Triangle-mesh modeling, as one of the approaches for representing images based on nonuniform sampling, has become quite popular and beneficial in many applications. In this thesis, image representation using triangle-mesh models and its application in image scaling are studied. Consequently, two new methods, namely, the SEMMG and MIS methods are proposed, where each solves a different problem. In particular, the SEMMG method is proposed to address the problem of image representation by producing effective mesh models that are used for representing grayscale images, by minimizing squared error. The MIS method is proposed to address the image-scaling problem for grayscale images that are approximately piecewise-smooth, using triangle-mesh models. The SEMMG method, which is proposed for addressing the mesh-generation problem, is developed based on an earlier work, which uses a greedy-point-insertion (GPI) approach to generate a mesh model with explicit representation of discontinuities (ERD). After in-depth analyses of two existing methods for generating the ERD models, several weaknesses are identified and specifically addressed to improve the quality of the generated models, leading to the proposal of the SEMMG method. The performance of the SEMMG method is then evaluated by comparing the quality of the meshes it produces with those obtained by eight other competing methods, namely, the error-diffusion (ED) method of Yang, the modified Garland-Heckbert (MGH) method, the ERDED and ERDGPI methods of Tu and Adams, the Garcia-Vintimilla-Sappa (GVS) method, the hybrid wavelet triangulation (HWT) method of Phichet, the binary space partition (BSP) method of Sarkis, and the adaptive triangular meshes (ATM) method of Liu. For this evaluation, the error between the original and reconstructed images, obtained from each method under comparison, is measured in terms of the PSNR. Moreover, in the case of the competing methods whose implementations are available, the subjective quality is compared in addition to the PSNR. Evaluation results show that the reconstructed images obtained from the SEMMG method are better than those obtained by the competing methods in terms of both PSNR and subjective quality. More specifically, in the case of the methods with implementations, the results collected from 350 test cases show that the SEMMG method outperforms the ED, MGH, ERDED, and ERDGPI schemes in approximately 100%, 89%, 99%, and 85% of cases, respectively. Moreover, in the case of the methods without implementations, we show that the PSNR of the reconstructed images produced by the SEMMG method are on average 3.85, 0.75, 2, and 1.10 dB higher than those obtained by the GVS, HWT, BSP, and ATM methods, respectively. Furthermore, for a given PSNR, the SEMMG method is shown to produce much smaller meshes compared to those obtained by the GVS and BSP methods, with approximately 65% to 80% fewer vertices and 10% to 60% fewer triangles, respectively. Therefore, the SEMMG method is shown to be capable of producing triangular meshes of higher quality and smaller sizes (i.e., number of vertices or triangles) which can be effectively used for image representation. Besides the superior image approximations achieved with the SEMMG method, this work also makes contributions by addressing the problem of image scaling. For this purpose, the application of triangle-mesh mesh models in image scaling is studied. Some of the mesh-based image-scaling approaches proposed to date employ mesh models that are associated with an approximating function that is continuous everywhere, which inevitably yields edge blurring in the process of image scaling. Moreover, other mesh-based image-scaling approaches that employ approximating functions with discontinuities are often based on mesh simplification where the method starts with an extremely large initial mesh, leading to a very slow mesh generation with high memory cost. In this thesis, however, we propose a new mesh-based image-scaling (MIS) method which firstly employs an approximating function with selected discontinuities to better maintain the sharpness at the edges. Secondly, unlike most of the other discontinuity-preserving mesh-based methods, the proposed MIS method is not based on mesh simplification. Instead, our MIS method employs a mesh-refinement scheme, where it starts from a very simple mesh and iteratively refines the mesh to reach a desirable size. For developing the MIS method, the performance of our SEMMG method, which is proposed for image representation, is examined in the application of image scaling. Although the SEMMG method is not designed for solving the problem of image scaling, examining its performance in this application helps to better understand potential shortcomings of using a mesh generator in image scaling. Through this examination, several shortcomings are found and different techniques are devised to address them. By applying these techniques, a new effective mesh-generation method called MISMG is developed that can be used for image scaling. The MISMG method is then combined with a scaling transformation and a subdivision-based model-rasterization algorithm, yielding the proposed MIS method for scaling grayscale images that are approximately piecewise-smooth. The performance of our MIS method is then evaluated by comparing the quality of the scaled images it produces with those obtained from five well-known raster-based methods, namely, bilinear interpolation, bicubic interpolation of Keys, the directional cubic convolution interpolation (DCCI) method of Zhou et al., the new edge-directed image interpolation (NEDI) method of Li and Orchard, and the recent method of super-resolution using convolutional neural networks (SRCNN) by Dong et al.. Since our main goal is to produce scaled images of higher subjective quality with the least amount of edge blurring, the quality of the scaled images are first compared through a subjective evaluation followed by some objective evaluations. The results of the subjective evaluation show that the proposed MIS method was ranked best overall in almost 67\% of the cases, with the best average rank of 2 out of 6, among 380 collected rankings with 20 images and 19 participants. Moreover, visual inspections on the scaled images obtained with different methods show that the proposed MIS method produces scaled images of better quality with more accurate and sharper edges. Furthermore, in the case of the mesh-based image-scaling methods, where no implementation is available, the MIS method is conceptually compared, using theoretical analysis, to two mesh-based methods, namely, the subdivision-based image-representation (SBIR) method of Liao et al. and the curvilinear feature driven image-representation (CFDIR) method of Zhou et al.. / Graduate

