" In the field of Robotics, Monocular Simultaneous Localization and Mapping (Monocular SLAM) has gained immense popularity, as it replaces large and costly sensors such as laser range finders with a single cheap camera. Additionally, the well-developed area of Computer Vision provides robust image processing algorithms which aid in developing feature detection technique for the implementation of Monocular SLAM. Similarly, in the field of digital electronics and embedded systems, hardware acceleration using FPGAs, has become quite popular. Hardware acceleration is based upon the idea of offloading certain iterative algorithms from the processor and implementing them on a dedicated piece of hardware such as an ASIC or FPGA, to speed up performance in terms of timing and to possibly reduce the net power consumption of the system. Good strides have been taken in developing massively pipelined and resource efficient hardware implementations of several image processing algorithms on FPGAs, which achieve fairly decent speed-up of the processing time. In this thesis, we have developed a very simple algorithm for feature detection in an indoor environment by means of a single camera, based on Canny Edge Detection and Hough Transform algorithms using OpenCV library, and proposed its integration with existing feature initialization technique for a complete Monocular SLAM implementation. Following this, we have developed hardware accelerators for Canny Edge Detection & Hough Transform and we have compared the timing performance of implementation in hardware (using FPGAs) with an implementation in software (using C++ and OpenCV). "

<p>This report contains a description on how it is possible to guide a robot along an edge, by using a camera mounted on the robot. If stereo matching is used to calculate 3Dcoordinates of an object or an edge, it requires two images from different known positions and orientations to calculate where it is. In the image analysis in this project, the Canny edge filter has been used. The result from the filter is not useful directly, because it finds too many edges and it misses some pixels. The Canny edge result must be sorted and finally filled up before the final calculations can be started. This additional work with the image decreases unfortunately the accuracy in the calculations. The accuracy is estimated through comparison between measured coordinates of the edge using a coordinate measuring machine and the calculated coordinates. There is a deviation of up to three mm in the calculated edge. The camera calibration has been described in earlier thesis so it is not mentioned in this report, although it is a prerequisite of this project.</p>

This report contains a description on how it is possible to guide a robot along an edge, by using a camera mounted on the robot. If stereo matching is used to calculate 3Dcoordinates of an object or an edge, it requires two images from different known positions and orientations to calculate where it is. In the image analysis in this project, the Canny edge filter has been used. The result from the filter is not useful directly, because it finds too many edges and it misses some pixels. The Canny edge result must be sorted and finally filled up before the final calculations can be started. This additional work with the image decreases unfortunately the accuracy in the calculations. The accuracy is estimated through comparison between measured coordinates of the edge using a coordinate measuring machine and the calculated coordinates. There is a deviation of up to three mm in the calculated edge. The camera calibration has been described in earlier thesis so it is not mentioned in this report, although it is a prerequisite of this project.

MEDEIROS NETO. F. G. Extração automática de características de asas de mosca da espécie Drosophila melanogaster. 2017. 59 f. Dissertação (Mestrado em Engenharia Elétrica e da Computação) - Campus de Sobral, Universidade Federal do Ceará, Sobral, 2017. / Submitted by Programa de Pós-Graduação Engenharia Elétrica e de Computação (secretaria_ppgeec@sobral.ufc.br) on 2017-08-24T13:13:22Z No. of bitstreams: 1 2017_dis_fgmneto.pdf: 2887253 bytes, checksum: 71db95333b633d65ae536330c8799d28 (MD5) / Approved for entry into archive by Djeanne Costa (djeannecosta@gmail.com) on 2017-09-01T11:43:30Z (GMT) No. of bitstreams: 1 2017_dis_fgmneto.pdf: 2887253 bytes, checksum: 71db95333b633d65ae536330c8799d28 (MD5) / Made available in DSpace on 2017-09-01T11:43:31Z (GMT). No. of bitstreams: 1 2017_dis_fgmneto.pdf: 2887253 bytes, checksum: 71db95333b633d65ae536330c8799d28 (MD5) Previous issue date: 2017-08 / Biometrics techniques are used in studies of several animal species, such as the Drosophila melanogaster, popularly known as fruit fly. This species has become a model organism for the study of the impacts that other insects produce to the environment. In addition, these flies have proteins and genes similar to those of humans. A challenge for specialists in the study of these individuals is the similarity of the wings between males and females, which may be affected by mutations or variations in the genotype. This work proposes a method of discrimination for gender and genotype of flies of the species Drosophila melanogaster from features extracted from images of the wings. This approach is based on the fractal dimension extracted from the Canny filter segmentation of the components of the Stationary Wavelet Transform. The methodology is validated by dividing the data into groups with variable training and test rates and using six different classifiers: Random Forest, Support Vector Machines, Multi-layer Perceptron, Linear Discriminant Analysis, Quadratic Discriminant Analysis and K Nearest Neighbors. Then, the classification is repeated with data reduction, only females for genotype or only individuals without mutation for gender. The results were satisfactory, surpassing works of the literature with automatic methodologies. For genotype, the hit rates were lower due to the physical similarity between the wings. / Técnicas de biometria são utilizadas nos estudos de diversas espécies de animais, como exemplo a Drosophila Melanogaster, popularmente conhecida como mosca da fruta. Essa espécie tornou-se um organismo modelo para o estudo dos impactos que outros insetos produzem ao meio ambiente. Ademais, essas moscas possuem proteínas e genes similares aos dos seres humanos. Uma dificuldade para especialistas no estudo desses indivíduos é a semelhança das asas entre machos e fêmeas, que podem ser afetadas por mutações ou variações no genótipo. Este trabalho propõe um método de discriminação de gênero e genótipo de moscas da espécie Drosophila melanogaster a partir de características extraídas de imagens das asas. Essa abordagem se baseia na dimensão fractal extraída da segmentação por filtro de Canny das componentes da Transformada Wavelet Estacionária. A metodologia é validada com a divisão dos dados em grupos com taxas de treinamento e teste variáveis e na utilização de seis classificadores de abordagens diferentes: Floresta Aleatória, Máquinas de Vetor de Suporte, Perceptron Multicamadas, Análise por Discriminante Linear, Análise por Discriminante Quadrático e K Vizinhos Mais Próximos. Em seguida, a classificação é repetida com redução dos dados, apenas fêmeas para genótipo ou apenas indivíduos sem mutação para gênero. Os resultados obtidos foram satisfatórios, superando trabalhos da literatura com metodologias que não utilizam interação humana. Para genótipo, as taxas de acerto foram mais baixas devido à semelhança física entre as asas.

