Automated Image Analysis Techniques Research Articles

PH influence on oxygen mass transfer coefficient in a bubble column. Individual characterization of kL and a

Experiments were performed in a laboratory scale bubble column (10L), to investigate the pH influence on oxygen mass transfer coefficient, in order to achieve a better control of biological processes. The liquid-side mass transfer coefficient, kL, and the specific interfacial area, a, were studied individually. The specific interfacial area was obtained using the new automatic image analysis technique developed by Ferreira et al. (2012). The pH was changed by the addition to the system of the most common acids and base used in biological process: hydrochloric acid (HCl), phosphoric acid (H3PO4) and potassium hydroxide (KOH). The results show that aqueous systems containing HCl, H3PO4 or KOH present lower volumetric liquid side mass transfer coefficient, kLa, in relation to pure systems (distilled water), this decrease being not linear. It was found that the specific interfacial area presents higher values in KOH and HCl solutions in comparison with distilled water. However, an opposite behavior was observed in the liquid-side mass transfer coefficient values. The kL behavior on the impure systems was explained based on bubble surface contamination. Higbie's and Fröessling's equations were adapted in the present work in order to be used in bubble dispersion systems.

Coastal Vulnerability and Shoreline Changes for Southern Tip of India-Remote Sensing and GIS Approach

The present research aims to classify the vulnerable risk zones of the Southern tip of India using shoreline change analysis and coastal vulnerability index (CVI). The shoreline change analysis has been done by automatic image analysis techniques using multi-temporal Landsat data (1973, 1992, 2000 and 2006). The results have shown remarkable erosion was found in Cape Camoron (Left) (4.21 m/year), Idindakarai (4.56 m/year) and Vijayapathi (4.66 m/year). In contrast, the station between Chinna muttam and Visvanarayanapuram has predominant deposition. The CVI index were established based on following six variables: Geomorphology, Shoreline change rate (m/yr), Coastal slope (deg), Relative Sea level change (mm/yr), Mean wave height (m), Mean Tide range (m). According to the CVI value, Cape Camoron (Left), Idindakarai and Vijayapathi sites are identified as highly vulnerable zones. Overall the study, remarkable coastal landform dynamics observed in chinna muttam. The vulnerable map prepared for the southern tip of Indian coast can be useful to prevent the coastline erosion and future disaster mitigation.

Phase-Based Image Analysis of 3D Seismic Data

Automated image analysis techniques can be effectively used to detect discontinuities (e.g. faults, pinchouts, channels, etc.) within seismic data in a non-subjective manner. Conventional image pro...

DIGITAL RECONSTRUCTION OF THE CHURCH OF SAN ILDEFONSO AT ZAMORA (SPAIN) USING ORTHOWARE

Abstract. This paper describes the surveying process performed on the Church of San Ildefonso in Zamora (Spain) using Orthoware©, an innovative photogrammetric software tool specially designed for the digital reconstruction of cultural heritage. This software is the result of intense R&D at Metria Digital after several years producing heritage true orthoimages, plans and full color 3D models in a commercial environment. Orthoware allows true measurements and produces high quality true orthoimages and full color 3D models starting out from conventional digital photographs. This is a progressive tool designed for non-specialist users, providing intuitive and quick methods to visually diagnose the quality of the results. The Church of San Ildefonso in Zamora was built over a previously existing temple whose Romanesque construction dates back to the 11th century, although it is nowadays hidden among extensions and remodelings carried out up until 18th century. With a length of more than 30 meters, the original floor plan of the Church consists on three naves and three apses, although only one nave is visible now, covered by groin vault, and one semicircular apse partially hidden by the current building. The south front maintains the greater part of its Romanesque origins, in spite of being hidden and higher than the present ground level. At the feet of the temple a tower rises, whose first stage is Romanesque but which has been altered by numerous Baroque elements. The objective of the photogrammetric reconstruction was the integral survey of the monument, including its four façades, interior faces and roofs for the production of some true-orthoimages, cross-sections, longitudinal-sections and ground plans at scale 1/50 with an accuracy of 10 mm for the drawings and a pixel size below 10 mm for the synthetic imagery. The usual photogrammetric workflow for producing true-orthoimages and digital 3D models in cultural heritage depends to a great extent on finding and matching homologous features amongst various images. This is a time-consuming, repetitive and blind recognition process requiring some spatial intuition and experience from the user. Orthoware makes use of automatic image analysis and computer vision techniques to improve this processing. Its innovative graphic user interface allows full interactivity and corrections or refinements to be performed at any time providing intuitive diagnostics from partial results. This flow involves very intensive calculations achieved through a software development specific for GPU (Graphic Processing Unit), using OpenGL (Open Graphics Library) and DirectX. Therefore, a combination of manual and automatic techniques makes up the ideal tool for a production environment. The workflow presented herein allow users to reduce orthoimage production time from months to just a few weeks.

