Biometric systems allow identification of human persons based on physiological or behavioral characteristics, such as voice, handprint, iris or facial characteristics. The use of face and iris recognition as a way to authenticate user’s identities has been a topic of research for years. Present iris recognition systems require that subjects stand close (<2m) to the imaging camera and look for a period of about three seconds until the data are captured. This cooperative behavior is required in order to capture quality images for accurate recognition. This will eventually restrict the amount of practical applications where iris recognition can be applied, especially in an uncontrolled environment where subjects are not expected to cooperate such as criminals and terrorists, for example. For this reason, this thesis develops a collection of methods to deal with low quality face and iris images and that can be applied for face and iris recognition in a non-cooperative environment. This thesis makes the following main contributions: I. For eye and face tracking in low quality images, a new robust method is developed. The proposed system consists of three parts: face localization, eye detection and eye tracking. This is accomplished using traditional image-based passive techniques such as shape information of the eye and active based methods which exploit the spectral properties of the pupil under IR illumination. The developed method is also tested on underexposed images where the subject shows large head movements. II. For iris recognition, a new technique is developed for accurate iris segmentation in low quality images where a major portion of the iris is occluded. Most existing methods perform generally quite well but tend to overestimate the occluded regions, and thus lose iris information that could be used for identification. This information loss is potentially important in the covert surveillance applications we consider in this thesis. Once the iris region is properly segmented using the developed method, the biometric feature information is calculated for the iris region using the relative entropy technique. Iris biometric feature information is calculated using two different feature decomposition algorithms based on Principal Component Analysis (PCA) and Independent Component Analysis (ICA). III. For face recognition, a new approach is developed to measure biometric feature information and the changes in biometric sample quality resulting from image degradations. A definition of biometric feature information is introduced and an algorithm to measure it proposed, based on a set of population and individual biometric features, as measured by a biometric algorithm under test. Examples of its application were shown for two different face recognition algorithms based on PCA (Eigenface) and Fisher Linear Discriminant (FLD) feature decompositions.

The ability of humans to perceive significant pattern and structure of an image is something which humans take for granted. We can recognize objects and patterns independent of changes in image contrast and illumination. In the past decades, it has been widely recognized in both biology and computer vision that phase contains critical information in characterizing the structures in images. Despite the importance of local phase information and its significant success in many computer vision and image processing applications, the coherence behavior of local phases at scale-space is not well understood. This thesis concentrates on developing an invariant image representation method based on local phase information. In particular, considerable effort is devoted to study the coherence relationship between local phases at different scales in the vicinity of image features and to develop robust methods to measure the strength of this relationship. A computational framework that computes local phase coherence (LPC) intensity with arbitrary selections in the number of coefficients, scales, as well as the scale ratios between them has been developed. Particularly, we formulate local phase prediction as an optimization problem, where the objective function computes the closeness between true local phase and the predicted phase by LPC. The proposed framework not only facilitates flexible and reliable computation of LPC, but also broadens the potentials of LPC in many applications. We demonstrate the potentials of LPC in a number of image processing applications. Firstly, we have developed a novel sharpness assessment algorithm, identified as LPC-Sharpness Index (LPC-SI), without referencing the original image. LPC-SI is tested using four subject-rated publicly-available image databases, which demonstrates competitive performance when compared with state-of-the-art algorithms. Secondly, a new fusion quality assessment algorithm has been developed to objectively assess the performance of existing fusion algorithms. Validations over our subject-rated multi-exposure multi-focus image database show good correlations between subjective ranking score and the proposed image fusion quality index. Thirdly, the invariant properties of LPC measure have been employed to solve image registration problem where inconsistency in intensity or contrast patterns are the major challenges. LPC map has been utilized to estimate image plane transformation by maximizing weighted mutual information objective function over a range of possible transformations. Finally, the disruption of phase coherence due to blurring process is employed in a multi-focus image fusion algorithm. The algorithm utilizes two activity measures, LPC as sharpness activity measure along with local energy as contrast activity measure. We show that combining these two activity measures result in notable performance improvement in achieving both maximal contrast and maximal sharpness simultaneously at each spatial location.