My master's thesis deals with the different techniques used in fingerprints processing for identifying fingerprints. Using the software tool Visual C++ and functions of OpenCV library I programmed a separate application, that is able to select from a database of fingerprints the most consistent with a comparative fingerprint images, even when they are mutually shifted in the direction of axes X and Y. The next step in my program is to gather the edges of the fingerprint image. Those obtained using Canny edge detector. Furthermore, getting the contours of the image edges. To determine, whether the contours are the same, just compare some characteristic points of contours. Next I use a histogram function to determine the number of points for approximation of contours and evaluating compliance fingerprints. Since the processing of the input fingerprint image (or rather the approximation of the contour points) remains in the picture as black (background) and red (the approximation of the contour points), this means, that zero and the last element of the histogram represent the number of black and red points. Comparison is in percentage and is obtained by subtracting the approximated points of contours image from the original fingerprint image of approximated contour points of matched fingerprints. It determined, what percentage of red points have disappeared, so as to match two fingerprint images. If on the resulting figure is not left neither a red point, that corresponds to 100% of the fingerprints Compliance.

Ces travaux de recherche visaient à développer un système d'aide à la mobilité pour les personnes ayant une déficience visuelle (VIP ‘Visually Impaired Person’) appelé ‘Smart Environment Explorer Stick (SEES)’. Le but particulier de cette recherche était de développer de nouveaux algorithmes pour améliorer la précision de la détection de la présence de poteaux de la canne SEE-stick en utilisant la méthode de calcul de distance et la recherche de paires de lignes verticales basées sur l'optimisation de la technique de détection de contour de Canny. Désormais, l'algorithme de détection des poteaux est appelé l’algorithme YuRHoS. Le SEES développé comme système de support d'aide à la mobilité VIP a été intégré avec succès à plusieurs dispositifs tels que le serveur distant dénommé iSEE, le serveur local embarqué dénommé SEE-phone et la canne intelligente dénommée SEE-stick. Les performances de SEE-stick ont été améliorées grâce à l'algorithme YuRHoS qui permet de discriminer avec précision les objets (obstacles) en forme de poteau parmi les objets détectés. La comparaison des résultats de détection des poteaux avec ceux des autres algorithmes a conclu que l'algorithme YuRHoS était plus efficace et précis. Le lieu et la couleur des poteaux de test d’évaluation étaient deux des facteurs les plus importants qui influaient sur la capacité du SEE-stick à détecter leur présence. Le niveau de précision de SEE-stick est optimal lorsque le test d’évaluation est effectué à l'extérieur et que les poteaux sont de couleur argentée. Les statistiques montrent que la performance de l'algorithme YuRHoS à l'intérieur était 0,085 fois moins bonne qu'à l'extérieur. De plus, la détection de la présence de poteaux de couleur argentée est 11 fois meilleure que celle de poteaux de couleur noir. / This research aimed to develop a technology system of mobility aid for Visually Impaired Person (VIP) called Smart Environment Explorer Stick (SEES).Particular purpose of this research was developing new algorithm in improving accuracy of SEE-stick for pole detection using distance calculation method and vertical line pair search based on Canny edge detection optimization and Hough transform. Henceforth, the pole detection algorithm was named as YuRHoS algorithm.The developed SEES as supporting system of VIP mobility aid had been successfully integrated several devices such as global remote server (iSEE), embedded local server (SEE-phone) and smart stick (SEE-stick). Performance of SEE-stick could be improved through YuRHoS algorithm, which was able to fix the accuracy of SEE-stick in detecting pole. Test comparison of pole detection results among others algorithm concluded that YuRHoS algorithm had better accuracy in pole detection.Two most significant factors affecting SEE-stick ability in detecting pole was test location and pole color. Level of accuracy of SEE-stick would be optimum once the test location was performed outdoor and pole color was silver. Statistics result shown that YuRHoS algorithm performance indoor was 0.085 times worse than outdoor. Meanwhile, silver-pole-color as object detection could increase YuRHoS algorithm performance as much as 11 times better compare to black-pole-color.