MULTITEMPORAL QUALITY ASSESSMENT OF GRASSLAND AND CROPLAND OBJECTS OF A TOPOGRAPHIC DATASET

Abstract. As a consequence of the wide-spread application of digital geo-data in geographic information systems (GIS), quality control has become increasingly important to enhance the usefulness of the data. For economic reasons a high degree of automation is required for the quality control process. This goal can be achieved by automatic image analysis techniques. An example of how this can be achieved in the context of quality assessment of cropland and grassland GIS objects is given in this paper. The quality assessment of these objects of a topographic dataset is carried out based on multi-temporal information. The multi-temporal approach combines the channels of all available images as a multilayer image and applies a pixel-based SVM-classification. In this way multispectral as well as multi-temporal information is processed in parallel. The features used for the classification consist of spectral, textural (Haralick features) and structural (features derived from a semi-variogram) features. After the SVM-classification, the pixel-based result is mapped to the GIS-objects. Finally, a simple ruled-based approach is used in order to verify the objects of a GIS database. The approach was tested using a multi-temporal data set consisting of one 5-channel RapidEye image (GSD 5 m) and two 3-channel Disaster Monitoring Constellation (DMC) images (GSD 32 m). All images were taken within one year. The results show that by using our approach, quality control of GIS- cropland and grassland objects is possible and the human operator saves time using our approach compared to a completely manual quality assessment.

Pore structure development in oxidized IG-110 nuclear graphite

The oxidation-induced porosity development in nuclear graphite has great effect on its mechanical behavior, thus it is very important to understand the pore structure development of nuclear graphite during oxidation. This paper reports on the oxidation kinetics of grade IG-110 nuclear graphite and the porosity development in oxidized samples. The distribution of the oxidized layer in IG-110 specimens oxidized at 600–750°C was studied using optical microscopy coupled with automated image analysis technique, and the mechanism of porosity development was determined. The thickness of oxidized layer decreased with the oxidation temperature but was independent of the weight loss level. Oxidation caused consumption of graphite structure and development of porosity, which was initiated from the binder phase. Statistical analysis indicated that generation and growth of pores was dominant at low temperatures, while merging and collapse of pores was the main effect at high temperatures. Compared with medium-grained PCEA graphite, the fine-grained IG-110 graphite demonstrates deeper penetration of the oxidant because of its higher pore density and greater porosity.

Special issue on intelligent techniques for multimedia information management and personalization

