Automated image tagging through tag propagation

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial Para obtenção do grau de Mestre em Engenharia Informática

Análise comparada da classificação “pixel a pixel” e orientada por objecto de uma imagem WorldView 2 de Maputo, Moçambique

O desenvolvimento das tecnologias associadas à Detecção Remota e aos Sistemas de Informação Geográfica encontram-se cada vez mais na ordem do dia. E, graças a este desenvolvimento de métodos para acelerar a produção de informação geográfica, assiste-se a um crescente aumento da resolução geométrica, espectral e radiométrica das imagens, e simultaneamente, ao aparecimento de novas aplicações com o intuito de facilitar o processamento e a análise de imagens através da melhoria de algoritmos para extracção de informação. Resultado disso são as imagens de alta resolução, provenientes do satélite WorldView 2 e o mais recente software Envi 5.0, utilizados neste estudo. O presente trabalho tem como principal objectivo desenvolver um projecto de cartografia de uso do solo para a cidade de Maputo, com recurso ao tratamento e à exploração de uma imagem de alta resolução, comparando as potencialidades e limitações dos resultados extraídos através da classificação “pixel a pixel”, através do algoritmo Máxima Verossimilhança, face às potencialidades e eventuais limitações da classificação orientada por objecto, através dos algoritmos K Nearest Neighbor (KNN) e Support Vector Machine (SVM), na extracção do mesmo número e tipo de classes de ocupação/uso do solo. Na classificação “pixel a pixel”, com a aplicação do algoritmo classificação Máxima Verosimilhança, foram ensaiados dois tipos de amostra: uma primeira constituída por 20 classes de ocupação/uso do solo, e uma segunda por 18 classes. Após a fase de experimentação, os resultados obtidos com a primeira amostra ficaram aquém das espectativas, pois observavam-se muitos erros de classificação. A segunda amostra formulada com base nestes erros de classificação e com o objectivo de os minimizar, permitiu obter um resultado próximo das espectativas idealizadas inicialmente, onde as classes de interesse coincidem com a realidade geográfica da cidade de Maputo. Na classificação orientada por objecto foram 4 as etapas metodológicas utilizadas: a atribuição do valor 5 para a segmentação e 90 para a fusão de segmentos; a selecção de 15 exemplos sobre os segmentos gerados para cada classe de interesse; bandas diferentemente distribuídas para o cálculo dos atributos espectrais e de textura; os atributos de forma Elongation e Form Factor e a aplicação dos algoritmos KNN e SVM. Confrontando as imagens resultantes das duas abordagens aplicadas, verificou-se que a qualidade do mapa produzido pela classificação “pixel a pixel” apresenta um nível de detalhe superior aos mapas resultantes da classificação orientada por objecto. Esta diferença de nível de detalhe é justificada pela unidade mínima do processamento de cada classificador: enquanto que na primeira abordagem a unidade mínima é o pixel, traduzinho uma maior detalhe, a segunda abordagem utiliza um conjunto de pixels, objecto, como unidade mínima despoletando situações de generalização. De um modo geral, a extracção da forma dos elementos e a distribuição das classes de interesse correspondem à realidade geográfica em si e, os resultados são bons face ao que é frequente em processamento semiautomático.

Aplicació de visió per dispositius mòbils

En aquest projecte es presenta l’aplicació per a dispositius mòbils Doppelganger. La seva funció és, a partir d’una fotografia, detectar la cara i mostrar la persona famosa de la nostra base de dades que més s’assembla a la persona en la fotografia. Per la implementació s’han utilitzat algoritmes de visió per computador i d’aprenentatge automàtic com per exemple el PCA i el K-Nearest Neighbor, tot utilitzant llibreries gratuïtes com són les OpenCV.

Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

Pedotransfer functions to predict water retention for soils of the humid tropics: a review

Over the past three decades, pedotransfer functions (PTFs) have been widely used by soil scientists to estimate soils properties in temperate regions in response to the lack of soil data for these regions. Several authors indicated that little effort has been dedicated to the prediction of soil properties in the humid tropics, where the need for soil property information is of even greater priority. The aim of this paper is to provide an up-to-date repository of past and recently published articles as well as papers from proceedings of events dealing with water-retention PTFs for soils of the humid tropics. Of the 35 publications found in the literature on PTFs for prediction of water retention of soils of the humid tropics, 91 % of the PTFs are based on an empirical approach, and only 9 % are based on a semi-physical approach. Of the empirical PTFs, 97 % are continuous, and 3 % (one) is a class PTF; of the empirical PTFs, 97 % are based on multiple linear and polynomial regression of n th order techniques, and 3 % (one) is based on the k-Nearest Neighbor approach; 84 % of the continuous PTFs are point-based, and 16 % are parameter-based; 97 % of the continuous PTFs are equation-based PTFs, and 3 % (one) is based on pattern recognition. Additionally, it was found that 26 % of the tropical water-retention PTFs were developed for soils in Brazil, 26 % for soils in India, 11 % for soils in other countries in America, and 11 % for soils in other countries in Africa.

Image-Based Coral Reef Classification and Thematic Mapping

This paper presents a novel image classification scheme for benthic coral reef images that can be applied to both single image and composite mosaic datasets. The proposed method can be configured to the characteristics (e.g., the size of the dataset, number of classes, resolution of the samples, color information availability, class types, etc.) of individual datasets. The proposed method uses completed local binary pattern (CLBP), grey level co-occurrence matrix (GLCM), Gabor filter response, and opponent angle and hue channel color histograms as feature descriptors. For classification, either k-nearest neighbor (KNN), neural network (NN), support vector machine (SVM) or probability density weighted mean distance (PDWMD) is used. The combination of features and classifiers that attains the best results is presented together with the guidelines for selection. The accuracy and efficiency of our proposed method are compared with other state-of-the-art techniques using three benthic and three texture datasets. The proposed method achieves the highest overall classification accuracy of any of the tested methods and has moderate execution time. Finally, the proposed classification scheme is applied to a large-scale image mosaic of the Red Sea to create a completely classified thematic map of the reef benthos

Keraamisten laattojen luokittelu väripiirteiden avulla

Vaikka keraamisten laattojen valmistusprosessi onkin täysin automatisoitu, viimeinen vaihe eli laaduntarkistus ja luokittelu tehdään yleensä ihmisvoimin. Automaattinen laaduntarkastus laattojen valmistuksessa voidaan perustella taloudellisuus- ja turvallisuusnäkökohtien avulla. Tämän työn tarkoituksena on kuvata tutkimusprojektia keraamisten laattojen luokittelusta erilaisten väripiirteiden avulla. Oleellisena osana tutkittiin RGB- ja spektrikuvien välistä eroa. Työn teoreettinen osuus käy läpi aiemmin aiheesta tehdyn tutkimuksen sekä antaa taustatietoa konenäöstä, hahmontunnistuksesta, luokittelijoista sekä väriteoriasta. Käytännön osan aineistona oli 25 keraamista laattaa, jotka olivat viidestä eri luokasta. Luokittelussa käytettiin apuna k:n lähimmän naapurin (k-NN) luokittelijaa sekä itseorganisoituvaa karttaa (SOM). Saatuja tuloksia verrattiin myös ihmisten tekemään luokitteluun. Neuraalilaskenta huomattiin tärkeäksi työkaluksi spektrianalyysissä. SOM:n ja spektraalisten piirteiden avulla saadut tulokset olivat lupaavia ja ainoastaan kromatisoidut RGB-piirteet olivat luokittelussa parempia kuin nämä.

Using aster multispectral imagery for mapping woody invasive species in pico da vara natural reserve (Azores Islands, Portugal)

This paper aims to assess the effectiveness of ASTER imagery to support the mapping of Pittosporum undulatum, an invasive woody species, in Pico da Vara Natural Reserve (S. Miguel Island, Archipelago of the Azores, Portugal). This assessment was done by applying K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Maximum Likelihood (MLC) pixel-based supervised classifications to 4 different geographic and remote sensing datasets constituted by the Visible, Near-Infrared (VNIR) and Short Wave Infrared (SWIR) of the ASTER sensor and by digital cartography associated to orography (altitude and "distance to water streams") of which the spatial distribution of Pittosporum undulatum directly depends. Overall, most performed classifications showed a strong agreement and high accuracy. At targeted species level, the two higher classification accuracies were obtained when applying MLC and KNN to the VNIR bands coupled with auxiliary geographic information use. Results improved significantly by including ecology and occurrence information of species (altitude and distance to water streams) in the classification scheme. These results show that the use of ASTER sensor VNIR spectral bands, when coupled to relevant ancillary GIS data, can constitute an effective and low cost approach for the evaluation and continuous assessment of Pittosporum undulatum woodland propagation and distribution within Protected Areas of the Azores Islands.

