|
Biometric fingerprint liveness detection
Rišian, Lukáš ; Vítek, Martin
This work addresses the problem of biometric recognition of fingerprint liveness to identify and differentiate between real fingerprints and their artificial replicas. The main objective was to identify the features that are crucial for fingerprint liveness recognition and based on these features to propose an efficient classification algorithm. We worked with the LivDet database from 2009, which contains both real and fake fingerprints. This database has been used in a worldwide competition and the results of all implemented algorithms are publicly available for subsequent comparison of success rates. An important part of this work was the preprocessing of the image data, which was crucial for testing the selected features and implementing the algorithms. We analyzed more than 180 different features from which we selected the most relevant ones. We then used the selected features to develop several fingerprint recognition and classification algorithms. Using the selected features, several possible variations of the algorithms have been proposed. Among all the implemented algorithms, we achieved the best result of almost 90%. Compared to other algorithms that have been implemented for the same purpose and have been used and tested on the same database, this can be considered a satisfactory and reliable result. In conclusion, the main objective of this work was to provide an efficient, secure, and reliable solution in the field of biometric fingerprint spoof detection.
|
|
Application, analysis and evaluation of a novel medical image annotation and segmentation tools
Sucháček, Jan ; Paštěka, Richard (referee) ; Dr.Benjamin Ramberger, MSc. BSc. BSc. (advisor)
This thesis explores the creation of 3D models of the human upper airways from CT scans to enhance the understanding of complex anatomical details of the upper airways, assist in detecting pathological changes, and facilitate therapeutic decision-making. These models also enable simulation and assessment of airflow characteristics within the human upper airways. To generate these 3D models, two annotation and three segmentation methods were employed on a dataset of six patient CT scans. Various metrics, such as the number of triangles, surface area, volume, model intersection volume, Dice coefficient, and modelto-model distance, were calculated for all resulting 3D models to characterize the models and compare the methods. A detailed analysis focused on four anatomical parts: the nasal cavity with sinuses, pharynx, larynx, and trachea, was performed. Additionally, a computational fluid dynamics (CFD) simulation was conducted on one model to analyze airflow in the upper airways during breathing. This simulation provided insights into airflow dynamics inside the upper airways, potentially reducing the need for invasive examinations. The findings of this thesis demonstrate the potential of 3D upper airway models to improve diagnostic accuracy, treatment planning, and patient outcomes in respiratory medicine.and compare the methods. A detailed analysis focused on four anatomical parts: the nasal cavity with sinuses, pharynx, larynx, and trachea, was performed. Additionally, a computational fluid dynamics (CFD) simulation was conducted on one model to analyze airflow in the upper airways during breathing. This simulation provided insights into airflow dynamics inside the upper airways, potentially reducing the need for invasive examinations. The findings of this thesis demonstrate the potential of 3D upper airway models to improve diagnostic accuracy, treatment planning, and patient outcomes in respiratory medicine.
|
|
Fusing image and non-grid-like data for object segmentation
Repka, Samuel ; Nosko, Svetozár (referee) ; Zemčík, Pavel (advisor)
Objekt záujmu sa často dá popísať viacerými dátovými zdrojmi. Napríklad, z obrazu auta sa dá zistiť farba, značka, alebo aj jeho typ. Čo sa ale najskôr nedá, je zistiť stav motora, či beží alebo nie. Táto informácia sa ale dá zistiť inak, sluchom alebo aj dotykom. Aj keď je možné, že jeden dátový zdroj poskytuje všetky potrebné informácie, pridanie modality môže zlepšiť riešenie, kvôli možnej komplementarite dát. Tento proces dátovej fúzie môže byť ale pomerne komplikovaný proces. Rôzne dáta majú rôzne vlastnosti, štruktúry a rôzne výzvy, ktoré s nimi súvisia. Existuje veľké množstvo rôznych metód dátovej fúzie, ktoré sú ale často aplikovateľné len na konkrétne modality. Táto práca prezentuje nový prístup k dátovej fúzii dvoch modalít, primárne za účelom segmentácie obrazu. Jedna z modalít je obraz, druhá je ľubovoľná neštrukturovaná modalita. Prezentovaná metóda využíva graf na spoločnú reprezentáciu oboch modalít, dizajnovanú tak, aby čo najpresnejšie zachytila závislosti v modalitách aj medzi nimi. Graf je potom spracovaný, výsledkom čoho je graf so spojenými dátami, alebo aj priama segmentácia. Prezentované riešenie bolo otestované na dvoch datasetoch (z oblasti mineralógie a drevárskeho priemyslu) a porovnané s inými metódami. Výsledky ukazujú, že riešenie má veľký potenciál ale aj svoje limitácie. V prípade datasetu z mineralógie, výsledky boli výborné a ukazujú, že metóda je schopná dátovej fúzie a dokáže prekonať aj súčasné metódy vo viacerých metrikách. V druhom prípade, výsledky až tak jednoznačné neboli, pretože metóda nevylepšila výsledky v porovnaní s iným riešením, čo ale mohlo byť spôsobené aj ťažkým datasetom.