Over the last decade, we have witnessed an explosive growth in the information available in digital form, especially on the World Wide Web. Today, web browsers and search engines on our PCs provide easy access to a multitude of sources of text and multimedia data; however finding the desired information at the right time is not an easy task. In fact, standard search engines do not consider semantic information that can help in recognizing the relevance of a document with respect to the meaning of a query, so that users have to analyze every document and decide which documents are relevant with respect to the meaning implied in their search. Nowadays, intelligent techniques can be applied to solve challenging problems related to find, extract, filter, and evaluate the users desired information from distributed and heterogeneous multimedia data. Therefore novel smart tools integrating semantic and soft computing techniques are expected to enhance future information management systems improving information retrieval and visualization as well as providing personalized and adaptive applications. The aim of this Special Issue is to present the innovative researches, technologies and developments related to the intelligent management and personalization of multimedia information. This Special Issue was organized with papers from the 7th Atlantic Web Intelligence Conference (AWIC 2011), which was held in Fribourg, Switzerland from January 26 to January 28, 2011. AWIC 2011 received about 50 papers and only 21 papers were accepted for publication. We encouraged the authors of AWIC 2011 to extend their papers and submit to this Special Issue. Based on the quality and the relevance with the Special Issue, we selected seven papers. Each manuscript was reviewed by three reviewers consisting of guest editors and external reviewers. In the first paper by Cudre-Mauroux, the author introduces a new paradigm for the publication of personal information on the Web based on the concept of looselycoupled ontological constructs which reduces the burden on the end-user related to the use of semantic web techniques. The proposed approach encourages end-users to publish potentially incomplete or conflicting information according to their local context and consolidates heterogeneous data with a posteriori, bottom-up and decentralized process. The use of such approach has the main advantage of greatly simplifying the publication of usercreated data while preserving the advantage of expressiveness of semantic technologies. In the second paper by Arkadiusz Tomczyk et al., the authors propose a method, which combines automatic image analysis techniques with human generated knowledge in order to improve semantic descriptions of image content. The proposed method, called Cognitive Hierarchical Active Partitioning (CHAP), extends the active contours method and divides the whole process into a set of interrelated steps where each step provides the appropriate level of semantic knowledge based on the use of external expert experience. In the third paper by Niewiadomski, the author proposes a cylindric extension of interval-valued fuzzy set in order to describe compound linguistic expressions. The new description can be useful when two or more interval-valued fuzzy sets are defined in different universes of discourse but the terms represented concern the same object, e.g. a man E. Mugellini (&) M. Sokhn University of Applied Sciences of Western Switzerland, Fribourg, Switzerland e-mail: elena.mugellini@hefr.ch

Semi-automated Acanthamoeba polyphaga detection and computation of Salmonella typhimurium concentration in spatio-temporal images

Interaction between bacteria and protozoa is an increasing area of interest, however there are a few systems that allow extensive observation of the interactions. A semi-automated approach is proposed to analyse a large amount of experimental data and avoid a time demanding manual object classification. We examined a surface system consisting of non nutrient agar with a uniform bacterial lawn that extended over the agar surface, and a spatially localised central population of amoebae. Location and identification of protozoa and quantification of bacteria population are performed by the employment of image analysis techniques in a series of spatial images. The quantitative tools are based on intensity thresholding, or on probabilistic models. To accelerate organism identification, correct classification errors and attain quantitative details of all objects a custom written Graphical User Interfaces has also been developed.

Automatic detection of shoreline change on coastal Ramsar wetlands of Turkey

This research focuses on the shoreline change rate analysis by automatic image analysis techniques using multi-temporal Landsat images and Digital Shoreline Analysis System (DSAS) along the coastal Ramsar wetlands of Turkey. Five wetlands were selected for analysis: Yumurtalik Ramsar, the Goksu Ramsar, Kizilirmak and Yesilirmak wetlands and Gediz wetlands. Accretion or erosion processes were observed on multi-temporal satellite images along the areas of interest. Landsat images were geometrically and radiometrically corrected for the quantitative coastline delineation analysis. DSAS (Digital Shoreline Analysis System) was used as a reliable statistical approach for the rate of coastline change. For the detection of coastal change in Aegean part (Gediz wetland) of the study, zonal change detection method was used. As a result of the analysis, in some parts of research area remarkable shoreline changes (more than 765 m withdrawal and −20.68 m/yr erosion in Yumurtalik, 650 m withdrawal and −25.99 m/yr erosion in Goksu, 660 m withdrawal and −16.10 m/yr erosion in Kizilirmak and 640 m withdrawal and −4.91 m/yr erosion in Yesilirmak) were observed for three periods (1989, 1999 and 2009). Wetland in Gediz delta which is 35.57 km 2 was converted to sea or salt pan for the period 1975 and 2009.

