Minimum User Input Research Articles

Automatic variogram calculation and modeling

The variogram is one of the most used tools in geostatistics. It represents a key step for the results of estimation and simulation. This paper presents a methodology of the experimental variogram points calculation and subsequent modeling, including some practical considerations. The proposed methodology infers the variogram parameters directly from the dataset to require minimum user input. Autovar is a program that implements the described methodology, giving an initial variogram model for disseminated and tabular deposits.

Optimization algorithm for minimizing railway energy consumption in hybrid powertrain architectures: A direct method approach using a novel two-dimensional efficiency map approximation

SEnSOR (Smart Energy Speed Optimizer Rail) is a direct method based optimization algorithm developed at DLR for determining minimum energy speed trajectories for railway vehicles. This paper aims to reduce model error and improve this algorithm for any alternative powertrain architecture. Model simplifications such as projecting the efficiency maps of different train components onto one-dimensional space can lead to inaccuracies and non-optimalities in reality. In this work, 2D section-wise Chua functional representation was used to capture the complete behavior of efficiency maps and discuss its benefits. For this purpose, a new smoothing method was developed. It was observed that there is an average of 6% error in the energy calculation when both, 1D and 2D, models are compared against each other. Previously, solving for different powertrain architectures was time consuming with the requirement of manual modifications to the optimization problem. With a modular approach, the algorithm was modified to flexibly adapt the problem formulation to automatically take into account any changes in powertrain architectures with minimum user input. The benefit is demonstrated by performing optimization on a bi-mode train with three different power sources as developed within the EU-project FCH2RAIL. The advanced algorithm is now capable to adapt to such complex architectures and provide feasible optimization results within a reasonable time.

Comprehensive tool for a phase compensation reconstruction method in digital holographic microscopy operating in non-telecentric regime.

Quantitative phase imaging (QPI) via Digital Holographic microscopy (DHM) has been widely applied in material and biological applications. The performance of DHM technologies relies heavily on computational reconstruction methods to provide accurate phase measurements. Among the optical configuration of the imaging system in DHM, imaging systems operating in a non-telecentric regime are the most common ones. Nonetheless, the spherical wavefront introduced by the non-telecentric DHM system must be compensated to provide undistorted phase measurements. The proposed reconstruction approach is based on previous work from Kemper's group. Here, we have reformulated the problem, reducing the number of required parameters needed for reconstructing phase images to the sensor pixel size and source wavelength. The developed computational algorithm can be divided into six main steps. In the first step, the selection of the +1-diffraction order in the hologram spectrum. The interference angle is obtained from the selected +1 order. Secondly, the curvature of the spherical wavefront distorting the sample's phase map is estimated by analyzing the size of the selected +1 order in the hologram's spectrum. The third and fourth steps are the spatial filtering of the +1 order and the compensation of the interference angle. The next step involves the estimation of the center of the spherical wavefront. An optional final optimization step has been included to fine-tune the estimated parameters and provide fully compensated phase images. Because the proper implementation of a framework is critical to achieve successful results, we have explicitly described the steps, including functions and toolboxes, required for reconstructing phase images without distortions. As a result, we have provided open-access codes and a user interface tool with minimum user input to reconstruct holograms recorded in a non-telecentric DHM system.

Reinforcing optimization enabled interactive approach for liver tumor extraction in computed tomography images

<p>Detecting liver abnormalities is a difficult task in radiation planning and treatment. The modern development integrates medical imaging into computer techniques. This advancement has monumental effect on how medical images are interpreted and analyzed. In many circumstances, manual segmentation of liver from computerized tomography (CT) imaging is imperative, and cannot provide satisfactory results. However, there are some difficulties in segmenting the liver due to its uneven shape, fuzzy boundary and complicated structure. This leads to necessity of enabling optimization in interactive segmentation approach. The main objective of reinforcing optimization is to search the optimal threshold and reduce the chance of falling into local optimum with survival of the fittest (SOF) technique. The proposed methodology makes use of pre-processing stage and reinforcing meta heuristics optimization based fuzzy c-means (FCM) for obtaining detailed information about the image. This information gives the optimal threshold value that is used for segmenting the region of interest with minimum user input. Suspicious areas are recognized from the segmented output. Both public and simulated dataset have been taken for experimental purposes. To validate the effectiveness of the proposed strategy, performance criteria such as dice coefficient, mode and user interaction level are taken and compared with state-of-the-art algorithms.</p>