|
|
Segmentation of hyperspectral images of lizards
Kotrys, Kryštof ; Parák, Roman (referee) ; Škrabánek, Pavel (advisor)
Tato diplomová práce se zaměřuje na tvorbu systému pro segmentaci hyperspektrálních fotografií ještěrek žijících na území České republiky. První část práce obsahuje shrnutí existujících metod segmentace obrazu, informací o hyperspektrálním obrazu a konvolučních neuronových sítí. Druhá část práce navrhuje postup pro zpracování dat, které vede k tvorbě segmentovaných masek pro zadanou datovou množinu a také prezentuje získané výsledky.
|
|
Biometric fingerprint liveness detection
Rišian, Lukáš ; Smital, Lukáš (referee) ; Vítek, Martin (advisor)
This bachelor thesis deals with the problem of biometric fingerprint liveness recognition. The aim of the thesis is to propose a solution that reliably and securely recognizes fake fingerprints from genuine ones. Specifically, the work focuses on investigating methods for detecting fingerprint liveness using software tools, creating a custom fingerprint test database, testing and identifying relevant characteristics for successful liveness detection, and using them to implement fingerprint liveness recognition algorithms. Another goal was to create a GUI to provide a tool for overall detection. The work includes an analysis of the basics of biometrics, fingerprint characteristics and structure, current sensors used for fingerprint extraction, databases used, image preprocessing methods, tested features, implemented algorithms, and two GUI variants. More than 180 different image features were tested and more than 20 variants of algorithms were implemented. From these algorithms, the best ones were selected, whose detection results were then compared with those of foreign authors. The best algorithm achieved an accuracy of almost 90%, which can be considered a reliable and satisfactory result compared to foreign authors.
|
|
Creating 3D Model of Temporomandibular Joint
Šmirg, Ondřej ; Bartušek, Karel (referee) ; Liberda,, Ondřej (referee) ; Smékal, Zdeněk (advisor)
The dissertation thesis deals with 3D reconstruction of the temporomandibular joint from 2D slices of tissue obtained by magnetic resonance. The current practice uses 2D MRI slices in diagnosing. 3D models have many advantages for the diagnosis, which are based on the knowledge of spatial information. Contemporary medicine uses 3D models of tissues, but with the temporomandibular joint tissues there is a problem with segmenting the articular disc. This small tissue, which has a low contrast and very similar statistical characteristics to its neighborhood, is very complicated to segment. For the segmentation of the articular disk new methods were developed based on the knowledge of the anatomy of the joint area of the disk and on the genetic-algorithm-based statistics. A set of 2D slices has different resolutions in the x-, y- and z-axes. An up-sampling algorithm, which seeks to preserve the shape properties of the tissue was developed to unify the resolutions in the axes. In the last phase of creating 3D models standard methods were used, but these methods for smoothing and decimating have different settings (number of polygons in the model, the number of iterations of the algorithm). As the aim of this thesis is to obtain the most precise model possible of the real tissue, it was necessary to establish an objective method by which it would be possible to set the algorithms so as to achieve the best compromise between the distortion and the model credibility achieve.
|
|
Using the Kinect sensor in detection of people
Janás, Lukáš ; Šmirg, Ondřej (referee) ; Přinosil, Jiří (advisor)
Bachelor thesis deals with the methods of people detection by using Microsoft Kinect. Depth image captured by this device is further processed by using standard algorithms from freely available OpenCV library. All of image processing methods are described in detail of their function and influence to image. The practical part of the work is focused on the realization of a simple program, which is serving for image segmentation and finding people.
|
| |
|
Person's identification by means of bipedal locomotion
Krzyžanek, Jakub ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
The aim of this thesis is to recognize a walking person in a sequence of images by defining his or her reference points to compare the course of their movement and then to identify the scanned person. Methods „k-means“ and „mean shift“ are used to obtain the silhouette of the person. However “environment model estimation” method is used here before those mentioned above. It is a type of a difference method and it helps to specify the scanning area and shortens the time of segmentation. During the search for the reference points the thesis focuses on three areas: the centre of the head and both ankle joints. Those points are later determined on the previous image sequence and compared with the real locations of the centre of the head and ankle joints marked by the user. The thesis also focuses on comparing the movement courses of those points and tries to identify the people whose walks are being scanned. Problematic situations which occurred during the whole process are analyzed in the end. The result of the thesis is an algorithm which can locate a moving person in an image sequence (video) and determine the reference points (centre of the head and ankles) to compare them and identify the scanned person.
|
|
Neural Network Based Image Segmentation
Vrábelová, Pavla ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
This paper deals with application of neural networks in image segmentation. First part is an introduction to image processing and neural networks, second part describes an implementation of segmentation system and presents results of experiments. The segmentation system enables to use different types of classifiers, various image features extraction and also to evaluate the success of segmentation. Two classifiers were created - a neural network (self-organizing map) and an algorithm K-means. Colour (RGB and HSV) and texture features and their combinations were used for classification. Texture features were extracted using a set of Gabor filters. Experiments with designed classifiers and feature extractors were carried out and results were compared.
|