Darbe aprašoma tyrimas, kurio metu buvo sukurta programa, naudojantis OpenCV ir DNT klaidos skleidimo atgal algoritmu, gebanti aptikti ir bandanti klasifikuoti veidus. Darbo eigoje: • Įsigilinta į OpenCV funkcijų biblioteką; • Išanalizuota DNT teorinė medžiaga; • Sukurta programinė įranga, kuri, naudojantis „webcam“, geba aptikti ir bando klasifikuoti veidus; • Atliktas eksperimentinis tyrimas; • Nustatyti programos trūkumai; • Pateikti kiti sprendimo būdai; Realizuota programinė įranga gali būti naudojama edukaciniais tikslais. / The work describes an experiment,in which progress was created a software,by using OpenCV and ANN error back propagation algorithm capable of detecting and attempting to classify the faces. Workflow: • Delved deeply into the OpenCV library functions; • Analyzed the theoretical material of ANN • Developed the software, which, using webcam, is capable of detecting and trying to classify the faces; • Made an experimental study; • Determined the weaknesses of the program; • The other methods; created software can be used for educational purposes.

Drip bags are used in hospital environments to administerdrugs and nutrition to patients. Ensuring that they are usedcorrectly and are refilled in time are important for the safetyof patients. This study examines the use of a ConvolutionalNeural Network (CNN) to monitor the fluid levels of drip bagsvia image recognition to potentially form the base of an earlywarning system, and assisting in making medical care moreefficient. Videos of drip bags were recorded as they wereemptying their contents in a controlled environment and fromdifferent angles. A CNN was built to analyze the recordeddata in order to predict a bags fluid level with a 5% intervalprecision from a given image. The results show that the CNNused performs poorly when monitoring fluid levels in dripbags.

Automated Guided Vehicle(AGV) as a kind of material conveying equipment has been widely used in modern manufacturing systems. [1] It carries the goods between the workshop along the designated paths. The ability of localization and recognizing the environment around themselves is the essential technology. AGV navigation is developed from several technologies such as fuzzy theory, neural network and other intelligent technology. Among them, visual navigation is one of the newer navigations, because of its path laying is easy to maintain, can identify variety of road signs. Compared with traditional methods, this approach has a better flexibility and robustness, since it can recognition more than one path branch with high anti-jamming capability. Recognizing the environment from imagery can enhance safety and dependability of an AGV, make it move intelligently and brings broader prospect for it. University West has a Patrolbot which is an AGV robot with basic functions. The task is to enhance the ability of vision analysis, to make it become more practical and flexible. The project is going to add object detection, object recognition and object localization functions on the Patrolbot. This thesis project develops methods based on image recognition, deep learning, machine vision, Convolution Neural Network and related technologies. In this project Patrolbot is a platform to show the result, we can also use this kind of program on any other machines. This report generally describes methods of navigation, image segmentation and object recognition. After analyzing the different methods of image recognition, it is easy to find that Neural Network has more advantages for image recognition, it can reduce the parameters and shorting the training and analyzing time, therefore Convolution Neural Network was introduced detailly. After that, the way to achieve image recognition using convolution neural network was presented and in order to recognize several objects at the same time, an image segmentation was also presented here. On the other hand, to make this image recognition processes to be used widely, the ability of transfer learning becomes important. Therefore, the method of transfer learning is presented to achieve customized requirement.