This work deals with the task of image scaling using GPU paralelization. Portion of text is devoted to signal processing and his affection of whole result including measuring it's quality. Describtion of the most important methods including super-resolution is given further in the text. An important part of this thesis is library implementing choosen methods with usage of paralelization on graphic chip. Achieved results of paralelization are demonstrated on set of speed tests.

Information på webben konsumeras idag via en mängd heterogena enheter. Faktorer som nätverksunderlag och skärmupplösning påverkar vilken bild som är lämplig att leverera till klienten, då en bild i sitt originaltillstånd på en tekniskt begränsad enhet tar lång tid att hämta samt kräver en stor datamängd. Eftersom surfandet på mobila enheter via mobila nätverk förväntas att öka är en lösning för adaptiv bildladdning relevant. Syftet är att undersöka huruvida en webbtjänst, bestående av en klient och en server, kan avgöra bäst lämpad bildkvalitet att leverera till klienten, baserat på dennes aktuella nätverksprestanda och skärmupplösning. En enhet med lägre skärmupplösning och ett långsammare nätverk berättigar en bild i sämre kvalitet och lägre bildupplösning. Därmed förkortas hämtnings- tiden och datamängden reduceras, vilket bidrar till en förbättrad användarupplevelse.Uppsatsen presenterar och utvärderar flera lösningar för adaptiv bildladdning. Lös- ningarna baseras på två parametrar: bredden på klientens webbläsarfönster samt svarstid mellan klient och server, med hjälp av javascript. Dessa parametrar står till grund för den skalning av storlek och kvalitet som sedan appliceras på bilden. Bilden tillhandahålls klien- ten genom någon av de två leveransmetoderna fördefinierade bilder, där flera olika versioner av bilden lagras på servern, och dynamiska bilder, där bilderna i realtid renderas på servern genom gd-biblioteket i php utifrån på originalbilden. Tre typer av adaptiv bildladdning – kvalitetsadaption, storleksadaption och en kombination av de båda, undersöks med av- seende på tidsåtgång och levererad datamängd. Dessa utvärderas sedan i förhållande till basfallet bestående av originalbilderna.Att använda någon typ av adaptionsmetod är i 14 av 15 fall bättre än att enbart leverera originalbilder. Bäst resultat ger kombinerad adaption på enheter med mindre skärmupp- lösning och långsammare nätverk men är även gynnsamt för enheter med medelsnabba nätverk och enheter med stöd för högre skärmupplösning. Både fördefinierad och dyna- misk leveransmetod ger bra resultat men då den dynamiska leveransmetodens skalbarhet med flera parallella anslutningar inte är känd rekommenderas fördefinierade bilder. / Today, information on the web is consumed via a variety of heterogeneous devices. Factors, such as network connection and screen resolution, affects which image that is the most suitable to deliver to the client. An image in its original condition, in a technically limited device, takes a long time to download and requires a large amount of data. Since the number of devices browsing the internet via mobile networks are expected to increase, a solution for adaptive image loading is needed. The aim of this thesis is to explore whether a web service, consisting of a client and a server, can determine the best suited image that should be delivered to the client. This is based on the client’s current network connection and screen resolution. A device with a lower screen resolution and a slower network connection requires an image of lower quality and lower resolution. Thus, the download time can be shortened and the data volume reduced, contributing to improved user experience.Our adaptive solution is based on two measurements – the width of the client’s browser window and the latency between the client and the server – using javascript. These para- meters are the basis for the scaling of the size and quality which applies to the image. The image is provided to the client by one of the two delivery methods: “predefined images”, where several different versions of the image are stored on the server, and “dynamic images”, where the images are rendered on the server by the gd library in php, based on the original image. Three types of adaptive image loading – quality adaptation, size adaptation and a combination of both, are investigated considering delivery time and the amount of data delivered. These are then evaluated in relation to the base case consisting of the original images.Using some type of adaptation method is in 14 out of 15 cases better than simply delivering the original images. The best results are given by the combined adaption method on devices with smaller screen resolutions and slower network connections, but is also beneficial for devices with medium speed connections and devices that support higher screen resolutions. Both predefined and dynamic delivery methods shows good results, but since the dynamic delivery method’s scalability with multiple concurrent clients is not known, it is recommended to use predefined images.