Design of a specialized search engine for university students dedicated to education and environment

The aim of this study is to introduce a new specialized search engine that helps university students learn about environmental issues and improve their environmental literacy. Our search engine collects information from environmental documents and scientific articles from trusted sources. After intensive word processing, it provides a list of different contexts for the terms queried, depending on the chosen field, allowing students to refine their online search. In a single operation, students can find phrases and paragraphs using multiple related terms. This model aims to generate maximum output with semantic value using minimum user input, thanks to the new search mechanism on which it is based. The search engine is optimized for environmental education, allowing students to access environmental information in their preferred language. Our work is structured as follows: first, we motivate the need for a specialized environmental education search engine. Then, we discuss the context and construction of our specialized search engine for environmental education. Finally, we review the proposed solution and conclude with future work.

GMAC: A Geant4-based Monte Carlo Automated computational platform for developing nuclear tool digital twins

Nuclear technology is widely used for hydrocarbon exploration by deploying nuclear tools of detection to help obtain important parameters of a given geographical formation. Monte Carlo software is generally used to simulate nuclear tools in the environment of well logging, to accurately predict their responses downhole. In other words, a digital Monte Carlo twin of the designated tool is constructed, and its responses, are used to identify features that are important, for instance, for assessing the feasibility of deployment of the tool or optimizing the design of its hardware. However, the downhole environment is complex and changeable, such that it is determined by many parameters, e.g., the formation, the fluid, and the structure of the well. A significant modeling setup is thus often required to be able to consider all environmental variations, where this increases the burden on field engineers who need to construct several batches of repetitive models to simulate the same tool in a variety of environments. The appropriate automation of this process is thus highly desirable. In this work, the authors propose downhole Geant4-based Monte Carlo Automated Computational Platform (GMAC) to develop digital twins of nuclear tools. We construct a platform that enables us to design a Monte Carlo digital twin of a given nuclear tool. GMAC can automate the process of simulating the tool under various environments based on minimum user input and provide a comprehensive evaluation of its performance. The proposed platform also provides feasible means to optimize the tool by connecting the CAE twin directly to the Monte Carlo twin. The main structure and developer/user functions of the GMAC are discussed in detail. Three examples of nuclear tools are also provided to detail and verify its complete process from tool design to application. The results confirm the correctness and efficiency of the proposed computational platform.

TransPi-a comprehensive TRanscriptome ANalysiS PIpeline for de novo transcriptome assembly.

The use of RNA sequencing (RNA-Seq) data and the generation of de novo transcriptome assemblies have been pivotal for studies in ecology and evolution. This is especially true for nonmodel organisms, where no genome information is available. In such organisms, studies of differential gene expression, DNA enrichment bait design and phylogenetics can all be accomplished with de novo transcriptome assemblies. Multiple tools are available for transcriptome assembly, but no single tool can provide the best assembly for all data sets. Therefore, a multi-assembler approach, followed by a reduction step, is often sought to generate an improved representation of the assembly. To reduce errors in these complex analyses while at the same time attaining reproducibility and scalability, automated workflows have been essential in the analysis of RNA-Seq data. However, most of these tools are designed for species where genome data are used as reference for the assembly process, limiting their use in nonmodel organisms. We present TransPi, a comprehensive pipeline for de novo transcriptome assembly, with minimum user input but without losing the ability of a thorough analysis. A combination of different model organisms, k-mer sets, read lengths and read quantities was used for assessing the tool. Furthermore, a total of 49 nonmodel organisms, spanning different phyla, were also analysed. Compared to approaches using single assemblers only, TransPi produces higher BUSCO completeness percentages, and a concurrent significant reduction in duplication rates. TransPi is easy to configure and can be deployed seamlessly using Conda, Docker and Singularity.

