej (referee)
In this thesis viewpoints of Hegel's philosophy of history were confronted with selected fields of 20th century social theory. The Enlightenment was chosen as a keyword. In Hegel's Phenomenology of Mind the Enlightenment is a mode of experience of consciousness, or a phenomenon of Spirit in its history, a phenomenon which is becoming outdated in his time. To illustrate such overcome this conception of Enlightenment is demonstrated on Kant's article The answer to a Question: What is Enlightenment?. Thesis then examines the way in which had Hegel's interpretation inspired Critical theory - specifically Adorno's and Horkheimer's Dialectic of Enlightenment and Marcuse's Reason and Revolution. The last part of thesis is focused on the broader field of social theory to find manifestations of thought stream begun by Hegel. It finds it out especially in thought of Gadamer in considerably radical form calling to a question the epistemology of humanities till his present. Viewpoints emerged from Hegel's philosophical reaction to the Enlightenment represent still current counterpart of neopositivist approaches and a relevant reference point in epistemological uncertainty and in finding out an adequate socio-historical role of humanities.
|
|
|
Changes in perception of subjective vertical in cerebrovascular accident patients
Kříž, Petr ; Čakrt, Ondřej (advisor) ; Bitnar, Petr (referee)
Cerebro-vascular accident often affects parts of brain responsible for spatial orientation. Optimal integration of afference from visual, somatosensory and vestibular system is necessary for maintaining balance and often in the end for the functional indepencence of the patient. Examination of subjective vertical is a sensitive signifier for spatial orientation and the ability to discern graviception. By using clinical examination of subjective visual vertical it is possible to objectify and quantify graviception disorder excluding visual context. Current level of understanding in this field is briefly summarized in theoretical part of this study. In practical part subjective visual vertical examination by bucket-method was for statistically comparison of 29 patients after a cerebro- vascular accident with 34 healthy seniors. Hypotheses about the influence of a side of a lesion and a time elapsed since the lesions were also tested. The study concludes that the perception of verticality in patients after cerebro- vascular accident can be severely affected. Additionally, the study highlights the reliability of examination of patients after cerebro-vascular accident using clinically practical bucket-method.
|
|
|
Video stabilization using global optimization algorithms
Bartoš, Patrik ; Říha, Kamil (referee) ; Kříž, Petr (advisor)
This bachelor thesis focuses on video stabilization using CRS (Controlled Random Search) and GA (Genetic Algorithm) optimization algorithms. It describes registration process, geometrical transformations, interpolation methods, similarity criteria and optimization algorithms. It also briefly describes structure of the program created in MATLAB. Finally it contains results of achieved stabilization.
|
|
|
Measuring positions of objects using a pair of cameras
Sláma, Adam ; Říha, Kamil (referee) ; Kříž, Petr (advisor)
The thesis focuses on acquiring spatial information of a digital image. Simple measuring device consists of two static cameras and of a created software, which is able to find the coordinates of measured object in the sensing area with certain accuracy due to the reference coordinate system. The program was formed in the development environment Microsoft Visual Studio 2015 using package of OpenCV libraries in C++ programming language. The program is based on calibration of image, determination of the global and pixel coordinates and on triangulation method.
|
|
|
Corrosion resistant and heat resistant steels
Kříž, Petr ; Tulka, Jaromír (referee) ; Molliková, Eva (advisor)
This bachelor thesis deals with stainless steels and heat resistant steels. It speaks about their chemical composition, heat treatment, structure and options of its practical usage in various fields. One of its parts is also focused on corrosion in general, corrosion types, economic impacts, kinds of corrosion attacks and factors which affect her.
|
|
|
Recognition of persons clothing in the video signal
Mlýnková, Barbora ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This paper is dealing with the detection clothes characteristics in the picture, for the use of person identification. These characteristics are described and categorized. It also deals with the design of the database structure, which works with masks and categories of characteristics for their processing. This work uses haar cascades to detect face and to determine the position of clothing for the purpose of color detection
|
|
|
Detection of changes in digital images
Dorazil, Jan ; Kříž, Petr (referee) ; Říha, Kamil (advisor)
This thesis concerns with change detection problematics in digital images captured under indoor conditions with an ordinary integrated camera in two consecutive moments. All challenges that accompany this problem will be discussed, starting with preprocessing and arriving to evaluation of the results. Currently used methods from this field are described and compared with each other such as differencing and LCP (Local Correlation Peak). A novel method, based on LTP descriptors, effectively solving this problem is proposed in this work. The proposed method is then tested on real data. The results of this tests are discussed subsequently. Besides the change detection method a method for parallax error minimization is proposed here.
|
|
|
Tracking the movement of objects in the video signal
Šidó, Balázs ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
Tato diplomova prace se zameruje na sledovani pohybu vice objektu. Prace popisuje dve implementace filtru, ktere jsou v podstate zalozeny na principu Kalmanova filtru. Obe implementace jsou zalozeny na principu sledovani vice objektu, na zaklade znalosti pozic vsech objektu v kazdem snimku. Prvni implementace je smisena verze Globalniho a Standardniho filtru nejblizsich sousedu. Druha implementace je postavena na pravde- podobnostnim pristupu k procesu sdruzeni. Posledni kapitola poskytuje srovnani mezi temito filtry a Zakladnim filtrem. Algoritmy byly realizovany v jave.
|
guest ::
