Thesis studied correlations between swallowing accelerometry parameters and anthropometrics in 50 healthy participants. Anthropometrics include: age, gender, weight, height, body fat percent, neck circumference and mandibular length. Dual-axis swallowing signals, from a biaxial accelerometer were obtained for 5-saliva and 10-water (5-wet and 5-wet chin-tuck) swallows per participant. Two patient-independent automatic segmentation algorithms using discrete wavelet transforms of swallowing sequences segmented: 1) saliva/wet swallows and 2) wet chin-tuck swallows. Extraction of swallows hinged on dynamic thresholding based on signal statistics. Canonical correlation analysis was performed on sets of anthropometric and swallowing signal variables including: variance, skewness, kurtosis, autocorrelation decay time, energy, scale and peak-amplitude. For wet swallows, significant linear relationships were found between signal and anthropometric variables. In superior-inferior directions, correlations linked weight, age and gender to skewness and signal-memory. In anterior-posterior directions, age was correlated with kurtosis and signal-memory. No significant relationship was observed for dry and wet chin-tuck swallowing

Thesis studied correlations between swallowing accelerometry parameters and anthropometrics in 50 healthy participants. Anthropometrics include: age, gender, weight, height, body fat percent, neck circumference and mandibular length. Dual-axis swallowing signals, from a biaxial accelerometer were obtained for 5-saliva and 10-water (5-wet and 5-wet chin-tuck) swallows per participant. Two patient-independent automatic segmentation algorithms using discrete wavelet transforms of swallowing sequences segmented: 1) saliva/wet swallows and 2) wet chin-tuck swallows. Extraction of swallows hinged on dynamic thresholding based on signal statistics. Canonical correlation analysis was performed on sets of anthropometric and swallowing signal variables including: variance, skewness, kurtosis, autocorrelation decay time, energy, scale and peak-amplitude. For wet swallows, significant linear relationships were found between signal and anthropometric variables. In superior-inferior directions, correlations linked weight, age and gender to skewness and signal-memory. In anterior-posterior directions, age was correlated with kurtosis and signal-memory. No significant relationship was observed for dry and wet chin-tuck swallowing

The presented diploma thesis deals with the division of points into homogeneous groups. The work provides a broad overview of the current state in this topic and a brief explanation of the main segmentation methods principles. From the analysis of the articles are selected and programmed five algorithms. The work defines the principles of selected algorithms and explains their mathematical models. For each algorithm is also given a code design description. The diploma thesis also contains a cross comparison of segmentation capabilities of individual algorithms on created as well as on measured data. The results of the curves extraction are compared with each other graphically and numerically. At the end of the work is a comparison graph of time dependence on the number of points and the table that includes a mutual comparison of algorithms in specific areas.

Prostate segmentation is a required step in determining the volume of a prostate, which is very important in the diagnosis and the treatment of prostate cancer. In the past, radiologists manually segment the two-dimensional cross-sectional ultrasound images. Typically, it is necessary for them to outline at least a hundred of cross-sectional images in order to get an accurate estimate of the prostate's volume. This approach is very time-consuming. To be more efficient in accomplishing this task, an automated procedure has to be developed. However, because of the quality of the ultrasound image, it is very difficult to develop a computerized method for defining boundary of an object in an ultrasound image. The goal of this thesis is to find an automated segmentation algorithm for detecting the boundary of the prostate in ultrasound images. As the first step in this endeavour, a semi-automatic segmentation method is designed. This method is only semi-automatic because it requires the user to enter four initialization points, which are the data required in defining the initial contour. The discrete dynamic contour (DDC) algorithm is then used to automatically update the contour. The DDC model is made up of a set of connected vertices. When provided with an energy field that describes the features of the ultrasound image, the model automatically adjusts the vertices of the contour to attain a maximum energy. In the proposed algorithm, Mallat's dyadic wavelet transform is used to determine the energy field. Using the dyadic wavelet transform, approximate coefficients and detailed coefficients at different scales can be generated. In particular, the two sets of detailed coefficients represent the gradient of the smoothed ultrasound image. Since the gradient modulus is high at the locations where edge features appear, it is assigned to be the energy field used to drive the DDC model. The ultimate goal of this work is to develop a fully-automatic segmentation algorithm. Since only the initialization stage requires human supervision in the proposed semi-automatic initialization algorithm, the task of developing a fully-automatic segmentation algorithm is reduced to designing a fully-automatic initialization process. Such a process is introduced in this thesis. In this work, the contours defined by the semi-automatic and the fully-automatic segmentation algorithm are compared with the boundary outlined by an expert observer. Tested using 8 sample images, the mean absolute difference between the semi-automatically defined and the manually outlined boundary is less than 2. 5 pixels, and that between the fully-automatically defined and the manually outlined boundary is less than 4 pixels. Automated segmentation tools that achieve this level of accuracy would be very useful in assisting radiologists to accomplish the task of segmenting prostate boundary much more efficiently.