TB2J: A python package for computing magnetic interaction parameters

We present TB2J, a Python package for the automatic computation of magnetic interactions, including exchange and Dzyaloshinskii–Moriya, between atoms of magnetic crystals from the results of density functional calculations. The program is based on the Green’s function method with the local rigid spin rotation treated as a perturbation. As input, the package uses the output of either Wannier90, which is interfaced with many density functional theory packages, or of codes based on localized orbitals. One of the main interests of the code is that it requires only one first-principles electronic structure calculation in the non-relativistic case (or three in the relativistic case) and from the primitive cell only to obtain the magnetic interactions up to long distances, instead of first-principles calculations of many different magnetic configurations and large supercells. The output of TB2J can be used directly for the adiabatic magnon band structure and spin dynamics calculations. A minimal user input is needed, which allows for easy integration into high-throughput workflows. Program summaryProgram Title: TB2JCPC Library link to program files:https://doi.org/10.17632/dm45fcn69d.1Developer’s repository link:https://github.com/mailhexu/TB2JCode Ocean capsule:https://codeocean.com/capsule/6486145Licensing provisions: BSD 2-clauseProgramming language: PythonNature of problem: TB2J is a package for the computing of parameters in the extended Heisenberg model of the magnetic interaction, including the isotropic exchange, anisotropic exchange and Dzyaloshinskii–Moriya interactions from first principles result. It can make use of the Wannier function Hamiltonian, which can be constructed from many first principles codes, or localized orbital based codes.Solution method: It uses the magnetic force theorem and takes the rigid spin rotation as a perturbation to the electronic structure. The energy variation is calculated from the Green’s functions from tight-binding like Hamiltonian based on Wannier functions or localized orbitals.Additional comments including restrictions and unusual features: Isotropic exchange, anisotropic exchange, and Dzyaloshinskii–Moriya interactions can all be computed with the input of many DFT codes through the interface of Wannier90, or directly from localized orbital codes. The magnetic interaction parameters up to any distance can be computed from one DFT calculation. A minimum user-input is required which provides a black-box like experience. It generates output for several spin dynamics codes and thus bridges the first principles electronic structure simulation with the large scale spin dynamics simulation.

Smartphone-based lateral flow imaging system for detection of food-borne bacteria E.coli O157:H7

We report an application for the smartphone as an accurate and unbiased reading platform of a lateral flow immunoassays for food safety application. In particular, this report focuses on detection of food-borne bacteria in samples extracted from food matrices such as ground beef and spinach. The lateral flow assay is a widely accepted methodology owing to its on-site results, low-cost analysis, and ease of use with minimum user inputs, even though sensitivity is not quite equivalent to that of standard laboratory equipment. An antibody-antigen relationship is transduced into a color change on a nitrocellulose pad while visual interpretation of this color change can result in uncertainty, particularly near the detection limit of the assay. Employing the high resolution integrated camera, constant illumination from light source, and computing power of a smartphone, we provide an objective and accurate method to determine the bacterial cell concentration in a food matrix based on the regression model from the color intensity of test lines. A 3D-printed sample holder was designed for representative commercial lateral flow assays and an in-house application was developed in Android Studio to solve the inverse problem to provide cell concentration information from the color intensity. Test results with E.coli O157:H7 as a model organism suggests that smartphone-based reader can detect 104-105 CFU/ml from ground beef and spinach food matrices.

Pressure–velocity coupling algorithm-based pressure reconstruction from PIV for laminar flows

In this study, we propose a method to reconstruct pressure fields from planar particle image velocimetry measurements for laminar flows by employing semi-implicit method for pressure-linked equations algorithm to solve governing equations where measured velocities are inherently used as boundary conditions. The method starts with interpolating the measured velocity field on a staggered computational grid. The continuity equation, in the form of pressure equation for incompressible flows, is solved with this velocity data to reach an initial pressure field. Momentum equations are solved with calculated pressure field and then pressure correction equation is solved for calculating the mass imbalance in continuity equation. Using this mass imbalance, the current velocity field is corrected. Repeating this procedure until convergence provides not only the pressure field that satisfies governing equations, but also error reduction on the measured velocity. The method is validated with theoretical flows and its sensitivity to the velocity field error is assessed. This method reconstructs the pressure fields exactly for error-free velocity fields and can correct the flow-fields to accurate values even with extremely high experimental errors. Application on a flapping airfoil experiment showed that the method can successfully reconstruct pressure field by slightly altering the measured velocity field. The proposed method offers a non-intrusive, global pressure measurement for laminar flows with minimum end user input.