The ability of humans to perceive significant pattern and structure of an image is something which humans take for granted. We can recognize objects and patterns independent of changes in image contrast and illumination. In the past decades, it has been widely recognized in both biology and computer vision that phase contains critical information in characterizing the structures in images. Despite the importance of local phase information and its significant success in many computer vision and image processing applications, the coherence behavior of local phases at scale-space is not well understood. This thesis concentrates on developing an invariant image representation method based on local phase information. In particular, considerable effort is devoted to study the coherence relationship between local phases at different scales in the vicinity of image features and to develop robust methods to measure the strength of this relationship. A computational framework that computes local phase coherence (LPC) intensity with arbitrary selections in the number of coefficients, scales, as well as the scale ratios between them has been developed. Particularly, we formulate local phase prediction as an optimization problem, where the objective function computes the closeness between true local phase and the predicted phase by LPC. The proposed framework not only facilitates flexible and reliable computation of LPC, but also broadens the potentials of LPC in many applications. We demonstrate the potentials of LPC in a number of image processing applications. Firstly, we have developed a novel sharpness assessment algorithm, identified as LPC-Sharpness Index (LPC-SI), without referencing the original image. LPC-SI is tested using four subject-rated publicly-available image databases, which demonstrates competitive performance when compared with state-of-the-art algorithms. Secondly, a new fusion quality assessment algorithm has been developed to objectively assess the performance of existing fusion algorithms. Validations over our subject-rated multi-exposure multi-focus image database show good correlations between subjective ranking score and the proposed image fusion quality index. Thirdly, the invariant properties of LPC measure have been employed to solve image registration problem where inconsistency in intensity or contrast patterns are the major challenges. LPC map has been utilized to estimate image plane transformation by maximizing weighted mutual information objective function over a range of possible transformations. Finally, the disruption of phase coherence due to blurring process is employed in a multi-focus image fusion algorithm. The algorithm utilizes two activity measures, LPC as sharpness activity measure along with local energy as contrast activity measure. We show that combining these two activity measures result in notable performance improvement in achieving both maximal contrast and maximal sharpness simultaneously at each spatial location.

Darbe nagrinėjama socialinio darbo kokybė ir jos vertinimas institucinės socialinės globos įstaigose senyvo amžiaus asmenims. Darbo tikslas - vadovaujantis socialinių darbuotojų vertinimais, išryškinti socialinių paslaugų kokybės charakteristikas institucinės socialinės globos įstaigose senyvo amžiaus žmonėms. Siekiant atskleisti socialinių darbuotojų paslaugų kokybės sampratos charakteristikas ir užtikrinimo praktikoje bruožus, atliktas kokybinis tyrimas. Duomenys surinkti interviu metodu. Jame dalyvavo 5 institucinės socialinės globos įstaigose senyvo amžiaus dirbantys socialiniai darbuotojai. Tyrimu atskleista, kad socialinių paslaugų kokybė (įstaigos perspektyva) yra suprantama kaip subjektyvus, pasitenkinimą keliantis, kūrybiškas, pagrįstas kvalifikacija ir profesine patirtimi, socialinis darbas. Formalusis išorinis paslaugų kokybės vertinimas suprantamas kaip privalomas, neformalusis – kaip naudingas dėl galimybės vertinti kitų darbą ir įsivertinti save. Kokybės vertinimas laikomas probleminiu veiklos aspektu, nes atlikti trūksta laiko, vertinimo įrankių, vienodo vertinimo prasmės suvokimo. Socialinių darbuotojų veiklos suvokime profesiniu lygmeniu išryškėjo atliekamo vaidmens sudėtingumas, neapibrėžtumas, plačios atsakomybės sritys, vaidmens nuvertinimas ar neįvertinimas sąveikoje su kitų sričių specialistais, neigiamos patirtys dirbant kompetencijos neatitinkantį darbą. Atskleidžiant socialinių darbuotojų ir jų klientų sąveikos bruožus, reikšmingus kliento gyvenimo... [toliau žr. visą tekstą] / The paper examines the quality of social work and its assessment in the residential care homes for the elderly. The goal of the paper is to stress the main aspects of quality social services in the residential care homes for the elderly from social workers point of view. Qualitative study was conducted in order to reveal the social worker service