DECIPHERING THE FINEST IMPRINT OF GLACIAL EROSION: OBJECTIVE ANALYSIS OF STRIAE PATTERNS ON BEDROCK

The aim of this study is to compare the efficiency of different mathematical and statistical geometrical methods applied to characterise the orientation distribution of striae on bedrock for deciphering the finest imprint of glacial erosion. The involved methods include automatic image analysis techniques of Fast Fourier Transform (FFT), and the experimental investigations by means of Saltikov's directed secants analysis (rose of intersection densities), applied to digital and analogue images of the striae pattern, respectively. In addition, the experimental data were compared with the modelling results made on the basis of Underwood's concept of linear systems in a plane. The experimental and modelling approaches in the framework of stereology yield consistent results. These results reveal that stereological methods allow a reliable and efficient delineation of different families of glacial striae from a complex record imprinted in bedrock.

The AddNeuroMed framework for multi‐centre MRI assessment of Alzheimer's disease : experience from the first 24 months

To describe the AddNeuroMed imaging framework for multi-centre magnetic resonance imaging (MRI) assessment of longitudinal changes in Alzheimer's disease and report on early results from the first 24 months of the project. A multi-centre study similarly to a faux clinical trial has been established to assess longitudinal MRI changes in Alzheimer disease (AD), mild cognitive impairment (MCI) and healthy control subjects using an image acquisition protocol compatible with Alzheimer disease neuroimaging initiative (ADNI). Comprehensive quality control (QC) measures have been established throughout the study. An intelligent web-accessible database holds details on both the raw images and data processed using a sophisticated image analysis pipeline. A total of 378 subjects have been recruited (130 AD, 131 MCI, 117 healthy controls) of which a high percentage (97.3%) of the T1-weighted volumes passed the QC criteria. Measurements of normalized whole brain volume and whole brain cortical thickness showed significant differences between AD and controls, AD and MCI and MCI and controls. A framework for multi-centre MRI studies of Alzheimer's disease has been established consisting of a harmonized MRI acquisition protocol across centres, rigorous QC at both the sites and central data analysis hub and an automated image analysis pipeline. Early results demonstrate the high quality of the images acquired and the applicability of the automated image analysis techniques employed.

Counting touching cell nuclei using fast ellipse detection to assess in vitro cell characteristics: a feasibility study

In this article, we describe a new image analysis software that allows rapid segmentation and separation of fluorescently stained cell nuclei using a fast ellipse detection algorithm. Detection time ranged between 1.84 and 3.14 s. Segmentation results were compared with manual evaluation. The achieved over-segmentation rate was 0.11 (0.1 double counts and 0.01 false positive detections), and the under-segmentation rate was of 0.03 over all images. We demonstrate the applicability of the proposed algorithm to automated counting of fluorescent-labeled cell nuclei and to tissue characterization. Moreover, the performance of the proposed algorithm is compared with preexisting automated image analysis techniques described by others.

Evaluation of the Shapes of Pores and Particles in Powder Metallurgy (PM) Materials Using Automated Image Analysis Techniques

Extended abstract of a paper presented at Microscopy and Microanalysis 2010 in Portland, Oregon, USA, August 1 – August 5, 2010.

Automated Hazard Assessment Techniques Using Satellite Images Following the 2008 Sichuan China Earthquake

ABSTRACT Rapid seismic hazard assessment is crucial for accurate damage estimation right after earthquakes. New technologies provide faster damage detection compared to the traditional, manual assessments. One of the new technologies includes using satellite images. Pre- and post-earthquake satellite images can be used to identify damage patterns. One of the recent disastrous earthquakes occurred in Sichuan (Mw = 7.9) on May 12, 2008. Records show that 5 million buildings have collapsed, and more than 21 million buildings were damaged. This article presents an approach for earthquake hazard assessment using a change detection method applied to pre- and post-earthquake satellite imagery of Sichuan. The damage inspection for the identified areas was carried out performing image analysis of the pre- and post-event satellite images. In this study, a novel automated image analysis technique was developed to assess the impact of the earthquake on the flooding of the area's rivers as well as the tectonic movement of mountains. The technique was used to quantify the flooding and movement of mountains in Sichuan right after the earthquake. The proposed methodology utilizes satellite images and may potentially be used as a rapid procedure to quantify damage soon after an earthquake.