Business process centric energy modelling

PurposeSustainability is an accepted measure of business performance, with reductions in energy demand a commonly practised sustainability initiative by multinational corporations (MNCs). Traditional energy models have limited scope when applied to the entire MNC as the models exhibit high data and time intensity, high technical proficiency, specificity of application and omission of non-manufacturing activities. The purpose of this paper is to propose a process centric energy model (PCEM), which adopts a novel approach of applying business processes for business energy assessment and optimisation. Business processes are a fundamental requirement of MNCs across all sectors. The defining features of the proposed model are genericity, reproducibility, minimum user input data, reduced modelling time and energy evaluation of non-manufacturing activities. The approach forwards the adoption of Industry 4.0, a subset of which focuses on business process automation or part thereof.Design/methodology/approachA quantitative approach is applied in development of the PCEM. The methodology is demonstrated by application to the procure to pay and electroplating business processes.FindingsThe PCEM quantifies and optimises the business energy demand and associated carbon dioxide emissions of the procure to pay and electroplating business processes, validating the application of business processes. The application demonstrates minimum user inputs as only equipment operational parameters are required and minimum modelling time as business process models and optimisation options are pre-defined requiring only user modification. As MNCs have common business processes across multiple sites, once a business process energy demand is quantified, its inputs are applied as the default in the proceeding sites, only requiring updating. The model has no specialist skills requirement enabling business wide use and eliminating costs associated with training and expert’s services. The business processes applied in the evaluation are developed by the researchers and are not as comprehensive as those in actual MNCs, but is sufficiently detailed to accurately calculate an MNC energy demand. The model databases are not exhaustive of all resources found in MNCs.Originality/valueThis paper provides a new approach to MNC business energy assessment and optimisation. The model can be applied to MNEs across all sectors. The model allows the integration of manufacturing and non-manufacturing activities, as it occurs in practice, providing holistic business energy assessment and optimisation. The model analyses the impacts of the adoption of Industry 4.0 technologies on business energy demand, CO2 emission and personnel hours.

Non-negative Factor (NNF) Assisted Partial Least Square (PLS) Analysis of Excitation-Emission Matrix Fluorescence Spectroscopic Data Sets: Automating the Identification and Quantification of Multifluorophoric Mixtures.

Excitation-emission matrix fluorescence spectroscopy is simple and sensitive techniques that generate the composite fluorescence fingerprints. EEMF can be used for the identification and quantification of the fluorophores without involving any pre-separation step provided a suitable data analysis approach is applied. In the present work, non-negative factor (NNF) assisted partial least square (PLS) analysis is used for the analysis of EEMF data sets acquired for the dilute aqueous mixtures of fluorophores. The proposed approach allows automatic selection of the optimum number of factors for NNF analysis by incorporating the Akaike information criterion. The proposed approach also incorporates the spectral correlation analysis for the automatic identification of the NNF retrieved EEMF spectral profiles. The NNF retrieved contribution values along with their real concentration values are subjected to PLS analysis to develop a calibration model. The proposed approach was successfully tested using EEMF data acquired for the dilute aqueous mixtures of Catechol, Hydroquinone, Indole, Tryptophan and Tyrosine. The results were evaluated using the various statistical parameters and each of them found to well within the expected limits. In summary, NNF assisted PLS analysis of EEMF technique allows automatized analysis of the multifluorophoric mixtures with minimum user inputs.