quality concept, its characteristics and features of the assurance. Data collected using the interview method. Five individual interviews were carried out with social workers, working at residential care homes for the elderly. The results of the study revealed that the quality of social services is understood as a social work: subjective, gratifying, creative, based on qualifications and professional experience. Social workers understand that formal external assessment of quality of social services is mandatory. Nonformal they perceive as useful. The key challenge of the quality assurance is the lack of time, quality assessment tools and equal understanding. Social workers are aware of their professional role as a complex, uncertain, covering broad areas of responsibility, impaired or lost, when there are interactions with other specialists. Social workers feel frustrated when working on an inappropriate job. From social workers point of view, the client's quality of life associated with long-term and professional contact with an experienced social worker. Customer confidence in the quality of services when faced with a social worker... [to full text]

A avaliação objetiva da qualidade de imagens é de especial importância em diversas aplicações, por exemplo na compressão de imagens, onde pode ser utilizada para regular a taxa que deve ser empregada para que haja a máxima compressão (permitindo perda de dados) sem comprometer a qualidade final; outro exemplo é na inserção de marcas dágua, isto é, introdução de informações descritivas utilizadas para atestar a autenticidade de uma imagem, que devem ser invisíveis para o observador. O SSIM (Structural SIMilarity) é uma métrica de avaliação objetiva da qualidade de imagens de referência completa projetada para imagens em tons de cinza. Esta dissertação investiga sua aplicação na avaliação de imagens coloridas. Para tanto, inicialmente é feito um estudo do SSIM utilizando quatro diferentes espaços de cores RGB, YCbCr, L&#945;&#946; e CIELAB. O SSIM é primeiramente calculado nos canais individuais desses espaços de cores. Em seguida, com inspiração no trabalho desenvolvido em (1) são testadas formas de se combinar os valores SSIM obtidos para cada canal em um valor único os chamados SSIM Compostos. Finalmente, a fim de buscar melhores correlações entre SSIM e avaliação subjetiva, propomos a utilização da mínima diferença de cor perceptível, calculada utilizando o espaço de cores CIELAB, conjuntamente com o SSIM. Para os testes são utilizados três bancos de dados de imagens coloridas, LIVE, IVC e TID, a fim de se conferir consistência aos resultados. A avaliação dos resultados é feita utilizando as métricas empregadas pelo VQEG (Video Quality Experts Group) para a avaliação da qualidade de vídeos, com uma adaptação. As conclusões do trabalho sugerem que os melhores resultados para avaliação da qualidade de imagens coloridas usando o SSIM são obtidas usando os canais de luminância dos espaços de cores YCbCr, L&#945;&#946; e especialmente o CIELAB. Também se concluiu que a utilização da mínima diferença de cor perceptível contribui para o melhoramento dos resultados da avaliação objetiva. / Objective image quality evaluation is of special interest in many image applications, for example for image compression, where it can be used to control the rate in order to keep a tradeoff between lost of data and image quality; another example is in the application of watermarks, i.e., introduction of descriptive information used to guarantee the authenticity of an image, that must be invisible to the observer who looks at the image. SSIM (Structural SIMilarity) index is a full-reference image quality assessment metric developed to evaluate gray images. This work investigates the application of SSIM in the evaluation of color images. Therefore, four different color spaces are tested RGB, YCbCr, L&#945;&#946; e CIELAB. Initially SSIM is calculated individually for each one of color spaces channels. Then, inspired in (1), the results of the SSIM in the individual channels are combined in a unique result the so called Composite SSIM. Finally, in order to improve the correlations between, calculated using CIELAB color space, together with SSIM. Three color image databases, LIVE, IVC and TID, were employed in the tests in order to confer solidity to the results. The evaluation of the results is made using VQEG (Video Quality Experts Group) methodology, developed for video quality evaluation with an adaptation regarding the time dimension that does not exist in the image domain. The conclusions from the work were that SSIM performs better in the evaluation of color images when applied to luminance channel of YCbCr, L&#945;&#946; and especially to CIELAB color spaces. It was also concluded that the use of just noticeable difference concept improve objective assessment results.

