• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 150
  • 54
  • 15
  • 13
  • 13
  • 7
  • 2
  • 2
  • 2
  • 1
  • 1
  • Tagged with
  • 301
  • 301
  • 117
  • 89
  • 73
  • 70
  • 69
  • 54
  • 46
  • 46
  • 45
  • 44
  • 43
  • 42
  • 42
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
11

General image classifier for fluorescence microscopy using transfer learning

Öhrn, Håkan January 2019 (has links)
Modern microscopy and automation technologies enable experiments which can produce millions of images each day. The valuable information is often sparse, and requires clever methods to find useful data. In this thesis a general image classification tool for fluorescence microscopy images was developed usingfeatures extracted from a general Convolutional Neural Network (CNN) trained on natural images. The user selects interesting regions in a microscopy image and then, through an iterative process, using active learning, continually builds a training data set to train a classifier that finds similar regions in other images. The classifier uses conformal prediction to find samples that, if labeled, would most improve the learned model as well as specifying the frequency of errors the classifier commits. The result show that with the appropriate choice of significance one can reach a high confidence in true positive. The active learning approach increased the precision with a downside of finding fewer examples.
12

Complex-Wavelet Structural Similarity Based Image Classification

Gao, Yang January 2012 (has links)
Complex wavelet structural similarity (CW-SSIM) index has been recognized as a novel image similarity measure of broad potential applications due to its robustness to small geometric distortions such as translation, scaling and rotation of images. Nevertheless, how to make the best use of it in image classification problems has not been deeply investi- gated. In this study, we introduce a series of novel image classification algorithms based on CW-SSIM and use handwritten digit and face image recognition as examples for demonstration, including CW-SSIM based nearest neighbor method, CW-SSIM based k means method, CW-SSIM based support vector machine method (SVM) and CW-SSIM based SVM using affinity propagation. Among the proposed approaches, the best compromise between accuracy and complexity is obtained by the CW-SSIM support vector machine algorithm, which combines an unsupervised clustering method to divide the training images into clusters with representative images and a supervised learning method based on support vector machines to maximize the classification accuracy. Our experiments show that such a conceptually simple image classification method, which does not involve any registration, intensity normalization or sophisticated feature extraction processes, and does not rely on any modeling of the image patterns or distortion processes, achieves competitive performance with reduced computational cost.
13

Complex-Wavelet Structural Similarity Based Image Classification

Gao, Yang January 2012 (has links)
Complex wavelet structural similarity (CW-SSIM) index has been recognized as a novel image similarity measure of broad potential applications due to its robustness to small geometric distortions such as translation, scaling and rotation of images. Nevertheless, how to make the best use of it in image classification problems has not been deeply investi- gated. In this study, we introduce a series of novel image classification algorithms based on CW-SSIM and use handwritten digit and face image recognition as examples for demonstration, including CW-SSIM based nearest neighbor method, CW-SSIM based k means method, CW-SSIM based support vector machine method (SVM) and CW-SSIM based SVM using affinity propagation. Among the proposed approaches, the best compromise between accuracy and complexity is obtained by the CW-SSIM support vector machine algorithm, which combines an unsupervised clustering method to divide the training images into clusters with representative images and a supervised learning method based on support vector machines to maximize the classification accuracy. Our experiments show that such a conceptually simple image classification method, which does not involve any registration, intensity normalization or sophisticated feature extraction processes, and does not rely on any modeling of the image patterns or distortion processes, achieves competitive performance with reduced computational cost.
14