Advanced Economic Control of Electricity-Based Space Heating Systems in Domestic Coalitions with Shared Intermittent Energy Resources

Over the past few years, Domestic Heating Automation Systems (DHASs) that optimize the domestic space heating control process with minimum user input, utilizing appropriate occupancy prediction technology, have emerged as commercial products (e.g., the smart thermostats from Nest and Honeywell). At the same time, many houses are being equipped with, potentially grid-connected, Intermittent Energy Resources (IERs), such as rooftop photovoltaic systems and/or small wind turbine generators. Now, in many regions of the world, such houses can sell energy to the grid but at a lower price than the price of buying it. In this context, and given the anticipated increase in electrification of heating, the next generation DHASs need to incorporate Advanced Economic Control (AEC). Such AEC can exploit the energy buffer that heating loads provide, in order to shift the consumption of electricity-based heating systems to follow the intermittent energy generation of the house. By so doing, the energy imported from the grid can be minimized and considerable monetary gains for the household can be achieved, without affecting the occupants’ schedule. These benefits can be amplified still further in domestic coalitions, where a number of houses come together and share their IER generation to minimize their cumulative grid energy import. Given the above, in this work we extend a state-of-the-art DHAS, to propose AdaHeat+, a practical DHAS, that, for the first time, incorporates AEC. Our work is applicable to both individual houses and domestic coalitions and comes complete with an allocation mechanism to share the coalition gains. Importantly, we propose an effective heuristic heating schedule planning approach for collective AEC that (i) has a complexity that scales in a linear and parallelizable manner with the coalition size, and (ii) enables AdaHeat+ to handle the distinct preferences, in balancing heating cost and thermal discomfort, of the households. Our approach relies on stochastic IER power output predictions. In this context, we propose a simple and effective formulation for the site-specific calibration of such predictions based on adaptive Gaussian process modeling. Finally, we demonstrate the effectiveness of AdaHeat+ through real data evaluation, to show that collective AEC can improve heating cost-efficiency by up to 60%, compared to independent AEC (and even more when compared to no-AEC).

RBioplot: an easy-to-use R pipeline for automated statistical analysis and data visualization in molecular biology and biochemistry.

BackgroundStatistical analysis and data visualization are two crucial aspects in molecular biology and biology. For analyses that compare one dependent variable between standard (e.g., control) and one or multiple independent variables, a comprehensive yet highly streamlined solution is valuable. The computer programming language R is a popular platform for researchers to develop tools that are tailored specifically for their research needs. Here we present an R package RBioplot that takes raw input data for automated statistical analysis and plotting, highly compatible with various molecular biology and biochemistry lab techniques, such as, but not limited to, western blotting, PCR, and enzyme activity assays.MethodThe package is built based on workflows operating on a simple raw data layout, with minimum user input or data manipulation required. The package is distributed through GitHub, which can be easily installed through one single-line R command. A detailed installation guide is available at http://kenstoreylab.com/?page_id=2448. Users can also download demo datasets from the same website.Results and DiscussionBy integrating selected functions from existing statistical and data visualization packages with extensive customization, RBioplot features both statistical analysis and data visualization functionalities. Key properties of RBioplot include: -Fully automated and comprehensive statistical analysis, including normality test, equal variance test, Student’s t-test and ANOVA (with post-hoc tests);-Fully automated histogram, heatmap and joint-point curve plotting modules;-Detailed output files for statistical analysis, data manipulation and high quality graphs;-Axis range finding and user customizable tick settings;-High user-customizability.

Mössbauer spectral curve fitting combining fundamentally different techniques

We propose the use of fundamentally distinctive techniques to solve the problem of curve fitting a Mössbauer spectrum. The techniques we investigated are: evolutionary algorithm, basin hopping, and hill climbing. These techniques were applied in isolation and combined to fit different shapes of Mössbauer spectra. The results indicate that complex Mössbauer spectra can be automatically curve fitted using minimum user input, and combination of these techniques achieved the best performance (lowest statistical error). The software and sample of Mössbauer spectra have been made available through a link at the reference.

Interactive Image Segmentation using Color and Texture Features

Image segmentation is the process of selecting objects of interest in background images. Since the fully automatic segmentation is difficult for natural images due to the complex color and texture features. This paper presents the idea of image segmentation using maximum similarity based region merging with minimum user inputs using simple brush strokes called markers(object and background markers).Therefore, the proposed system presents a new region merging method that grow regions from foreground/background seeds based on the color and texture features for interactive image segmentation. An initial segmentation is required to partition the image into homogeneous regions for merging. After the completion of the initial segmentation, initial segmented regions are represented by means of some descriptors such as color and texture to guide the region merging process. Therefore, the proposed method is very effective and it can quickly and accurately segment a wide variety of natural images with ease.