The application of the wrinkle measuring method described in Müller et al. (2017) and the subsequent evaluation algorithm of a range of deep-drawn samples were used to determine the influences and interdependencies of blankholder force, tool temperatures, and drawing height on the formation of wrinkles in paperboard. The main influences were identified and quantitatively evaluated. For the given experimental space, a regression function was derived and validated in further experiments. It was shown that a quadratic regression was superior to the previously used linear regression. The findings were discussed and compared with the results of similar experiments from past publications. Special attention was given to the wrinkles formed and the resulting quality of the formed paperboard cups. The restrictions of the data acquisition from the measuring method that was used and limitations of the model were presented to demonstrate the reliability of the results.

La qualité méthodologique en recherche clinique est une exigence garantissant la fiabilité des expérimentations médicales, au bénéfice des praticiens comme à celui des patients. Cette thèse a pour objectif de mesurer la qualité des essais thérapeutiques présentés au Comité d’Ethique de la Région Sud-Est II et son évolution sur des périodes pluriannuelles. Deux études transversales exhaustives ont été réalisées. La première a pour objet de mesurer l’impact du Règlement Pédiatrique Européen de 2007 sur l’évolution qualitative et quantitative de essais pédiatriques, compte tenu du faible nombre de recherches dans cette population. La deuxième analyse le niveau de qualité des essais contrôlés randomisés en utilisant le score de Jadad et identifie les éléments qui l’influencent. L'outil de travail est constitué des protocoles détenus par le Comité d’Ethique, et non de publications de la littérature. Le concept de qualité et ses deux composantes, éthique et fiabilité scientifique, a été étudié. Les différents outils proposés par les experts pour mesurer la qualité ont été expertisés, ce qui a permis la sélection de l’échelle méthodologiquement la plus adaptée. Le niveau de qualité observé pour les essais pédiatriques est élevé, mais n’a pas été influencé par le Règlement Européen, qui a pu, cependant, entraîner une progression forte du nombre des essais pédiatriques, pouvant être l’indice d’un développement de la recherche en pédiatrie. Concernant les essais contrôlés randomisés, deux marqueurs sont associés à un haut score qualité des protocoles, identifiés après une analyse multivariée : le caractère multicentrique de la recherche et les essais portant sur les médicaments. / Methodological quality in clinical research is mandatory to ensure the reliability of medical experiments, with benefits for both practitioners and patients. This PhD thesis aims at measuring the quality of therapeutic trials submitted to the Ethics Committee of the South-East Region II, and its evolution over several years. Two comprehensive cross-sectional studies were conducted. The first explore the field of pediatric research, and aims at measuring the impact of the introduction of European Pediatric Regulation in 2007, on the evolution of the quantity and quality of trials in this field, given the low number of research in this population. The second analyzes the quality of randomized controlled trials using the JADAD score and seeks to identify the elements that influence it. These studies were conducted using the protocols submitted to the Ethics Committee, and not from a literature analysis. The concept of quality was first studied based on their ethical and scientific reliability. The various assessing tools proposed by the experts to measure the quality were appraised, which allowed the selection of the most methodologically scale adapted to this study. Conclusion: we show that the level of quality observed for pediatric trials is high, but was not influenced by the introduction of the European Regulation, which could, on the other hand, have led to an important increase in the number of pediatric trials. Regarding randomized controlled trials, a multivariate analysis allowed the identification of two statistically significant markers associated with high quality score of the protocol: the multicentric character of the research, and the drugs trials.

