abstract: The origin and function of color in animals has been a subject of great interest for taxonomists and ecologists in recent years. Coloration in animals is useful for many important functions like species identification, camouflage and understanding evolutionary relationships. Quantitative measurements of color signal and patch size in mammals, birds and reptiles, to name a few are strong indicators of sexual selection cues and individual health. These measurements provide valuable insights into the impact of environmental conditions on habitat and breeding of mammals, birds and reptiles. Recent advances in the area of digital cameras and sensors have led to a significant increase in the use of digital photography as a means of color quantification in animals. Although a significant amount of research has been conducted on ways to standardize image acquisition conditions and calibrate cameras for use in animal color quantification, almost no work has been done on designing automated methods for animal color quantification. This thesis presents a novel perceptual"–"based framework for the automated extraction and quantification of animal coloration from digital images with slowly varying (almost homogenous) background colors. This implemented framework uses a combination of several techniques including color space quantization using a few dominant colors, foreground"–"background identification, Bayesian classification and mixture Gaussian modelling of conditional densities, edge"–"enhanced model"–"based classification and Saturation"–"Brightness quantization to extract the colored patch. This approach assumes no prior information about the color of either the subject or the background and also the position of the subject in the image. The performance of the proposed method is evaluated for the plumage color of the wild house finches. Segmentation results obtained using the implemented framework are compared with manually scored results to illustrate the performance of this system. The segmentation results show a high correlation with manually scored images. This novel framework also eliminates common problems in manual scoring of digital images such as low repeatability and inter"–"observer error. / Dissertation/Thesis / M.S. Electrical Engineering 2013

Autonomous vehicles are the subject of intense research because they are a safe and convenient alternative to present-day vehicles. Human drivers base their navigational decisions primarily on visual information and researchers have been attempting to use computers to do the same. The current challenge in using computer vision lies not in the collection or transmission of visual data, but in the perception of visual data to extract from it useful information. The focus of this thesis is on the use of computer vision to navigate an autonomous vehicle that will participate in the Intelligent Ground Vehicle Competition (IGVC.) This document starts with a description of the IGVC and the software design of an autonomous vehicle. This thesis then focuses on the weakest link in the system - the computer vision module. Vehicles at the IGVC are expected to autonomously navigate an obstacle course. Competing vehicles need to recognize and stay between lines painted on grass or pavement. The research presented in this document describes two methods used for boundary line extraction: color-based object extraction, and shape analysis for line recognition. This is the first time a combination of these methods is being applied to the problem of line recognition in the context of the IGVC. The most significant contribution of this work is a method for extracting lines in a binary image even when the line is attached to a shape that is not a line. Novel methods have been used to simplify camera calibration, and for perspective correction of the image. The results give promise of vastly improved autonomous vehicle performance. / Master of Science

Made available in DSpace on 2014-12-17T15:41:51Z (GMT). No. of bitstreams: 1 BethATA_DISSERT.pdf: 4261945 bytes, checksum: f9ef7f539e59502be1e168b17a14bf4a (MD5) Previous issue date: 2009-07-17 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / Polyester fibers are the most used fibers in the world and disperse dyes are used for dyeing these fibers. After dyeing, the colorful dyebath is discharged into effluent streams, which needs a special treatment for color removal. Surfactants interaction with dyes has been evaluated in several studies, including the textile area, specifically in the separation of dyes from textile wastewater. In this work a cationic surfactant was used in a microemulsion system for the extraction of anionic dyes (disperses dyes) from textile wastewater. These microemulsion system was composed by dodecylamonium chloride (surfactant), kerosene oil (organic phase), isoamyl alcohol (cosurfactant) and the wastewater (aqueous phase). The wastewater that results after the dyeing process is acid (pH 5). It was observed that changing the pH value to above 12.8 the extraction could be made, resulting in an aqueous phase with low color level. The Scheff? net experimental design was used for the extraction process optimization, and the obtained results were evaluated using the program "Statistica 7.0". The optimal microemulsion system was composed by 59.8wt.% of wastewater, 30.1wt.% of kerosene, 3.37wt.% of surfactant and 6.73wt.% of cosurfactant, providing extraction upper than 96%. A mix of reactive dyebath (50%) and disperse dyebath (50%) was used as aqueous phase and it presented extraction upper than 98%. The water phase after extraction process can be reused in a new dyeing, being obtained satisfactory results, according to the limits established by textile industry for a good dyeing. Tests were accomplished seeking to study the influence of salt addition and temperature. An experimental design was used for this purpose, which showed that the extraction doesn't depend on those factors. In this way, the removal of color from textile wastewater by microemulsion is a viable technique (that does not depend of external factors such as salinity and temperature), being obtained good extraction results even with in wastewater mixtures / Fibras de poli?ster s?o as fibras sint?ticas mais utilizadas no mundo e corantes dispersos s?o empregados para o tingimento destas fibras. Depois do tingimento, o banho colorido ? descarregado no efluente, que precisa de um tratamento especial para remo??o de cor. A intera??o de tensoativos com corantes foi estudada em diversas pesquisas inclusive na ?rea t?xtil, especificamente na separa??o de corantes de efluentes t?xteis. Neste trabalho foi usado um tensoativo cati?nico em um sistema de microemuls?o para extra??o de corantes n?oi?nico (corantes dispersos) de efluente t?xtil. Esse sistema de microemuls?o foi composto por cloreto de dodecil am?nio (tensoativo), querosene (fase org?nica), ?lcool isoam?lico (cotensoativo) e o efluente l?quido (fase aquosa). O efluente que resulta depois do processo de tingimento ? ?cido (pH 5). Foi observado que mudando o valor do pH para acima de 12,8 a extra??o poderia ser feita, resultando em uma fase aquosa com baixo n?vel de cor. Um planejamento experimental do tipo rede de Scheff? foi usado, para a otimiza??o do processo de extra??o, e os resultados obtidos foram avaliados usando o programa "Statistica 7.0". O ponto ?timo do sistema de microemuls?o ? composto por 59,8% em massa de efluente, 30,1% de querosene, 3,37% de tensoativo e 6,73% de cotensoativo, promovendo uma extra??o superior a 96%. Foi analisada a efici?ncia da remo??o da cor em um efluente composto por 50% de banho de corante reativo e 50% de banho de corante disperso, obtendo-se uma extra??o superior a 98%. A fase aquosa obtida ap?s a extra??o do corante pode ser reutilizada em um novo tingimento, obtendo-se resultados satisfat?rios, dentro dos limites estabelecidos para um bom tingimento na ind?stria. Tamb?m foram realizados testes que mostravam a influencia de fatores como a adi??o de sal e a varia??o da temperatura. Para isso foi utilizado um planejamento experimental, o qual mostrou que a extra??o n?o depende desses fatores. Dessa forma, a remo??o da cor de efluentes t?xteis por microemuls?o ? uma t?cnica vi?vel (que independe de fatores externos como salinidade e temperatura), obtendo-se inclusive bons resultados de extra??o em misturas de efluentes