O presente trabalho trata-se do desenvolvimento de um programa para de análise de imagens de topografia corneana de sistemas comerciais, para ser implementado no topógrafo corneano para Lâmpada de Fenda, em desenvolvimento no Laboratório de Instrumentação Oftálmica - EESC/USP e no Laboratório de Física Oftálmica - FMRP/USP. O programa foi desenvolvido em C++, utilizando a plataforma Windows, e fornece mapas axiais de topografia corneana. O programa foi testado em esferas de calibração e em olhos humanos, apresentando um fator de correlação de 0,9998 para as medidas em esferas e um erro inerente estimado em 3%. Os mapas de topografias axiais em olhos humanos foram comparados com os mapas gerados por sistemas comerciais e o padrão visual de forma e relevo estão em concordância. / This work is about a software for the analisys of corneal topography images provided by commercial available systems to be implemented in a corneal topographer for slit lamps under evelopment at Laboratório de Instrumentação Oftálmica . EESC/USP e no Laboratório de Física Oftálmica . FRMP/USP. The software was developed in Borland C++ Builder for Windows and provides the corneal topography axial maps. The software has been tested in calibration spheres and in human eyes, presenting a correlation factor of 0,9998 for the measurements performed in the spheres and an inherent error of 3%. The axial topographic maps form the exams performe in human eyes have been compared to the axial maps provided by the commercial available system and the visual pattern as well as the relief are in accordance.

Object detection is the initial step in any image analysis procedure and is essential for the performance of object recognition and augmented reality systems. Research concerning the detection of edges and blobs is particularly rich and many algorithms or methods have been proposed in the literature. This master‟s thesis presents 4 most common blob and edge detectors, proposes method for detected numbers separation and describes the experimental setup and results of object detection and detected numbers separation performance. Finally, we determine which detector demonstrates the best results for mobile augmented reality system. / Objektų aptikimas yra pagrindinis žingsnis vaizdų analizės procese ir yra pagrindinis veiksnys apibrėžiantis našumą objektų atpažinimo ir papildytosios realybės sistemose. Literatūroje gausu metodų ir algoritmų aprašančių sričių ir ribų aptikimą. Šiame magistro laipsnio darbe aprašomi 4 dažniausiai naudojami sričių ir ribų aptikimo algoritmai, pasiūlomas metodas aptiktų skaičių atskyrimo problemai išspręsti. Pateikiami atliktų eksperimentų rezultatai, palyginmas šių algoritmų našumas. Galiausiai yra nustatoma, kuris iš jų yra geriausias.

O presente trabalho trata-se do desenvolvimento de um programa para de análise de imagens de topografia corneana de sistemas comerciais, para ser implementado no topógrafo corneano para Lâmpada de Fenda, em desenvolvimento no Laboratório de Instrumentação Oftálmica - EESC/USP e no Laboratório de Física Oftálmica - FMRP/USP. O programa foi desenvolvido em C++, utilizando a plataforma Windows, e fornece mapas axiais de topografia corneana. O programa foi testado em esferas de calibração e em olhos humanos, apresentando um fator de correlação de 0,9998 para as medidas em esferas e um erro inerente estimado em 3%. Os mapas de topografias axiais em olhos humanos foram comparados com os mapas gerados por sistemas comerciais e o padrão visual de forma e relevo estão em concordância. / This work is about a software for the analisys of corneal topography images provided by commercial available systems to be implemented in a corneal topographer for slit lamps under evelopment at Laboratório de Instrumentação Oftálmica . EESC/USP e no Laboratório de Física Oftálmica . FRMP/USP. The software was developed in Borland C++ Builder for Windows and provides the corneal topography axial maps. The software has been tested in calibration spheres and in human eyes, presenting a correlation factor of 0,9998 for the measurements performed in the spheres and an inherent error of 3%. The axial topographic maps form the exams performe in human eyes have been compared to the axial maps provided by the commercial available system and the visual pattern as well as the relief are in accordance.

This work deals with the technical possibilities for automated optical inspection and the arrangements for monitoring the implementation of established elements. There are used methods of detection elements, including advanced algorithm processing. With the described methods was created program and each method was tested. The aim was on the clear description of the problem, the optimal design and processing program with objective results with the lowest number of false detection.