MRI Measures of Alzheimer's Disease and the AddNeuroMed Study

Here we describe the AddNeuroMed multicenter magnetic resonance imaging (MRI) study for longitudinal assessment in Alzheimer's disease (AD). The study is similar to a faux clinical trial and has been established to assess longitudinal MRI changes in AD, mild cognitive impairment (MCI), and healthy control subjects using an image acquisition protocol compatible with the Alzheimer's Disease Neuroimaging Initiative (ADNI). The approach consists of a harmonized MRI acquisition protocol across centers, rigorous quality control, a central data analysis hub, and an automated image analysis pipeline. Comprehensive quality control measures have been established throughout the study. An intelligent web-accessible database holds details on both the raw images and data processed using a sophisticated image analysis pipeline. A total of 378 subjects were recruited (130 AD, 131 MCI, 117 healthy controls) of which a high percentage (97.3%) of the T1-weighted volumes passed the quality control criteria. Measurements of normalized whole brain volume, whole brain cortical thickness, and point-by-point group-based cortical thickness measurements, demonstrating the power of the automated image analysis techniques employed, are reported.

Quantitative Study on Nonmetallic Inclusion Particles in Steels by Automatic Image Analysis With Extreme Values Method

The presence of nonmetallic inclusion particles which appear during steelmaking process is harmful to the properties of steels, which is mainly as a function of some aspects such as size, volume fraction, shape, and distribution of these particles. The automatic image analysis technique is one of the most important tools for the quantitative determination of these parameters. The classical Student approach and the Extreme Values Method (EVM) were used for the inclusion size and shape determination and the evaluation of distance between the inclusion particles. The results thus obtained indicated that there were significant differences in the characteristics of the inclusion particles in the analyzed products. Both methods achieved results with some differences, indicating that EVM could be used as a faster and more reliable statistical methodology.

Neuroanatomical correlates of neurological soft signs in antipsychotic-naive schizophrenia

Recent imaging studies suggest that the so-called “soft” neurological signs in schizophrenia might have neuroanatomical validity. We examined gray matter volume correlates of neurological soft signs (NSS) in antipsychotic-naive schizophrenia patients using an automated image analysis technique. NSS were assessed using a modified neurological evaluation scale with good inter-rater reliability. Magnetic resonance images of 30 schizophrenia patients and 27 age-, sex-, education- and handedness-matched healthy controls were processed using optimized voxel-based morphometry (VBM). Logistic regression analysis showed that only the Motor Sequencing Signs (MSS) sub-score was a significant predictor of subject's status among the NSS sub-scores. Optimized VBM analysis showed that the MSS sub-score had a significant negative correlation with total and regional gray matter volumes (prefrontal, posterior cingulate, temporal cortices, putamen, and cerebellum) in schizophrenia patients but not in controls. Prefrontal and temporal cortices, putamen and cerebellum had significant volume deficits in patients. Cortical and cerebellar correlates of the sub-score MSS support the concept of “cognitive dysmetria” in schizophrenia.

An image analysis method to determine crystal size distributions of olivine in kimberlite

Crystal size distributions (CSDs) are a standard method of describing populations of crystals within magmatic rocks. Olivine is the dominant phase in kimberlite (∼40–50% by volume) and features a diverse range of sizes, shapes and origins. CSDs of olivine provide a logical means of semi-quantitatively characterising kimberlite. The CSDs can then be used to distinguish or correlate between kimberlite bodies or to investigate processes related to ascent, emplacement and eruption. In this paper, we present an automatic image analysis technique that provides efficient quantification of olivine CSDs within digital images of polished slabs of kimberlite. This technique relies on a combination of algorithms for detecting regions of interest (ROI) and for segmentation of ROIs in order to identify individual olivine crystals that are used for size distribution datasets. The detection process identifies regions expected to be olivine using a model-based colour detection technique using Mahalanobis distance combined with texture analysis based on local standard deviation and greyscale foreground enhancement techniques. The segmentation process separates adjacent domains to identify individual crystals using an iterative marker-based watershed algorithm to separate adjoined structures of varying sizes. We demonstrate the utility of automatic image analysis by comparing CSDs for olivine derived from this method versus results from manual digitisation of olivine grains. The automatic detection system correctly identified ∼86% of the manually detected olivine domains; ∼88% of the automatically detected regions correctly correlate to manually defined olivine grains. Discrepancies between the two methods are mostly the result of oversimplification of crystal margins (i.e. rounding) by manual tracing whereas automatic boundary recognition shows clear advantages in identifying irregularities in crystal edges. Closer examination of the results shows that both methods suffer from under-representation of smaller crystals due to: (1) human subjectivity and error in manual tracing and (2) noise removal processes in automatic detection. Automatic detection of olivine grains is much more efficient than conventional manual tracing; manual detection requires ∼6 h per sample versus ∼1 min for automatic analysis of the same sample.

