Key words. Artificial neuronal network, computational vision, image processing and analysis, image segmentation and quantification, multilayer perceptron, materials science.
SummaryThis paper presents a new computational solution to quantify the porosity of synthetic materials from optical microscopic images. The solution is based on an artificial neuronal network of the multilayer perceptron type and a backpropagation algorithm is used for training. To evaluate this new solution, 40 sample images of a synthetic material were analysed and the quality of the results was confirmed by human visual analysis. In addition, these results were compared with ones obtained with a commonly used commercial system confirming their superior quality and the shorter time needed. The effect of images with noise was also studied and the new solution showed itself to be more reliable. The training phase of the new solution was analysed confirming that it can be performed in a very easy and straightforward manner. Thus, the new solution demonstrated that it is a valid and adequate option for researchers, engineers, specialists and other professionals to quantify the porosity of materials from microscopic images in an automatic, fast, efficient and reliable manner.
Macular holes are a blinding condition that occur due to overuse of the fovea, in which a hole alters the natural retinal structure. Optical Coherence Tomography (OCT) is a way of mapping and shaping retinal sections without physical contact and has become a powerful tool for diagnosing pathologies. This paper deals with a review of automated segmentation of macular holes in OCT images, detailing its varied possibilities. It may be considered something new, no reviews were made about the topic. The purpose of this review is to show the latest trends, through the approaches in preprocessing and segmentation. Recent studies were used to validate the research, 2011 onwards, from the Science Direct, IEEE, PubMed and Google scholar bases. The objectives, methodology, tools, database, advantages, disadvantages, validation metrics and results of the selected material are analyzed and mentioned. Based on this, techniques and their results are compared. From this, future outlook scenarios of automated segmentation of macular holes in OCT images are mentioned.
The retina is a part of the ocular system responsible for vision. In the central region of the retina is the macula, that enables detailed view. There is a distinct macular disease called Macular Hole (MH). It causes a condition of low vision related to the weakening of the fovea, high myopia, eye trauma and severe exposure to the sun. A surgery depends of the size and shape of the MH. A macular hole can be identified in Optical Coherence Tomography (OCT) images through the top boundaries of the Internal Limiting Membrane (ILM) and the Retinal Pigment Epithelium (RPE). Manual segmentation of OCT images is time consuming whereas automatic segmentation is fast and has a low computational cost, and consequently of interest to specialists. Thus, the main objective of this work is to develop an algorithm that automatically segments the ILM boundary layer and the area of the MH in OCT images. Another objective that was also pursued included the automatic acquisition of MH measurements. The segmentation was performed through a set of techniques involving shortest distance from a point to a curve (Euclidean Distance), Flood Fill and Border Following algorithms. The proposed method reached satisfactory results for all applications made. The automatic segmentation of MH and the extraction of its measures is a significant contribution to aid the medical diagnosis of the macular hole pathology.
RESUMO:Estudou-se uma forma para estimar o peso dos frutos de melão amarelo por meio de técnicas de Visão Computacional (VC). A estimativa de peso foi baseada na correlação entre o peso real e a segmentação da área do melão. Para isso, a escala da imagem de entrada do melão foi determinada e, em seguida, um filtro de cores e segmentação por contornos foram aplicadas nessas imagens. Para a realização deste trabalho, foram utilizados 65 melões. Dentre estes, 45 frutos foram utilizados para gerar as equações de estimativa de peso, e o restante, 20 imagens de diferentes melões, para a realização dos testes. A melhor correlação obtida entre o peso e a área do melão foi de 0,969. Os resultados mostraram um erro médio de 0,143 (kg) e desvio padrão de 0,146 (kg), para a estimativa do peso do melão. Através de ajustes, nas técnicas implementadas, existe a possibilidade que o sistema proposto seja adaptado para dispositivos móveis ou em sistemas embarcados. Com isso, o sistema pode utilizado, como exemplo, para estimar o peso do melão antes da colheita do fruto.
PALAVRAS-CHAVE:Cucumis melo L., estimativa de peso, Processamento Digital de Imagens.
ESTIMATED WEIGHT OF YELLOW MELON THROUGH COMPUTER VISIONABSTRACT: We studied a way to estimate the weight of yellow melon fruits by means of Computational Vision (VC) techniques. The weight estimate was based on the correlation between the actual weight and the segmentation of the melon area. For this, the input image scale of the melon was determined and then a color filter and contour segmentation were applied to these images. For this work, 65 melons were used. Among these, 45 fruits were used to 1 Doutor, Professor efetivo do IFCE -Sobral, Ceará.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.