The Use of Latent Semantic Indexing to Mitigate OCR Effects of Related Document Images

Due to both the widespread and multipurpose use of document images and the current availability of a high number of document images repositories, robust information retrieval mechanisms and systems have been increasingly demanded. This paper presents an approach to support the automatic generation of relationships among document images by exploiting Latent Semantic Indexing (LSI) and Optical Character Recognition (OCR). We developed the LinkDI (Linking of Document Images) service, which extracts and indexes document images content, computes its latent semantics, and defines relationships among images as hyperlinks. LinkDI was experimented with document images repositories, and its performance was evaluated by comparing the quality of the relationships created among textual documents as well as among their respective document images. Considering those same document images, we ran further experiments in order to compare the performance of LinkDI when it exploits or not the LSI technique. Experimental results showed that LSI can mitigate the effects of usual OCR misrecognition, which reinforces the feasibility of LinkDI relating OCR output with high degradation.

Morphological analysis of pitting corrosion in AISI 310S austenitic stainless steel after salt spray exposition

This paper aims to study evolution of increase, distribution and classification of pits in 310S austenitic stainless steels obtained in the state as-received and heat-treated under different exposure times in saline. This work applicability has been based on a technique development for morphologic characterization of localized corrosion associated with description aspects of shapes, size and population-specific parameters. Methodology has been consisted in the following steps: specimens preparation, corrosion tests via salt spray in different conditions, microstructural analysis, pits profiles analysis and images analysis, digital processing and image analysis in order to characterize the pits distribution, morphology and size. Results obtained in digital processing and profiles image analysis have been subjected to statistical analysis using median as parameter in the alloy as received and treated. The alloy as received displays the following morphology: hemispheric pits> transition region A> transition region B> irregular> conic. The pits amount in the treated alloy at each exposure time is: transition region B> hemispherical> transition region A> conic> irregular.

Proteomic analysis of normal and malignant prostate tissue to identify novel proteins lost in cancer

BACKGROUND. Alterations of important protein pathways, including loss of prostate secretory granules, and disruption of the prostatic secretory pathway have been identified as early events in malignancy. In this study, proteomics was used to map the differences in protein expression between normal and malignant prostate tissues and to identify and analyze differentially expressed proteins in human prostate tissue with particular regard to the proteins lost in malignancy. METHODS. Small quantities of normal and malignant prostate tissue were taken fresh from 34 radical prostatectomy cases. After histological examination, proteins were solubilized from selected tissues and separated using two-dimensional electrophoresis. Using image analysis, the proteome of normal and malignant tissues were mapped and differentially expressed proteins (present in normal and absent in malignant tissue) were identified and subsequently analyzed using peptide mass finger printing and N-terminal sequencing. Western blotting and immunohistochemistry were performed to examine expression profiles and tissue localization of candidate proteins. RESULTS. Comparison of protein maps of normal and malignant prostate were used to identify 20 proteins which were lost in malignant transformation, including prostate specific antigen (PSA), alpha-l antichymotrypsin (ACT), haptoglobin, and lactoylglutathione lyase. Three of the 20 had not previously been reported in human prostate tissue (Ubiquitin-like NEDD8, calponin, and a follistatin-related protein). Western blotting confirmed differences in the expression profiles of NEDD8 and calponin, and immunohistochemistry demonstrated differences in the cellular localization of these two proteins in normal and malignant prostate glands. CONCLUSIONS. The expression of NEDD8, calponin, and the follistatin-related protein in normal prostate tissues is a novel finding and the role of these important functional proteins in normal prostate and their loss or reduced expression in prostate malignancy warrants further investigations. (C) 2002 Wiley-Liss, Inc.

Microvascular Lymphatic Density Analysis in Cutaneous Regressive and Nonregressive Superficial Spreading Melanomas Using the Lymphatic Marker D2-40

Background: The prognostic significance of spontaneous regression in melanoma, especially thin lesions, has been a controversial issue for the past 20 years, although recent studies suggest that extensive and late regression may be related to worse prognosis. Many data suggest that lymphangiogenesis predicts metastatic spread in melanoma. Methods: We have quantified lymphatic microvascular density (LMVD) in thin (<= 1.0 mm) superficial spreading melanomas comparing regressive and nonregressive melanomas, regressive and nonregressive areas from the same tumor, and early and late histological stages of regression in the same tumor. In addition, we tried to correlate lymphangiogenesis and tumor growth phase. We conducted histological examinations and immunohistochemical analyses using monoclonal antibody D2-40 with subsequent quantification by image analysis of 37 melanomas, 16 regressive and 21 nonregressive (controls). Results: We found higher LMVD in the late stage of regression compared with nonregressive area (internal control) of regressive melanomas. Conclusions: Our study suggest that the late stage of spontaneous regression in thin melanomas may be related to worse prognosis as it showed higher LMVD, and evidence shows that this is related with increased risk of metastatic spread. But this supposition must be confirmed by a longer follow-up for detection of lymph node metastases.