Tensor-based morphometry as a neuroimaging biomarker for Alzheimer's disease: An MRI study of 676 AD, MCI, and normal subjects

In one of the largest brain MRI studies to date, we used tensor-based morphometry (TBM) to create 3D maps of structural atrophy in 676 subjects with Alzheimer's disease (AD), mild cognitive impairment (MCI), and healthy elderly controls, scanned as part of the Alzheimer's Disease Neuroimaging Initiative (ADNI). Using inverse-consistent 3D non-linear elastic image registration, we warped 676 individual brain MRI volumes to a population mean geometric template. Jacobian determinant maps were created, revealing the 3D profile of local volumetric expansion and compression. We compared the anatomical distribution of atrophy in 165 AD patients (age: 75.6±7.6 years), 330 MCI subjects (74.8±7.5), and 181 controls (75.9±5.1). Brain atrophy in selected regions-of-interest was correlated with clinical measurements – the sum-of-boxes clinical dementia rating (CDR-SB), mini-mental state examination (MMSE), and the logical memory test scores – at voxel level followed by correction for multiple comparisons. Baseline temporal lobe atrophy correlated with current cognitive performance, future cognitive decline, and conversion from MCI to AD over the following year; it predicted future decline even in healthy subjects. Over half of the AD and MCI subjects carried the ApoE4 (apolipoprotein E4) gene, which increases risk for AD; they showed greater hippocampal and temporal lobe deficits than non-carriers. ApoE2 gene carriers – 1/6 of the normal group – showed reduced ventricular expansion, suggesting a protective effect. As an automated image analysis technique, TBM reveals 3D correlations between neuroimaging markers, genes, and future clinical changes, and is highly efficient for large-scale MRI studies.

Correlates and Determinants of Nuclear Epidermal Growth Factor Receptor Content in an Oropharyngeal Cancer Tissue Microarray

We have previously reported nuclear localization of epidermal growth factor receptor (EGFR) protein in oropharyngeal cancer tissue. Nuclear EGFR levels were inversely correlated with survival and response to radiotherapy. Here, we sought to identify the determinants and correlates of nuclear EGFR content. We analyzed an oropharyngeal cancer tissue microarray for the expression of the key molecules of the EGFR signaling cascade using an automated image analysis technique (AQUA) scored on a scale of 0 to 255, which permits protein quantitation and subcellular localization. Patients with oropharyngeal squamous cell cancer treated with radiotherapy or surgery and radiotherapy were eligible. Data were analyzed using Spearman correlations and multiple linear regression with robust SEs. Of the 95 tumors included in this study, 72 (75%) had sufficient tissue for analysis of nuclear EGFR. Nuclear EGFR levels were associated with membranous/cytoplasmic EGFR levels (rho = 0.82, P < 0.001), nuclear extracellular signal-regulated kinase-2 (rho = 0.30, P = 0.01), and nuclear proliferating cell nuclear antigen (PCNA; rho = 0.36, P = 0.003). Nuclear phosphorylated-Akt, cyclin D1, phosphatase and tensin homolog (mutated in multiple cancers 1) (PTEN), p53, and proliferation marker Ki-67 levels did not correlate with nuclear EGFR level. In multivariable analysis, only PCNA retained its significant association (P = 0.01). These results are consistent with preclinical data showing that EGFR may function as a tyrosine kinase in the nucleus, phosphorylating and stabilizing PCNA. The nuclear activity of EGFR may constitute a novel therapeutic target.