Face recognition is a field of biometrics that deals with identification of subjects based on features present in the images of their faces. The factors that make face recognition popular and favorite as compared to other biometric methods are easier operation and ability to identify subjects without their knowledge. With these features, face recognition has become an integral part of the present day security systems, targeting a smart and secure world. There are various factors that de ne the performance of a face recognition system. The most important among them are recognition accuracy of algorithm used and time taken for recognition. Recognition accuracy of the face recognition algorithm gets affected by changes in pose, facial expression and illumination along with occlusions in the images. There have been a number of algorithms proposed to enable recognition under these ambient changes. However, it has been hard to and a single algorithm that can efficiently recognize faces in all the above mentioned conditions. Moreover, achieving real time performance for most of the complex face recognition algorithms on embedded platforms has been a challenge. Real-time performance is highly preferred in critical applications such as identification of crime suspects in public. As available software solutions for FR have significantly large latency in recognizing individuals, they are not suitable for such critical real-time applications. This thesis focuses on real-time aspect of FR, where acceleration of the algorithms is achieved by means of parallel hardware architectures. The major contributions of this work are as follows. We target to design a face recognition system that can identify at most 30 faces in each frame of video at 15 frames per second, which amounts to 450 recognitions per second. In addition, we target to achieve good recognition accuracy along with scalability in terms of database size and input image resolutions. To design a system with these specifications, as a first step, we explore algorithms in literature and come up with a hybrid face recognition algorithm. This hybrid algorithm shows good recognition accuracy on face images with changes in illumination, pose and expressions, and also with occlusions. In addition the computations in the algorithm are modular in nature which are suitable for real-time realizations through parallel processing. The face recognition system consists of a face detection module to detect faces in the input image, which is followed by a face recognition module to identify the detected faces. There are well established algorithms and architectures for face detection in literature which can perform detection at 15 frames per second on video frames. Detected faces of different sizes need to be scaled to the size specified by the face recognition module. To meet the real-time constraints, we propose a hardware architecture for real-time bi-cubic convolution interpolation with dynamic scaling factors. To recognize the resized faces in real-time, a scalable parallel pipelined architecture is designed for the hybrid algorithm which can perform 450 recognitions per second on a database containing grayscale images of at most 450 classes on Virtex 6 FPGA. To provide flexibility and programmability, we extend this design to REDEFINE, a multi-core massively parallel reconfigurable architecture. In this design, we come up with FR specific programmable cores termed Scalable Unit for Region Evaluation (SURE) capable of performing modular computations in the hybrid face recognition algorithm. We replicate SUREs in each tile of REDEFINE to construct a face recognition module termed REDEFINE for Face Recognition using SURE Homogeneous Cores (REFRESH). There is a need to learn new unseen faces on-line in practical face recognition systems. Considering this, for real-time on-line learning of unseen face images, we design tiny processors termed VOP, Processor for Vector Operations. VOPs function as coprocessors to process elements under each tile of REDEFINE to accelerate micro vector operations appearing in the synaptic weight computations. We also explore deep neural networks which operate similar to the processing in human brain and capable of working on very large face databases. We explore the field of Random matrix theory to come up with a solution for synaptic weight initialization in deep neural networks for better classification . In addition, we perform design space exploration of hardware architecture for deep convolution networks and conclude with directions for future work.