No description available.

Orientador: Vera Lucia da Silveira Nantes Button / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e Computação / Made available in DSpace on 2018-08-07T03:52:25Z (GMT). No. of bitstreams: 1 Zucatti_GlauciaRibeiro_M.pdf: 2508491 bytes, checksum: f6ba34520ac2e744607166ba5fb60754 (MD5) Previous issue date: 2003 / Resumo: A necessidade da Garantia da Qualidade do serviço prestado no ambiente hospitalar tem sido enfatizada nas publicações em Engenharia Clínica. Este trabalho tem por objetivo principal o desenvolvimento de um programa de controle de qualidade de imagem aplicado a equipamentos de imagem médica gerada por ultra-som Modo-S, envolvendo a elaboração e aplicação de protocolos que descrevam inspeção física e mecânica e testes de desempenho aplicados a estes equipamentos. Para a realização dos testes de desempenho, utilizamos um phantom que permite a aquisição das seguintes características do equipamento: uniformidade de imagem, profundidade de penetração do campo ultra-sônico, precisão das medidas do sistema, detecção de vazios esféricos, resoluções axial e lateral e zona morta. Os procedimentos adotados para a avaliação destas características foram estabelecidos através da consulta a normas internacionais e outras bibliografias específicas. Estas bibliografias especificam que os controles do equipamento devem ser ajustados da mesma maneira a cada teste, portanto, neste trabalho também foi realizado um estudo que avalia a influência dos controles de ganho geral, faixa dinâmica e ampliação da imagem nos testes de desempenho. Foram avaliados dez equipamentos de dois departamentos de ecografia distintos. Os resultados dos testes de controle de qualidade de imagem demonstram que 60% dos equipamentos analisados apresentaram algum tipo de defeito na inspeção física e mecânica e que 95,83% dos transdutores analisados apresentou algum dos indicadores de qualidade além do limite de tolerância / Abstract: Clinical Engineering publications have emphasized the necessity of quality assurance of the services done in the hospital environment. The objective of this work was to develop an image quality control program to be applied to B-mode ultrasound scanners, which included the development and application of protocols which describe physical and mechanical inspection and performance tests. For the accomplishment of the performance tests, we have used a multipurpose phantom that allowed the evaluation of the following scanners characteristics: uniformity of image, sensibility (depth of the ultrasonic field penetration), precision of the system measurements, detection of spherical voids, axial and lateral resolutions and dead zone. The procedures adopted for the evaluation of these characteristics have been established through the examination of international standards and specialized publications. These bibliographic materials specify that the controls of the equipment must be adjusted in the same way at each test realization; therefore, this work also have carried through a study that evaluated the influence of varying the general gain and dynamic range controls and the magnification (zoom) of the image field view in the performance tests results. The quality control tests results showed that 60% of the evaluated equipments presented some kind of problem in the physical and mechanical inspections, and that 95.83% of the evaluated transducers presented some of the quality pointers values beyond the limit of tolerance / Mestrado / Engenharia Biomedica / Mestre em Engenharia Elétrica

The diploma thesis deals with the problematics of machine vision. The research is devoted to description of the machine vision system hardware and software components. In practical part is described design and realization of the software, which allows several tasks of machine vision to be performed at the same time.

Monitoring of public areas and their automatic real-time processing became increasingly significant due to the changing security situation in the world. However, the problem is an analysis of low-quality records, where even the state-of-the-art methods fail in some cases. This work investigates an important area of image similarity – biometric identification based on face image. The work deals primarily with the face super-resolution from a sequence of low-resolution images and it compares this approach to the single-frame methods, that are still considered as the most accurate. A new dataset was created for this purpose, which is directly designed for the multi-frame face super-resolution methods from the low-resolution input sequence, and it is of comparable size with the leading world datasets. The results were evaluated by both a survey of human perception and defined objective metrics. A hypothesis that multi-frame methods achieve better results than single-frame methods was proved by a comparison of both methods. Architectures, source code and the dataset were released. That caused a creation of the basis for future research in this field.

When scanning biomedical images by magnetic resonance or ultrasound, unwanted elements in the form of noise are entered to the image. With help of various methods it is possible the noise from the image partially remove. There are many methods for noise reduction and every one works on a different principle. As a result of this the results of these methods are different and is necessary for them to be objectively assessed. There is use for the adjustment of the images wavelet transformation and some treshold techniques in the work. The quality of the resulting pictures is tested by the methods for objective quallity tests. Testing was done in the MATLAB program environment on the pictures from magnetic resonance and pictures from ultrasound.