Color Invariant Skin Segmentation

Xu, Han 25 March 2022 (has links)
This work addresses the problem of automatically detecting human skin in images without reliance on color information. Unlike previous methods, we present a new approach that performs well in the absence of such information. A key aspect of the work is that color-space augmentation is applied strategically during the training, with the goal of reducing the influence of features that are based entirely on color and increasing more semantic understanding. The resulting system exhibits a dramatic improvement in performance for images in which color details are diminished. We have demonstrated the concept using the U-Net architecture, and experimental results show improvements in evaluations for all Fitzpatrick skin tones in the ECU dataset. We further tested the system with RFW dataset to show that the proposed method is consistent across different ethnicities and reduces bias to any skin tones. Therefore, this work has strong potential to aid in mitigating bias in automated systems that can be applied to many applications including surveillance and biometrics. / Master of Science / Skin segmentation deals with the classification of skin and non-skin pixels and regions in a image containing these information. Although most previous skin-detection methods have used color cues almost exclusively, they are vulnerable to external factors (e.g., poor or unnatural illumination and skin tones). In this work, we present a new approach based on U-Net that performs well in the absence of color information. To be specific, we apply a new color space augmentation into the training stage to improve the performance of skin segmentation system over the illumination and skin tone diverse. The system was trained and tested with both original and color changed ECU dataset. We also test our system with RFW dataset, a larger dataset with four human races with different skin tones. The experimental results show improvements in evaluations for skin tones and complex illuminations.
15

[en] COMPARING AUTOMATIC IMAGE CLASSIFICATION TECHNIQUES OF REMOTE SENSING IMAGES / [pt] ANÁLISE COMPARATIVA DE TÉCNICAS DE CLASSIFICAÇÃO AUTOMÁTICA DE IMAGENS DE SENSORIAMENTO REMOTO

LEONARDO VIDAL BATISTA 22 August 2006 (has links)
[pt] Neste trabalho, diversas técnicas de classificação automática de imagens de sensoriamento remoto são investigadas. Na análise, incluem-se um método não- paramétrico, denominado K-Médias. Adaptativos Hierárquico (KMAH), e seis paramétricos: o Classificador de Máxima Verossimilhança (MV), o de Máxima Probabilidade a Posteriori (MAP), o MAP Adaptativo (MAPA), por Subimagens (MAPSI), o Contextual Tilton-Swain (CXTS) e o Contextual por Subimagens (CXSI). O treinamento necessário à implementação das técnicas paramétricas foi realizado de forma não-supervisionada, usando-se para tanto a classificação efetuada pelo KMAH. Considerações a respeito das vantagens e desvantagens dos classificadores, de acordo com a observação das taxas de erros e dos tempos de processamento, apontaram as técnicas MAPA e MAPSI com as mais convenientes / [en] In this thesis, several techniques of automatic classfication of remote sensing impeages are investigated. Included in the analysis are ane non-parametric method, known as Adaptative hierarchical K-means (KMAH), and six parametric ones: the Maximum Likelihood (MV), the Maximum a Posteriori Probability (MAP), the Adaptative MAP (MAPA), the Subimages MAP (MAPSI), the tilton-Swain Contextual, (CXTS) and the Subimages Contextual (CXSI) classifiers. The necessary training for the parametric case was done in a non-supervised form, by using the KMAH classification. Considerations about the advantages and disadvantages of the classifiers were made and, based on the observation of the error rates and processing time, the MAPA and MAPSI have shown the best performances.
16