Supporting content-based image retrieval and computer-aided diagnosis systems with association rule-based techniques

In this work, we take advantage of association rule mining to support two types of medical systems: the Content-based Image Retrieval (CBIR) systems and the Computer-Aided Diagnosis (CAD) systems. For content-based retrieval, association rules are employed to reduce the dimensionality of the feature vectors that represent the images and to improve the precision of the similarity queries. We refer to the association rule-based method to improve CBIR systems proposed here as Feature selection through Association Rules (FAR). To improve CAD systems, we propose the Image Diagnosis Enhancement through Association rules (IDEA) method. Association rules are employed to suggest a second opinion to the radiologist or a preliminary diagnosis of a new image. A second opinion automatically obtained can either accelerate the process of diagnosing or to strengthen a hypothesis, increasing the probability of a prescribed treatment be successful. Two new algorithms are proposed to support the IDEA method: to pre-process low-level features and to propose a preliminary diagnosis based on association rules. We performed several experiments to validate the proposed methods. The results indicate that association rules can be successfully applied to improve CBIR and CAD systems, empowering the arsenal of techniques to support medical image analysis in medical systems. (C) 2009 Elsevier B.V. All rights reserved.

An association rule-based method to support medical image diagnosis with efficiency

In this paper, we propose a method based on association rule-mining to enhance the diagnosis of medical images (mammograms). It combines low-level features automatically extracted from images and high-level knowledge from specialists to search for patterns. Our method analyzes medical images and automatically generates suggestions of diagnoses employing mining of association rules. The suggestions of diagnosis are used to accelerate the image analysis performed by specialists as well as to provide them an alternative to work on. The proposed method uses two new algorithms, PreSAGe and HiCARe. The PreSAGe algorithm combines, in a single step, feature selection and discretization, and reduces the mining complexity. Experiments performed on PreSAGe show that this algorithm is highly suitable to perform feature selection and discretization in medical images. HiCARe is a new associative classifier. The HiCARe algorithm has an important property that makes it unique: it assigns multiple keywords per image to suggest a diagnosis with high values of accuracy. Our method was applied to real datasets, and the results show high sensitivity (up to 95%) and accuracy (up to 92%), allowing us to claim that the use of association rules is a powerful means to assist in the diagnosing task.

Analysis of enamel microbiopsies in shed primary teeth by Scanning Electron Microscopy (SEM) and Polarizing Microscopy (PM)

The aims of this study were 1) to verify how close to the theoretically presumed areas are the areas of enamel microbiopsies carried out in vivo or in exfoliated teeth; 2) to test whether the etching solution penetrates beyond the tape borders: 3) to test whether the etching solution demineralizes the enamel in depth. 24 shed upper primary central incisors were randomly divided into two groups: the Rehydrated Teeth Group and the Dry Teeth Group. An enamel microbiopsy was performed, and the enamel microbiopsies were then analyzed by Scanning Electron Microscopy (SEMI) and Polarizing Microscopy (PM). Quantitative birefringence measurements were performed. The ""true"" etched area was determined by measuring the etched enamel using the NIH Image analysis program. Enamel birefringence was compared using the paired t test. There was a statistically significant difference when the etched areas in the Rehydrated teeth were compared with those of the Dry teeth (p = 0.04). The etched areas varied from -11.6% to 73.5% of the presumed area in the Rehydrated teeth, and from 6.6% to 61.3% in the Dry teeth. The mean percentage of variation in each group could be used as a correction factor for the etched area. Analysis of PM pictures shows no evidence of in-depth enamel demineralization by the etching solution. No statistically significant differences in enamel birefringence were observed between values underneath and outside the microbiopsy area in the same tooth, showing that no mineral loss occurred below the enamel superficial layer. Our data showed no evidence of in-depth enamel demineralization by the etching solution used in the enamel microbiopsy proposed for primary enamel. This study also showed a variation in the measured diameter of the enamel microbiopsy in nineteen teeth out of twenty four, indicating that in most cases the etching solution penetrated beyond the tape borders. (C) 2009 Elsevier B.V. All rights reserved.

On-line analysis of froth surface in coal and mineral flotation using JKFrothCam

The personal computer revolution has resulted in the widespread availability of low-cost image analysis hardware. At the same time, new graphic file formats have made it possible to handle and display images at resolutions beyond the capability of the human eye. Consequently, there has been a significant research effort in recent years aimed at making use of these hardware and software technologies for flotation plant monitoring. Computer-based vision technology is now moving out of the research laboratory and into the plant to become a useful means of monitoring and controlling flotation performance at the cell level. This paper discusses the metallurgical parameters that influence surface froth appearance and examines the progress that has been made in image analysis of flotation froths. The texture spectrum and pixel tracing techniques developed at the Julius Kruttschnitt Mineral Research Centre are described in detail. The commercial implementation, JKFrothCam, is one of a number of froth image analysis systems now reaching maturity. In plants where it is installed, JKFrothCam has shown a number of performance benefits. Flotation runs more consistently, meeting product specifications while maintaining high recoveries. The system has also shown secondary benefits in that reagent costs have been significantly reduced as a result of improved flotation control. (C) 2002 Elsevier Science B.V. All rights reserved.