In recent times the demand of high resolution 3D data has seen a rise, and the applications of airborne LiDAR data are increasing. Automatic extraction of building roofs is important in many of these applications such as city modelling. In 2018, Lantmäteriet (the Swedish mapping, cadastral and land registration authority) is planning a new flight to collect airborne LiDAR data. This data may become useful in extracting roof planes. The purpose of this thesis is to evaluate automatic methods for extracting buildings from airborne LiDAR data, and to perform a quality assessment of the footprints.This thesis proposes specific methods of extraction in using software called ArcGIS Pro and FME. The method was to process raw LiDAR points by separating the ground points, and finding building points through plane detection of points in clusters. Vegetation was removed using height difference of the points and the area. Polygons were created from the building points and a quality assessment was then carried out concerning completeness, accuracy and RMSE. The result on four different data sets shows a more appropriate extraction in FME. Lower point density sometimes leads to better extraction of buildings because of less vegetation. Higher point density has the advantage of higher accuracy and can extract smaller buildings, but includes more vegetation. The proposed method is recommended for larger buildings (&gt;25 m2) and a LiDAR point density around 12 points/m2.

Submitted by Priscila Nascimento (pnascimento@icict.fiocruz.br) on 2012-11-13T18:17:33Z No. of bitstreams: 1 carlos-renato-calvet.pdf: 572867 bytes, checksum: 445d1b96d9a8d9baadaf7ef3d8852421 (MD5) / Made available in DSpace on 2012-11-13T18:17:33Z (GMT). No. of bitstreams: 1 carlos-renato-calvet.pdf: 572867 bytes, checksum: 445d1b96d9a8d9baadaf7ef3d8852421 (MD5) Previous issue date: 2007 / Fundação Oswaldo Cruz. Instituto de Tecnologia em Imunobiológicos. Rio de Janeiro, RJ, Brasil / Fundação Oswaldo Cruz. Instituto Oswaldo Cruz. Rio de Janeiro, RJ, Brasil. / No Brasil, a Leishmaniose Visceral (LV) é uma antropozoonose que representa grave problema de saúde pública, presente em 19 estados da federação, com cerca de 3.500 casos humanos anuais. O agente etiológico da LV é um protozoário do gênero Leishmania, cujos vetores são insetos da sub-família Phlebotominae, sendo o Lutzomyia longipalpisa principal espécie das Américas. O cão é o mais importante reservatório da doença, atuando como hospedeiro doméstico o que torna necessária maior atenção sobre o papel destes animais na transmissão da doença e conseqüente urbanização. O controle da população canina consiste, principalmente, na eliminação de cães infectados e diagnosticados por exames parasitológicos ou sorológicos positivos para a leishmaniose visceral canina (LVC). Resultados sorológicos falso-positivos e falso-negativos podem levar à eutanásia animais supostamente infectados, determinando dados epidemiológicos imprecisos. Bio-Manguinhos produz e distribui os kits de LVC mais utilizados na rede de Laboratório Público do país: incluem-se os testes imunoenzimático (ELISA) e o teste de Imunofluorescência Indireta (IFI). O objetivo desta Dissertação foi pôr em execução um Programa de Avaliação Externa da Qualidade dos testes sorológicos da LVC em instituições localizadas em áreas endêmicas do país. Distribuímos, em outubro de 2006, carta-convite e questionário de cadastramento a 51 instituições responsáveis por realizar o diagnóstico sorológico no país com 78% de adesão (40). Sendo assim, em dezembro de 2006, enviamos um painel sorológico composto por 6 amostras de soro canino, por quatro (4) amostras positivas e duas (2) amostras negativas, todas com certeza diagnóstica confirmadapor ELISA e IFI, junto a um protocolo para o preenchimento dos resultados obtidos. Dos 75% laboratórios (30) que realizaram os exames, 30% (9) foram não-conformes, totalizando 10 erros. Os percentuais de resultados incorretos por metodologia obtidos nesse painel de AEQ-LVC foram 3,7% (4/108 / ELISA) e 3,4% (6/176 / IFI). As respostas dos questionários e dos resultados na sorologia dos painéis foram armazenadas em um banco de dados construído em software estatístico SPSS WIN 11.0. Apoiado nas informações do banco de dados, diversos aspectos foram analisadas (percentil, mediana, desvio-padrão). Além