Large-scale learning of discriminative image representations

Simonyan, Karen January 2013 (has links)
This thesis addresses the problem of designing discriminative image representations for a variety of computer vision tasks. Our approach is to employ large-scale machine learning to obtain novel representations and improve the existing ones. This allows us to propose descriptors for a variety of applications, such as local feature matching, image retrieval, image classification, and face verification. Our image and region descriptors are discriminative, compact, and achieve state-of-the-art results on challenging benchmarks. Local region descriptors play an important role in image matching and retrieval applications. We train the descriptors using a convex learning framework, which learns the configuration of spatial pooling regions, as well as a discriminative linear projection onto a lower-dimensional subspace. The convexity of the corresponding optimisation problems is achieved by using convex, sparsity-inducing regularisers: the L1 norm and the nuclear (trace) norm. We then extend the descriptor learning framework to the setting, where learning is performed from large image collections, for which the ground-truth feature matches are not available. To tackle this problem, we use the latent variables formulation, which allows us to avoid prefixing correct and incorrect matches based on heuristics. Image recognition systems strongly rely on discriminative image representations to achieve high accuracy. We propose several improvements for the Fisher vector and VLAD image descriptors, showing that better image classification performance can be achieved by using appropriate normalisation and local feature transformation. We then turn to the face image domain, where image descriptors, based on handcrafted facial landmarks, are currently widely employed. Our approach is different: we densely compute local features over face images, and then encode them using the Fisher vector. The latter is then projected onto a learnt low-dimensional subspace, yielding a compact and discriminative face image representation. We also introduce a deep image representation, termed the Fisher network, which can be seen as a hybrid between shallow representations (which it generalises) and deep neural networks. The Fisher network is based on stacking Fisher encodings, which is feasible due to the supervised dimensionality reduction, injected between encodings. Finally, we address the problem of fast medical image search, where we are interested in designing a system, which can be instantly queried by an arbitrary Region of Interest (ROI). To facilitate that, we present a medical image repository representation, based on the pre-computed non-rigid transformations between selected images (exemplars) and all other images. This allows for a fast retrieval of the query ROI, since only a fixed number of registrations to the exemplars should be computed to establish the ROI correspondences in all repository images.
17

Implementação de dados obtidos com imagens do sensor TM do Landsat 5 e da missão SRTM no modelo atmosférico BRAMS

Marques, Andréa Cury January 2009 (has links)
O estudo e a previsão dos sistemas de tempo, e suas variantes, é cada vez mais uma preocupação constante e difundida no meio cientifico. Esta necessidade torna-se imprescindível, à medida que tais eventos podem causar irreparáveis perdas materiais e humanas, com forte influência no seu desenvolvimento econômico e social. O BRAMS (Brazilian Regional Atmospheric Modeling System), modelo de mesoescala, tem como característica principal o aninhamento de grades, permitindo assim obter o comportamento de escala sinótica e microescala em uma única simulação. Este recebe como informações de entrada, dados de observações de superfície e altitude, subprodutos gerados de satélite ou então resultados de modelos numéricos, e estes dados necessitam estar em arquivo