Methods for automatic and assisted image annotation

Personal memories composed of digital pictures are very popular at the moment. To retrieve these media items annotation is required. During the last years, several approaches have been proposed in order to overcome the image annotation problem. This paper presents our proposals to address this problem. Automatic and semi-automatic learning methods for semantic concepts are presented. The automatic method is based on semantic concepts estimated using visual content, context metadata and audio information. The semi-automatic method is based on results provided by a computer game. The paper describes our proposals and presents their evaluations.

Dependent component analysis: a hyperspectral unmixing algorithm

Linear unmixing decomposes a hyperspectral image into a collection of reflectance spectra of the materials present in the scene, called endmember signatures, and the corresponding abundance fractions at each pixel in a spatial area of interest. This paper introduces a new unmixing method, called Dependent Component Analysis (DECA), which overcomes the limitations of unmixing methods based on Independent Component Analysis (ICA) and on geometrical properties of hyperspectral data. DECA models the abundance fractions as mixtures of Dirichlet densities, thus enforcing the constraints on abundance fractions imposed by the acquisition process, namely non-negativity and constant sum. The mixing matrix is inferred by a generalized expectation-maximization (GEM) type algorithm. The performance of the method is illustrated using simulated and real data.

Does Independent Component Analysis Play a Role in Unmixing Hyperspectral Data?

Chapter in Book Proceedings with Peer Review First Iberian Conference, IbPRIA 2003, Puerto de Andratx, Mallorca, Spain, JUne 4-6, 2003. Proceedings

Vertex component analysis: a fast algorithm to extract endmembers spectra from hyperspectral data

Chapter in Book Proceedings with Peer Review First Iberian Conference, IbPRIA 2003, Puerto de Andratx, Mallorca, Spain, JUne 4-6, 2003. Proceedings

Damage analysis of carbon/epoxy plates after drilling

Drilling of composites plates normally uses traditional techniques but damage risk is high. NDT use is important. Damage in a carbon/epoxy plate is evaluated by enhanced X-rays. Four different drills are used. The images are analysed using Computational Vision techniques. Surface roughness is compared. Results suggest strategies for delamination reduction.

O património local como recurso para o desenvolvimento de competências essenciais da história no 1.º ciclo

Relatório de Estágio apresentado à Escola Superior de Educação de Lisboa para obtenção de grau de mestre em Ensino do 1.º e do 2.º Ciclo do Ensino Básico

Imagiologia Espetral - Análise Forense de Notas e Escrita Manual

A análise forense de documentos é uma das áreas das Ciências Forenses, responsável pela verificação da autenticidade dos documentos. Os documentos podem ser de diferentes tipos, sendo a moeda ou escrita manual as evidências forenses que mais frequentemente motivam a análise. A associação de novas tecnologias a este processo de análise permite uma melhor avaliação dessas evidências, tornando o processo mais célere. Esta tese baseia-se na análise forense de dois tipos de documentos - notas de euro e formulários preenchidos por escrita manual. Neste trabalho pretendeu-se desenvolver técnicas de processamento e análise de imagens de evidências dos tipos referidos com vista a extração de medidas que permitam aferir da autenticidade dos mesmos. A aquisição das imagens das notas foi realizada por imagiologia espetral, tendo-se definidas quatro modalidades de aquisição: luz visível transmitida, luz visível refletida, ultravioleta A e ultravioleta C. Para cada uma destas modalidades de aquisição, foram também definidos 2 protocolos: frente e verso. A aquisição das imagens dos documentos escritos manualmente efetuou-se através da digitalização dos mesmos com recurso a um digitalizador automático de um aparelho multifunções. Para as imagens das notas desenvolveram-se vários algoritmos de processamento e análise de imagem, específicos para este tipo de evidências. Esses algoritmos permitem a segmentação da região de interesse da imagem, a segmentação das sub-regiões que contém as marcas de segurança a avaliar bem como da extração de algumas características. Relativamente as imagens dos documentos escritos manualmente, foram também desenvolvidos algoritmos de segmentação que permitem obter todas as sub-regiões de interesse dos formulários, de forma a serem analisados os vários elementos. Neste tipo de evidências, desenvolveu-se ainda um algoritmo de análise para os elementos correspondentes à escrita de uma sequência numérica o qual permite a obtenção das imagens correspondentes aos caracteres individuais. O trabalho desenvolvido e os resultados obtidos permitiram a definição de protocolos de aquisição de imagens destes tipos de evidências. Os algoritmos automáticos de segmentação e análise desenvolvidos ao longo deste trabalho podem ser auxiliares preciosos no processo de análise da autenticidade dos documentos, o qual, ate então, é feito manualmente. Apresentam-se ainda os resultados dos estudos feitos às diversas evidências, nomeadamente as performances dos diversos algoritmos analisados, bem como algumas das adversidades encontradas durante o processo. Apresenta-se também uma discussão da metodologia adotada e dos resultados, bem como de propostas de continuação deste trabalho, nomeadamente, a extração de características e a implementação de classificadores capazes aferir da autenticidade dos documentos.