disso, correlações entre realização prévia em Programa de Avaliação Externa da Qualidade (AEQ) foram correlacionadas àsvariáveis de estrutura e processo. A maioria dos laboratórios pertence à Rede Pública, sendo estaduais pouco mais da metade (55%). Apresentam funcionáriosexclusivos para realização da sorologia para LVC em 70% das instituições, com metade dos serviços contando, pelo menos, com um funcionário com instrução superior. Independente do nível de instrução, a experiência dos funcionários na execução do exame de IFI aproxima-se do dobro (em média 6 anos) daquela relativa à execução do ELISA. Quanto às informações estruturais, itens ligados à qualidade demonstraram que 77,5% das instituições possuem Procedimentos Operacionais Padrão (POP); 95,0% afirmaram utilizar equipamento de proteção individual (EPI) emais da metade (60%) dos laboratórios não calibra equipamentos e dentre esses um terço (31,3%) o faz com periodicidade irregular ou acima da anual. Por intermédio de painéis sorológicos, o AEQ-LVC pretende contribuir como importante instrumento para melhoria do desempenho dos laboratórios públicos. / Visceral leishmaniasis (VL) is one anthropozoonose that represents a serious problem of public health in Brazil with 3.500 new annual cases in 19 states of the country. The etiological agent of VL is a protozoa of the genus Leishmania, whose vectors are insects of the sub-family Phlebotominae, being the Lutzomyia longipalpis, the main species found in the Americas. The dog is the most important reservoir of the parasite acting as a domestic host, demanding agreater attention on the role of these animals in the transmission of the illness and its consequent urbanization. The control of the canine population consists mainly inthe elimination of infected dogs, diagnosed by parasitological examinations or positive serological tests for canine visceral leishmaniasis (CVL). False-positive and false-negative serological results may lead to the euthanasia of supposedly infected animals and the attainment of imprecise epidemiological data. Bio-Manguinhos produces and distributes the most consumed kits for CVL used in Brazil’s public laboratory network including immunoenzyme (ELISA) and indirect immunofluorescence (IFI) tests. The objective of the present study was to initiate a Program of External Quality Assessment (EQA) for CVL serological tests, in institutions located in endemic areas of the country. In October 2006, an invitation letter together with anenrollment form was sent to 51 institutions responsible for the serological diagnosis in the country to which 78% (40) had adhered. In December 2006, along with a protocol to be fulfilled with the results a serological panel was sent containing: four (4) positive and two (2) negative samples of canine serum, all of them confirmed by ELISA and IFI. Of the 30 (75%) laboratories that performed the exams, 9 (30%) werenot in agreement, totalizing 10 errors. The percentage of incorrect results by methodology obtained for this EQA-CVL panel was 3,7% (4/108) for ELISA and 3,4% (6/176) for IFI. The information obtained from the serological panel results was stored in a data bank, constructed in SPSS WIN 11.0 statistical software. Based on this data bank, some statistical were analyzed. Furthermore, correlations between previous programs of external quality assessment (EQA) were performed to compare structural and process variables. The majority of the laboratories belong to the public network with more than a half (55%) belonging to the state. Exclusive employees that perform CVL serology were found in 70% of the institutions and half of the servicespossess at least one employee with superior instruction. Independently of the instruction level, the employees experience on IFI is about 2 times greater (6 years) than thatrelated to ELISA tests. Concerning structural information, quality related items showed that 77,5% of the institutions possess Standard Operating Procedures (SOP), 95,0% use Individual Protection Equipment (IPE), more than a half (60%) do not calibrate equipments and amongst the ones that do the calibration, one-third (31,3%)make it with irregularly or over annual periodicity. Through serological panels, theEQA-CVL might contribute as an important instrument to improve the performance of public laboratories.