com formato compatível com o código do mesmo, para serem processados posteriormente. O objetivo deste trabalho foi utilizar dados provenientes do Satélite LANDSAT 5 TM (Land Remote Sensing Satellite – Thematic Mapper), para substituição das informações de vegetação e informações de altimetria da missão SRTM (Shutle Radar Topography Mission), utilizando estas informações como dados de entrada no mesmo, melhorando assim a representação das características físicas da região. A Região Metropolitana de Porto Alegre, foi a escolhida como área de estudo e especificamente foi testada a diferença quanto à simulação do modelo sem e com a implementação. Com o intuito de abranger completamente a área de estudo foram utilizadas 2 cenas do sensor TM, para a composição de mosaico de imagens, gerado originalmente com resolução espacial de 30 metros. Este mosaico foi editado, e submetido a uma classificação supervisionada através do Método da Máxima Verossimilhança com uma qualidade final na classificação de 99,7%. Após a classificação o mosaico foi reamostrado para 500 metros de resolução espacial, também foi feita uma adequação da codificação da classificação de acordo com os códigos do BRAMS. As simulações compreenderam às 24 horas do dia 9 de janeiro de 2007. Para a análise da contribuição da topografia e vegetação, foram analisadas as saídas do modelo. O resultado desta interação pode ser observado no campo de algumas variáveis meteorológicas, como direção do vento, temperatura e umidade relativa, que apresentaram comportamento distinto em cada simulação, demonstrando uma diferença qualitativa entre as duas simulações. / The study and attempt to predict weather, systems and its variants, is increasingly a constant concern of science and it is widely disseminated in the scientific field. This requirement becomes imperative, to the extent that such events can cause irreparable human and material losses, with strong influence in their social and economic development. The Brazilian Regional Atmospheric Modeling System – BRAMS, a mesoscale model, which has nesting grids as a main feature, therefore it obtains the scaling synoptic and microscale behavior on just a single simulation. It receives incoming information, surface observations and altitude data, by-products generated by satellite or numerical model results, and these data need to be set into a file format that is compatible to the code, in order to be processed later. The purpose of this work was to utilize satellite data from the LANDSAT 5 TM (Land Remote Sensing Satellite – Thematic Mapper) for the replacement of vegetation and altitude data obtained during the SRTM (Shuttle Radar Topography Mission), using this information as an input data on it, thus improving the representation of the physical features of the chosen region. The metropolitan region of Porto Alegre was chosen as the study area, and the difference as to the simulation of the model was specifically tested, with and without implementation. In order to completely cover the study area, two image scenes were used from the TM sensor for the mosaic composition, originally generated with a 30-meter spatial resolution. The mosaic was edited, and then submitted to a supervised classification through Maximum Likelihood Method with a final quality classification of 99.7%. After submitting the mosaic to sorting, it was resample into a 500-meter spatial resolution, it has been also made an appropriateness of the codification of classification according to BRAMS’ codes. The simulations comprised the 24 hours of January 9th 2007. For the analysis of the contribution of topography and vegetation, the model outputs were analyzed. The result of this interaction may be observed in the field of meteorological variables, such as some wind directions, temperature and relative humidity, which have distinct behavior at each simulation, demonstrating a qualitative difference between the two simulations.
18