Exploring Bit-Difference for Approximate KNN Search in High-dimensional Databases

In this paper, we develop a novel index structure to support efficient approximate k-nearest neighbor (KNN) query in high-dimensional databases. In high-dimensional spaces, the computational cost of the distance (e.g., Euclidean distance) between two points contributes a dominant portion of the overall query response time for memory processing. To reduce the distance computation, we first propose a structure (BID) using BIt-Difference to answer approximate KNN query. The BID employs one bit to represent each feature vector of point and the number of bit-difference is used to prune the further points. To facilitate real dataset which is typically skewed, we enhance the BID mechanism with clustering, cluster adapted bitcoder and dimensional weight, named the BID⁺. Extensive experiments are conducted to show that our proposed method yields significant performance advantages over the existing index structures on both real life and synthetic high-dimensional datasets.

Paged similarity queries

An important feature of a database management systems (DBMS) is its client/server architecture, where managing shared memory among the clients and the server is always an tough issue. However, similarity queries are specially sensitive to this kind of architecture, since the answer sizes vary widely. Usually, the answers of similarity query are fully processed to be sent in full to the user, who often is interested in just parts of the answer, e.g. just few elements closer or farther to the query reference. Compelling the DBMS to retrieve the full answer, further ignoring its majority is at least a waste of server processing power. Paging the answer is a technique that splits the answer onto several pages, following client requests. Despite the success of paging on traditional queries, little work has been done to support it in similarity queries. In this work, we present a technique that not only provides paging in similarity range or k-nearest neighbor queries, but also supports them in two variations: the forward similarity query and the backward similarity query. They return elements either increasingly farther of increasingly closer to the query reference. The reported experiments show that, depending on the proportion of the interesting part over the full answer, both techniques allow answering queries much faster than it is obtained in the non-paged way. (C) 2010 Elsevier Inc. All rights reserved.

Uma Análise de métodos de distriubuição de atributos em comitês de classificadores

The objective of the researches in artificial intelligence is to qualify the computer to execute functions that are performed by humans using knowledge and reasoning. This work was developed in the area of machine learning, that it s the study branch of artificial intelligence, being related to the project and development of algorithms and techniques capable to allow the computational learning. The objective of this work is analyzing a feature selection method for ensemble systems. The proposed method is inserted into the filter approach of feature selection method, it s using the variance and Spearman correlation to rank the feature and using the reward and punishment strategies to measure the feature importance for the identification of the classes. For each ensemble, several different configuration were used, which varied from hybrid (homogeneous) to non-hybrid (heterogeneous) structures of ensemble. They were submitted to five combining methods (voting, sum, sum weight, multiLayer Perceptron and naïve Bayes) which were applied in six distinct database (real and artificial). The classifiers applied during the experiments were k- nearest neighbor, multiLayer Perceptron, naïve Bayes and decision tree. Finally, the performance of ensemble was analyzed comparatively, using none feature selection method, using a filter approach (original) feature selection method and the proposed method. To do this comparison, a statistical test was applied, which demonstrate that there was a significant improvement in the precision of the ensembles

Fluorescence spectroscopy for the detection of tongue carcinoma - validation in an animal model

The efficacy of fluorescence spectroscopy to detect squamous cell carcinoma is evaluated in an animal model following laser excitation at 442 and 532 nm. Lesions are chemically induced with a topical DMBA application at the left lateral tongue of Golden Syrian hamsters. The animals are investigated every 2 weeks after the 4th week of induction until a total of 26 weeks. The right lateral tongue of each animal is considered as a control site (normal contralateral tissue) and the induced lesions are analyzed as a set of points covering the entire clinically detectable area. Based on fluorescence spectral differences, four indices are determined to discriminate normal and carcinoma tissues, based on intraspectral analysis. The spectral data are also analyzed using a multivariate data analysis and the results are compared with histology as the diagnostic gold standard. The best result achieved is for blue excitation using the KNN (K-nearest neighbor, a interspectral analysis) algorithm with a sensitivity of 95.7% and a specificity of 91.6%. These high indices indicate that fluorescence spectroscopy may constitute a fast noninvasive auxiliary tool for diagnostic of cancer within the oral cavity. (C) 2008 Society of Photo-Optical Instrumentation Engineers.