Context. Software testing is becoming more and more important in software development life-cycle especially for web testing. Selenium is one of the most widely used property-based Graph-User-Interface(GUI) web testing tools. Nevertheless, it also has some limitations. For instance, Selenium cannot test the web components in some specific plugins or HTML5 videos frame. But it is important for testers to verify the functionality of plugins or videos on the websites. Recently, the theory of the image recognition-based GUI testing is introduced which can locate and interact with the components to be tested on the websites by image recognition. There are only a few papers do research on comparing property-based GUI web testing and image recognition-based GUI testing. Hence, we formulated our research objectives based on this main gap. Objectives. We want to compare these two different techniques with EyeSel which is the tool represents the image recognition-based GUI testing and Selenium which is the tool represents the property-based GUI testing. We will evaluate and compare the strengths and drawbacks of these two tools by formulating specific JUnit testing scripts. Besides, we will analyze the comparative result and then evaluate if EyeSel can solve some of the limitations associated with Selenium. Therefore, we can conclude the benefits and drawbacks of property-based GUI web testing and image recognition-based GUI testing.   Methods. We conduct an experiment to develop test cases based on websites’ components both by Selenium and EyeSel. The experiment is conducted in an educational environment and we select 50 diverse websites as the subjects of the experiment. The test scripts are written in JAVA and ran by Eclipse.  The experiment data is collected for comparing and analyzing these two tools. Results. We use quantitative analysis and qualitative analysis to analyze our results. First of all, we use quantitative analysis to evaluate the effectiveness and efficiency of two GUI web testing tools. The effectiveness is measured by the number of components that can be tested by these two tools while the efficiency is measured by the measurements of test cases’ development time and execution time. The results are as follows (1) EyeSel can test more number of components in web testing than Selenium (2) Testers need more time to develop test cases by Selenium than by EyeSel (3) Selenium executes the test cases faster than EyeSel. (4) “Results (1)” indicates the effectiveness of EyeSel is better than Selenium while “Results (2)(3)” indicate the efficiency of EyeSel is better than Selenium. Secondly, we use qualitative analysis to evaluate four quality characteristics (learnability, robustness, portability, functionality) of two GUI web testing tools. The results show that portability and functionality of Selenium are better than EyeSel while the learnability of EyeSel is better than Selenium. And both of them have good robustness in web testing. Conclusions. After analyzing the results of comparison between Selenium and EyeSel, we conclude that (1) Image recognition-based GUI testing is more effectiveness than property-based GUI web testing (2) Image recognition-based GUI testing is more efficiency than property-based GUI web testing (3) The portability and functionality of property-based GUI web testing is better than Image recognition-based GUI testing (4) The learnability of image recognition-based GUI testing is better than property-based GUI web testing. (5) Both of them are good at different aspects of robustness

It is argued that a significant feature which acts as a disincentive against the adoption of CAAD systems by small private architectural practices, is the awkwardness of communicating with computers when compared with traditional drawing board techniques. This consideration, although not perhaps the dominant feature, may be mitigated by the development of systems in which the onus of communicating is placed on the machine, through the medium of an architect's sketch plan drawing. In reaching this conclusion, a design morphology is suggested, in which the creative generation of building designs is set in the context of the development of a 'data-base' of information which completely and consistently describes the architect's hypothetical building solution. This thesis describes research carried out by the author between 1981 and 1984, and describes the theory, development and application of algorithms to interpret architect's sketch plan drawings, and hence permit the encoding of building geometries for CAAD applications programs.

In this paper two convolutional neural networks are estimated to classify whether an image contains a swastika or not. The images are gathered from the gaming platform Steam and by scraping a web search engine. The architecture of the networks is kept moderate and the difference between the models is the final layer. The first model uses an average type operation while the second uses the conventional fully-connected layer at the end. The results show that the performance of the two models is similar and the test error is in the 6-9 % range.

The aim of the master thesis is to design a laboratory station and a control program operated by a collaborative robot IRB 14000 YuMi using an integrated effector camera to identify laboratory objects and control the progress of the task. In the introductory part, collaborative robots are briefly introduced, the IRB 14000 on which the task is implemented and the RobotStudio development environment together with the IntegratedVision extension are described in more detail. The following chapters describe the laboratory task itself, its solution and testing of the designed program.

Memory wall is becoming a more and more serious bottleneck of the processing speed of microprocessors. The mismatch between CPUs and memories has been increasing since three decades ago. SRAM was introduced as the bridge between the main memory and the CPU. SRAM is designed to be on the same die with CPU and stores temporary data and instructions that are to be processed by the CPU. Thus, the performance of SRAMs has a direct impact on the performance of CPUs. With the application of mass amount data to be processed nowadays, there is a great need for high-performance CPUs. Three dimensional CPUs and CPUs that are specifically designed for machine learning are gaining popularity. The objective of this work is to design high-performance SRAM for these two emerging applications. Firstly, a novel delay cell based on dummy TSV is proposed to replace traditional delay cells for better timing control. Secondly, a unique SRAM with novel architecture is custom designed for a high-performance machine learning processor. Post-layout simulation shows that the SRAM works well with the processing core and its design is optimized to work well with machine learning processors based on convolutional neural networks. A prototype of the SRAM is also tapped out to further verify our design.