Implementação de dados obtidos com imagens do sensor TM do Landsat 5 e da missão SRTM no modelo atmosférico BRAMS

Marques, Andréa Cury January 2009 (has links)
O estudo e a previsão dos sistemas de tempo, e suas variantes, é cada vez mais uma preocupação constante e difundida no meio cientifico. Esta necessidade torna-se imprescindível, à medida que tais eventos podem causar irreparáveis perdas materiais e humanas, com forte influência no seu desenvolvimento econômico e social. O BRAMS (Brazilian Regional Atmospheric Modeling System), modelo de mesoescala, tem como característica principal o aninhamento de grades, permitindo assim obter o comportamento de escala sinótica e microescala em uma única simulação. Este recebe como informações de entrada, dados de observações de superfície e altitude, subprodutos gerados de satélite ou então resultados de modelos numéricos, e estes dados necessitam estar em arquivo com formato compatível com o código do mesmo, para serem processados posteriormente. O objetivo deste trabalho foi utilizar dados provenientes do Satélite LANDSAT 5 TM (Land Remote Sensing Satellite – Thematic Mapper), para substituição das informações de vegetação e informações de altimetria da missão SRTM (Shutle Radar Topography Mission), utilizando estas informações como dados de entrada no mesmo, melhorando assim a representação das características físicas da região. A Região Metropolitana de Porto Alegre, foi a escolhida como área de estudo e especificamente foi testada a diferença quanto à simulação do modelo sem e com a implementação. Com o intuito de abranger completamente a área de estudo foram utilizadas 2 cenas do sensor TM, para a composição de mosaico de imagens, gerado originalmente com resolução espacial de 30 metros. Este mosaico foi editado, e submetido a uma classificação supervisionada através do Método da Máxima Verossimilhança com uma qualidade final na classificação de 99,7%. Após a classificação o mosaico foi reamostrado para 500 metros de resolução espacial, também foi feita uma adequação da codificação da classificação de acordo com os códigos do BRAMS. As simulações compreenderam às 24 horas do dia 9 de janeiro de 2007. Para a análise da contribuição da topografia e vegetação, foram analisadas as saídas do modelo. O resultado desta interação pode ser observado no campo de algumas variáveis meteorológicas, como direção do vento, temperatura e umidade relativa, que apresentaram comportamento distinto em cada simulação, demonstrando uma diferença qualitativa entre as duas simulações. / The study and attempt to predict weather, systems and its variants, is increasingly a constant concern of science and it is widely disseminated in the scientific field. This requirement becomes imperative, to the extent that such events can cause irreparable human and material losses, with strong influence in their social and economic development. The Brazilian Regional Atmospheric Modeling System – BRAMS, a mesoscale model, which has nesting grids as a main feature, therefore it obtains the scaling synoptic and microscale behavior on just a single simulation. It receives incoming information, surface observations and altitude data, by-products generated by satellite or numerical model results, and these data need to be set into a file format that is compatible to the code, in order to be processed later. The purpose of this work was to utilize satellite data from the LANDSAT 5 TM (Land Remote Sensing Satellite – Thematic Mapper) for the replacement of vegetation and altitude data obtained during the SRTM (Shuttle Radar Topography Mission), using this information as an input data on it, thus improving the representation of the physical features of the chosen region. The metropolitan region of Porto Alegre was chosen as the study area, and the difference as to the simulation of the model was specifically tested, with and without implementation. In order to completely cover the study area, two image scenes were used from the TM sensor for the mosaic composition, originally generated with a 30-meter spatial resolution. The mosaic was edited, and then submitted to a supervised classification through Maximum Likelihood Method with a final quality classification of 99.7%. After submitting the mosaic to sorting, it was resample into a 500-meter spatial resolution, it has been also made an appropriateness of the codification of classification according to BRAMS’ codes. The simulations comprised the 24 hours of January 9th 2007. For the analysis of the contribution of topography and vegetation, the model outputs were analyzed. The result of this interaction may be observed in the field of meteorological variables, such as some wind directions, temperature and relative humidity, which have distinct behavior at each simulation, demonstrating a qualitative difference between the two simulations.
19