Prostate segmentation is a required step in determining the volume of a prostate, which is very important in the diagnosis and the treatment of prostate cancer. In the past, radiologists manually segment the two-dimensional cross-sectional ultrasound images. Typically, it is necessary for them to outline at least a hundred of cross-sectional images in order to get an accurate estimate of the prostate's volume. This approach is very time-consuming. To be more efficient in accomplishing this task, an automated procedure has to be developed. However, because of the quality of the ultrasound image, it is very difficult to develop a computerized method for defining boundary of an object in an ultrasound image. The goal of this thesis is to find an automated segmentation algorithm for detecting the boundary of the prostate in ultrasound images. As the first step in this endeavour, a semi-automatic segmentation method is designed. This method is only semi-automatic because it requires the user to enter four initialization points, which are the data required in defining the initial contour. The discrete dynamic contour (DDC) algorithm is then used to automatically update the contour. The DDC model is made up of a set of connected vertices. When provided with an energy field that describes the features of the ultrasound image, the model automatically adjusts the vertices of the contour to attain a maximum energy. In the proposed algorithm, Mallat's dyadic wavelet transform is used to determine the energy field. Using the dyadic wavelet transform, approximate coefficients and detailed coefficients at different scales can be generated. In particular, the two sets of detailed coefficients represent the gradient of the smoothed ultrasound image. Since the gradient modulus is high at the locations where edge features appear, it is assigned to be the energy field used to drive the DDC model. The ultimate goal of this work is to develop a fully-automatic segmentation algorithm. Since only the initialization stage requires human supervision in the proposed semi-automatic initialization algorithm, the task of developing a fully-automatic segmentation algorithm is reduced to designing a fully-automatic initialization process. Such a process is introduced in this thesis. In this work, the contours defined by the semi-automatic and the fully-automatic segmentation algorithm are compared with the boundary outlined by an expert observer. Tested using 8 sample images, the mean absolute difference between the semi-automatically defined and the manually outlined boundary is less than 2. 5 pixels, and that between the fully-automatically defined and the manually outlined boundary is less than 4 pixels. Automated segmentation tools that achieve this level of accuracy would be very useful in assisting radiologists to accomplish the task of segmenting prostate boundary much more efficiently.

This thesis deals with the web page segmentation in a web browser. The implementation of Box Clustering Segmentation (BCS) method in JavaScript using an automated browser was created. The actual implementation consists of two main steps, which are the box extraction (leaf DOM nodes) from the browser context and their subsequent clustering based on the similarity model defined in BCS. Main result of this thesis is a functional implementation of BCS method usable for web page segmentation. The evaluation of the functionality and accuracy of the implementation is based on a comparison with a reference implementation created in Java.

Colour segmentation is the most commonly used method in road signs detection. Road sign contains several basic colours such as red, yellow, blue and white which depends on countries.The objective of this thesis is to do an evaluation of the four colour segmentation algorithms. Dynamic Threshold Algorithm, A Modification of de la Escalera’s Algorithm, the Fuzzy Colour Segmentation Algorithm and Shadow and Highlight Invariant Algorithm. The processing time and segmentation success rate as criteria are used to compare the performance of the four algorithms. And red colour is selected as the target colour to complete the comparison. All the testing images are selected from the Traffic Signs Database of Dalarna University [1] randomly according to the category. These road sign images are taken from a digital camera mounted in a moving car in Sweden.Experiments show that the Fuzzy Colour Segmentation Algorithm and Shadow and Highlight Invariant Algorithm are more accurate and stable to detect red colour of road signs. And the method could also be used in other colours analysis research. The yellow colour which is chosen to evaluate the performance of the four algorithms can reference Master Thesis of Yumei Liu.