This thesis is concerned with the automatic altitude estimation from a single landscape photograph. I solved this task using convolutional neural networks. There was no suitable training dataset available having information about image altitude, thus I  had to create a new one. To estimate human performance in altitude estimation task, an experiment was conducted counting 100 subjects. The goal of this experiment was to measure the accuracy of the human estimate of camera altitude from an image. The measured average estimation error of subjects was 879 m. An automatic system based on convolutional neural networks outperforms humans with an average elevation error 712 m. The proposed system can be used in more complex scenario like the visual camera geo-localization.

Mobile phones have evolved from feature phones to smart phones with processing power that can compete with personal computers ten years ago. Nevertheless, the computing power of personal computers has also multiplied in the past decade. Consequently, the gap between mobile platforms and personal computers and servers still exists. Mobile Cloud Computing (MCC) has emerged as a paradigm that leverages this difference in processing power. It achieve this goal by augmenting smart phones with resources from the cloud, including processing power and storage capacity. Recently, Mobile Edge Computing (MEC) has brought the benefits from MCC one hop away from the end user. Furthermore, it also provides additional advantages, e.g., access to network context information, reduced latency, and location awareness. This thesis explores the advantages provided by MEC in practice by augmenting an existing application called Human-Centric Positioning System (HoPS). HoPS is a system that relies on context information and information extracted from a photograph of signposts to estimate a user's location. This thesis presents the challenges of enabling HoPS in practice, and implement strategies that make use of the advantages provided by MEC to tackle the challenges. Afterwards, it presents an evaluation of the resulting system, and discusses the implications of the results. To summarise, we make three primary contributions in this thesis: (1) we find out that it is possible to augment HoPS and improve its response time by a factor of four by offloading the code processing; (2) we can improve the overall accuracy of HoPS by leveraging additional processing power at the MEC; (3) we observe that improved network conditions can lead to reduced response time, nevertheless, the difference becomes insignificant compared with the heavy processing required. / Utvecklingen av mobiltelefoner har skett på en rusande takt. Dagens smartphones har mer processorkraft än vad stationära datorer hade för tio år sen. Samtidigt så har även datorernas processorer blivit mycket starkare. Därmed så finns det fortfarande klyftor mellan mobil plattform och datorer och servrar. Mobile Cloud Computing (MCC) används idag som en hävstång för de olika plattformernas processorkraft. Den uppnår detta genom att förbättra smartphonens processorkraft och datorminne med hjälp från datormolnet. På sistånde så har Mobile Edge Computing (MEC) gjort så att förmånerna med MCC är ett steg ifrån slutanvändaren. Dessutom så finns det andra fördelar med MEC, till exempel tillgång till nätverkssammanhangsinformation, reducerad latens, och platsmedvetenhet. Denna tes utforskar de praktiska fördelarna med MEC genom att använda tillämpningsprogrammet Human-Centric Positioning System (HoPS). HoPS är ett system som försöker att hitta platsen där användaren befinner sig på genom att använda sammanhängande information samt information från bilder med vägvisare. Tesen presenterar även de hinder som kan uppstå när HoPS implementeras i verkligheten, och använder förmåner från MEC för att hitta lösningar till eventuella hinder. Sedan så utvärderar och diskuterar tesen det resulterande systemet. För att sammanfatta så består tesen av tre huvuddelar: (1) vi tar reda på att det är möjligt att förbättra HoPS och minska svarstiden med en fjärdedel genom att avlasta kodsprocessen; (2) vi tar reda på att man kan generellt förbättra HoPS noggrannhet genom att använda den utökade processorkraften från MEC; (3) vi ser att förbättrade nätverksförutsättningar kan leda till minskad svarstid, dock så är skillnaden försumbar jämfört med hur mycket bearbetning av information som krävs.