A study of neolignan compounds with biological activity against Paracoccidioides brasiliensis by using quantum chemical and chemometric methods

Métodos quimiométricos (estatísticos) são empregados para classificar um conjunto de compostos derivados de neolignanas com atividade biológica contra a Paracoccidioides brasiliensis. O método AM1 (Austin Model 1) foi utilizado para calcular um conjunto de descritores moleculares (propriedades) para os compostos em estudo. A seguir, os descritores foram analisados utilizando os seguintes métodos de reconhecimento de padrões: Análise de Componentes Principais (PCA), Análise Hierárquica de Agrupamentos (HCA) e o método de K-vizinhos mais próximos (KNN). Os métodos PCA e HCA mostraram-se bastante eficientes para classificação dos compostos estudados em dois grupos (ativos e inativos). Três descritores moleculares foram responsáveis pela separação entre os compostos ativos e inativos: energia do orbital molecular mais alto ocupado (EHOMO), ordem de ligação entre os átomos C1'-R7 (L14) e ordem de ligação entre os átomos C5'-R6 (L22). Como as variáveis responsáveis pela separação entre compostos ativos e inativos são descritores eletrônicos, conclui-se que efeitos eletrônicos podem desempenhar um importante papel na interação entre receptor biológico e compostos derivados de neolignanas com atividade contra a Paracoccidioides brasiliensis.

Novel estimation of the humification degree of soil organic matter by laser-induced breakdown spectroscopy

Soil organic matter (SOM) constitutes an important reservoir of terrestrial carbon and can be considered an alternative for atmospheric carbon storage, contributing to global warming mitigation. Soil management can favor atmospheric carbon incorporation into SUM or its release from SOM to atmosphere. Thus, the evaluation of the humification degree (HD), which is an indication of the recalcitrance of SOM, can provide an estimation of the capacity of carbon sequestration by soils under various managements. The HD of SOM can be estimated by using various analytical techniques including fluorescence spectroscopy. In the present work, the potential of laser-induced breakdown spectroscopy (LIBS) to estimate the HD of SUM was evaluated for the first time. Intensities of emission lines of Al, Mg and Ca from LIBS spectra showing correlation with fluorescence emissions determined by laser-induced fluorescence spectroscopy (LIFS) reference technique were used to obtain a multivaried calibration model based on the k-nearest neighbor (k-NN) method. The values predicted by the proposed model (A-LIBS) showed strong correlation with LIFS results with a Pearson's coefficient of 0.87. The HD of SUM obtained after normalizing A-LIBS by total carbon in the sample showed a strong correlation to that determined by LIFS (0.94), thus suggesting the great potential of LIBS for this novel application. (C) 2014 Elsevier B.V. All rights reserved.

Advantages and Applications of Transforming Empirical Model Input Space with Dimensional Models

Model-based calibration of steady-state engine operation is commonly performed with highly parameterized empirical models that are accurate but not very robust, particularly when predicting highly nonlinear responses such as diesel smoke emissions. To address this problem, and to boost the accuracy of more robust non-parametric methods to the same level, GT-Power was used to transform the empirical model input space into multiple input spaces that simplified the input-output relationship and improved the accuracy and robustness of smoke predictions made by three commonly used empirical modeling methods: Multivariate Regression, Neural Networks and the k-Nearest Neighbor method. The availability of multiple input spaces allowed the development of two committee techniques: a 'Simple Committee' technique that used averaged predictions from a set of 10 pre-selected input spaces chosen by the training data and the "Minimum Variance Committee" technique where the input spaces for each prediction were chosen on the basis of disagreement between the three modeling methods. This latter technique equalized the performance of the three modeling methods. The successively increasing improvements resulting from the use of a single best transformed input space (Best Combination Technique), Simple Committee Technique and Minimum Variance Committee Technique were verified with hypothesis testing. The transformed input spaces were also shown to improve outlier detection and to improve k-Nearest Neighbor performance when predicting dynamic emissions with steady-state training data. An unexpected finding was that the benefits of input space transformation were unaffected by changes in the hardware or the calibration of the underlying GT-Power model.