A avaliação objetiva da qualidade de imagens é de especial importância em diversas aplicações, por exemplo na compressão de imagens, onde pode ser utilizada para regular a taxa que deve ser empregada para que haja a máxima compressão (permitindo perda de dados) sem comprometer a qualidade final; outro exemplo é na inserção de marcas dágua, isto é, introdução de informações descritivas utilizadas para atestar a autenticidade de uma imagem, que devem ser invisíveis para o observador. O SSIM (Structural SIMilarity) é uma métrica de avaliação objetiva da qualidade de imagens de referência completa projetada para imagens em tons de cinza. Esta dissertação investiga sua aplicação na avaliação de imagens coloridas. Para tanto, inicialmente é feito um estudo do SSIM utilizando quatro diferentes espaços de cores RGB, YCbCr, L&#945;&#946; e CIELAB. O SSIM é primeiramente calculado nos canais individuais desses espaços de cores. Em seguida, com inspiração no trabalho desenvolvido em (1) são testadas formas de se combinar os valores SSIM obtidos para cada canal em um valor único os chamados SSIM Compostos. Finalmente, a fim de buscar melhores correlações entre SSIM e avaliação subjetiva, propomos a utilização da mínima diferença de cor perceptível, calculada utilizando o espaço de cores CIELAB, conjuntamente com o SSIM. Para os testes são utilizados três bancos de dados de imagens coloridas, LIVE, IVC e TID, a fim de se conferir consistência aos resultados. A avaliação dos resultados é feita utilizando as métricas empregadas pelo VQEG (Video Quality Experts Group) para a avaliação da qualidade de vídeos, com uma adaptação. As conclusões do trabalho sugerem que os melhores resultados para avaliação da qualidade de imagens coloridas usando o SSIM são obtidas usando os canais de luminância dos espaços de cores YCbCr, L&#945;&#946; e especialmente o CIELAB. Também se concluiu que a utilização da mínima diferença de cor perceptível contribui para o melhoramento dos resultados da avaliação objetiva. / Objective image quality evaluation is of special interest in many image applications, for example for image compression, where it can be used to control the rate in order to keep a tradeoff between lost of data and image quality; another example is in the application of watermarks, i.e., introduction of descriptive information used to guarantee the authenticity of an image, that must be invisible to the observer who looks at the image. SSIM (Structural SIMilarity) index is a full-reference image quality assessment metric developed to evaluate gray images. This work investigates the application of SSIM in the evaluation of color images. Therefore, four different color spaces are tested RGB, YCbCr, L&#945;&#946; e CIELAB. Initially SSIM is calculated individually for each one of color spaces channels. Then, inspired in (1), the results of the SSIM in the individual channels are combined in a unique result the so called Composite SSIM. Finally, in order to improve the correlations between, calculated using CIELAB color space, together with SSIM. Three color image databases, LIVE, IVC and TID, were employed in the tests in order to confer solidity to the results. The evaluation of the results is made using VQEG (Video Quality Experts Group) methodology, developed for video quality evaluation with an adaptation regarding the time dimension that does not exist in the image domain. The conclusions from the work were that SSIM performs better in the evaluation of color images when applied to luminance channel of YCbCr, L&#945;&#946; and especially to CIELAB color spaces. It was also concluded that the use of just noticeable difference concept improve objective assessment results.