In treatment of cancer using high energetic radiation the problem arises how to irradiate the tumor without damaging the healthy tissue in the immediate vicinity. In order to do this, intensity modulated radiation therapy (IMRT) is used. In this thesis, the general goal is to modulate the homogeneous radiation field delivered by an external accelerator using a multileaf collimator in comparison with beam modifying devices. In order to generate intensity modulated fields in a static mode with multileaf collimators, the heuristic algorithm of Galvin, Chen and Smith is used. This method aims at finding a segmentation with a small number of segments, taking account of mechanical constraints such as leaves can move only in one direction, on one row, the right and left leaves cannot overlap (Interleaf Collision) and also every element between the leaf and the side of the collimator to which the leaf is connected is also covered (no holes in leaves). During the implementation of the algorithm, the initial intensity matrix with the desired radiation rates is inserted and using essential transformations, a positive combination of special matrices, segments, corresponding to fixed positions of multileaf collimator are obtained. All calculations end with the superposition of segments which leads to the creation of the 3-D matrix that will be used to irradiate the tumor. The algorithm is implemented in C++. The calculations are fast and the procedure is user friendly. The model is implemented for the case of protection the spinal cord while treating a tumor in the neck area. Furthermore, dose distributions obtained with this model and beam modifying devices in the neck area were compared. / Κατά τη θεραπεία του καρκίνου με χρήση υψηλής ενέργειας ακτινοβολίας, πρόβλημα αποτελεί ο περιορισμός της ακτινοβολίας στον όγκο στόχο και ο περιορισμός της συμμετοχής του υγιούς ιστού, της γειτονικής περιοχής, στο ελάχιστο. Προκειμένου να επιλυθεί το πρόβλημα αυτό χρησιμοποιείται ακτινοθεραπεία με πεδία ακτινοβολίας διαμορφωμένης έντασης (Ιntensity Μodulated Radiαtion Therapy – IMRT), με τη βοήθεια των κατευθυντήρων πολλαπλών φύλλων (Multileaf Collimators- MLC). Στόχος της συγκεκριμένης διπλωματικής εργασίας είναι η διαμόρφωση του ομοιογενούς πεδίου ακτινοβολίας, που διανέμεται μέσω του γραμμικού επιταχυντή χρησιμοποιώντας κατευθυντήρα πολλαπλών φύλλων και η σύγκριση των αποτελεσμάτων της προσομοίωσης με τις συσκευές διαμόρφωσης δέσμης (Beam Modifying Devices). Προκειμένου να παραχθούν τα διαμορφωμένης έντασης πεδία ακτινοβολίας, σε στατική μορφή, χρησιμοποιήθηκε ο αλγόριθμος των Galvin, Chen και Smith. H μέθοδος αποσκοπεί στην τμηματοποίηση του πίνακα με τα επιθυμητά ποσοστά ακτινοβολίας σε έναν μικρό αριθμό τμημάτων “segments”, λαμβάνοντας υπόψιν μηχανικούς περιορισμούς. (i) Τα φύλλα δύναται να κινηθούν μόνο κατά μήκος μιας διεύθυνσης, (ii) σε μια γραμμή, το αριστερό και το δεξί φύλλο δεν μπορούν να επικαλυφτούν (Interleaf Collision) και (iii) κάθε στοιχείο μεταξύ του φύλλου και της πλευράς του διαμορφωτή, με την οποία είναι συνδεδεμένο, είναι πάντα καλυμμένο (Νo holes in leaves). Κατά την υλοποίηση του αλγορίθμου, εισάγεται ο αρχικός πίνακας με τα επιθυμητά ποσοστά ακτινοβολίας και με τη χρήσης κατάλληλων μετασχηματισμών, προκύπτει ένας συνδυασμός από ειδικούς πίνακες (segments), οι οποίοι αντιστοιχούν σε θέσεις των κατευθυντήρων πολλαπλών φύλλων και θα χρησιμοποιηθούν για την ακτινοβόληση του όγκου. Ο αλγόριθμος υλοποιήθηκε σε C++. Οι υπολογισμοί είναι γρήγοροι και η διεργασία είναι φιλική προς το χρήστη. Το μοντέλο υλοποιήθηκε για την περίπτωση προστασίας της σπονδυλικής στήλης κατά τη θεραπεία όγκου στην περιοχή του λαιμού. Τέλος, οι κατανομές δόσεις που προέκυψαν με την προαναφερθέν μοντέλο συγκρίθηκαν με αυτές των συσκευών διαμόρφωσης δέσμης.

This report deals with segmentation of web pages, which is important discipline of information extraction. In the first part, we describe several general ways to implement it. After that we introduce method Box Clustering Segmentation, which comes with a slightly different approach towards segmentation. In the second half, we describe implementation of this method as a part of framework FITLayout and final testing.