Implementação de dados obtidos com imagens do sensor TM do Landsat 5 e da missão SRTM no modelo atmosférico BRAMS

Marques, Andréa Cury January 2009 (has links)
O estudo e a previsão dos sistemas de tempo, e suas variantes, é cada vez mais uma preocupação constante e difundida no meio cientifico. Esta necessidade torna-se imprescindível, à medida que tais eventos podem causar irreparáveis perdas materiais e humanas, com forte influência no seu desenvolvimento econômico e social. O BRAMS (Brazilian Regional Atmospheric Modeling System), modelo de mesoescala, tem como característica principal o aninhamento de grades, permitindo assim obter o comportamento de escala sinótica e microescala em uma única simulação. Este recebe como informações de entrada, dados de observações de superfície e altitude, subprodutos gerados de satélite ou então resultados de modelos numéricos, e estes dados necessitam estar em arquivo com formato compatível com o código do mesmo, para serem processados posteriormente. O objetivo deste trabalho foi utilizar dados provenientes do Satélite LANDSAT 5 TM (Land Remote Sensing Satellite – Thematic Mapper), para substituição das informações de vegetação e informações de altimetria da missão SRTM (Shutle Radar Topography Mission), utilizando estas informações como dados de entrada no mesmo, melhorando assim a representação das características físicas da região. A Região Metropolitana de Porto Alegre, foi a escolhida como área de estudo e especificamente foi testada a diferença quanto à simulação do modelo sem e com a implementação. Com o intuito de abranger completamente a área de estudo foram utilizadas 2 cenas do sensor TM, para a composição de mosaico de imagens, gerado originalmente com resolução espacial de 30 metros. Este mosaico foi editado, e submetido a uma classificação supervisionada através do Método da Máxima Verossimilhança com uma qualidade final na classificação de 99,7%. Após a classificação o mosaico foi reamostrado para 500 metros de resolução espacial, também foi feita uma adequação da codificação da classificação de acordo com os códigos do BRAMS. As simulações compreenderam às 24 horas do dia 9 de janeiro de 2007. Para a análise da contribuição da topografia e vegetação, foram analisadas as saídas do modelo. O resultado desta interação pode ser observado no campo de algumas variáveis meteorológicas, como direção do vento, temperatura e umidade relativa, que apresentaram comportamento distinto em cada simulação, demonstrando uma diferença qualitativa entre as duas simulações. / The study and attempt to predict weather, systems and its variants, is increasingly a constant concern of science and it is widely disseminated in the scientific field. This requirement becomes imperative, to the extent that such events can cause irreparable human and material losses, with strong influence in their social and economic development. The Brazilian Regional Atmospheric Modeling System – BRAMS, a mesoscale model, which has nesting grids as a main feature, therefore it obtains the scaling synoptic and microscale behavior on just a single simulation. It receives incoming information, surface observations and altitude data, by-products generated by satellite or numerical model results, and these data need to be set into a file format that is compatible to the code, in order to be processed later. The purpose of this work was to utilize satellite data from the LANDSAT 5 TM (Land Remote Sensing Satellite – Thematic Mapper) for the replacement of vegetation and altitude data obtained during the SRTM (Shuttle Radar Topography Mission), using this information as an input data on it, thus improving the representation of the physical features of the chosen region. The metropolitan region of Porto Alegre was chosen as the study area, and the difference as to the simulation of the model was specifically tested, with and without implementation. In order to completely cover the study area, two image scenes were used from the TM sensor for the mosaic composition, originally generated with a 30-meter spatial resolution. The mosaic was edited, and then submitted to a supervised classification through Maximum Likelihood Method with a final quality classification of 99.7%. After submitting the mosaic to sorting, it was resample into a 500-meter spatial resolution, it has been also made an appropriateness of the codification of classification according to BRAMS’ codes. The simulations comprised the 24 hours of January 9th 2007. For the analysis of the contribution of topography and vegetation, the model outputs were analyzed. The result of this interaction may be observed in the field of meteorological variables, such as some wind directions, temperature and relative humidity, which have distinct behavior at each simulation, demonstrating a qualitative difference between the two simulations.
20

Classification of Heart Views in Ultrasound Images

Pop, David January 2020 (has links)
In today’s society, we experience an increasing challenge to provide healthcare to everyone in need due to the increasing number of patients and the shortage of medical staff. Computers have contributed to mitigating this challenge by offloading the medical staff from some of the tasks. With the rise of deep learning, countless new possibilities have opened to help the medical staff even further. One domain where deep learning can be applied is analysis of ultrasound images. In this thesis we investigate the problem of classifying standard views of the heart in ultrasound images with the help of deep learning. We conduct mainly three experiments. First, we use NasNet mobile, InceptionV3, VGG16 and MobileNet, pre-trained on ImageNet, and finetune them to ultrasound heart images. We compare the accuracy of these networks to each other and to the baselinemodel, a CNN that was proposed in [23]. Then we assess a neural network’s capability to generalize to images from ultrasound machines that the network is not trained on. Lastly, we test how the performance of the networks degrades with decreasing amount of training data. Our first experiment shows that all networks considered in this study have very similar performance in terms of accuracy with Inception V3 being slightly better than the rest. The best performance is achieved when the whole network is finetuned to our problem instead of finetuning only apart of it, while gradually unlocking more layers for training. The generalization experiment shows that neural networks have the potential to generalize to images from ultrasound machines that they are not trained on. It also shows that having a mix of multiple ultrasound machines in the training data increases generalization performance. In our last experiment we compare the performance of the CNN proposed in [23] with MobileNet pre-trained on ImageNet and MobileNet randomly initialized. This shows that the performance of the baseline model suffers the least with decreasing amount of training data and that pre-training helps the performance drastically on smaller training datasets.

Page generated in 0.1662 seconds