문제-지향적 교육용 격자 생성 프로그램의 개발

A grid generation program for specific problems is introduced. The program allows users to easily generate grid system for specific geometry such as an airfoil, cylinder, wedge, flat plate, and nozzle. Generating grid system for those problems can be proceeded with minimum user inputs such as geometry-defining parameters and grid-defining parameters. By using this program learning stage for preprocessing of CFD application can be efficiently shorten and novice students can learn and acquire experience by trying out grid generation and CFD solution by themselves.

Regional Assessment of Cardiac Left Ventricular Myocardial Function via MRI Statistical Features

Automating the detection and localization of segmental (regional) left ventricle (LV) abnormalities in magnetic resonance imaging (MRI) has recently sparked an impressive research effort, with promising performances and a breadth of techniques. However, despite such an effort, the problem is still acknowledged to be challenging, with much room for improvements in regard to accuracy. Furthermore, most of the existing techniques are labor intensive, requiring delineations of the endo- and/or epi-cardial boundaries in all frames of a cardiac sequence. The purpose of this study is to investigate a real-time machine-learning approach which uses some image features that can be easily computed, but that nevertheless correlate well with the segmental cardiac function. Starting from a minimum user input in only one frame in a subject dataset, we build for all the regional segments and all subsequent frames a set of statistical MRI features based on a measure of similarity between distributions. We demonstrate that, over a cardiac cycle, the statistical features are related to the proportion of blood within each segment. Therefore, they can characterize segmental contraction without the need for delineating the LV boundaries in all the frames. We first seek the optimal direction along which the proposed image features are most descriptive via a linear discriminant analysis. Then, using the results as inputs to a linear support vector machine classifier, we obtain an abnormality assessment of each of the standard cardiac segments in real-time. We report a comprehensive experimental evaluation of the proposed algorithm over 928 cardiac segments obtained from 58 subjects. Compared against ground-truth evaluations by experienced radiologists, the proposed algorithm performed competitively, with an overall classification accuracy of 86.09% and a kappa measure of 0.73.

Design and optimization of energy efficient complex separation networks

Separation processes account for more than half of capital and operating costs in chemical manufacturing. Separations are the energy intensive operations in the chemical industry. Rising energy consumption combined with the environmental impact increases the need for energy saving separation processes. Fortunately complex column networks have the potential for major energy savings estimated to range between 30 and 70% over simple column configuration. In this paper, a computer-aided synthesis method is introduced to synthesize optimal complex column arrangements which encode the cost and states of global solutions with minimum user input. A robust feasibility criterion helps select design and operating conditions for the entire network that can be realized in practice. Our method builds on thermodynamic transformations entitled temperature collocation which provides crucial advantages to determine the operating conditions, structure, and size of the separation network for achieving the desired product cuts. The computational approach guarantees realizable column profiles, which can be validated with industrially accepted simulation software such as AspenHysys and AspenPlus.

다중 단계 신호의 적응적 전파를 통한 동일 장면 영상의 이원 영역화

최근까지 단일 영상이나 동영상을 영역화하는 기법들은 다양하게 제시되어 왔으나, 유사한 장면에 대한 여러 장의 영상을 동시에 영역화하는 기법은 많지 않았다. 본 논문에서는 한 장소에서 연속적으로 촬영하였거나 전경 물체가 유사한 여러 영상들을 동일 장면 영상으로 정의하고, 이런 동일 장면 영상들을 적은 양의 사용자 입력을 통해 효과적으로 영역화하는 기법을 제안한다. 구체적으로, 사용자가 최초의 영상 한 장을 직접 영역화한 후, 그 영상의 영역화 결과와 영상의 특성을 토대로 다중 단계 신호를 적응적 가중치를 주어서 인접 영상으로 전파하고, 이를 통해 제안하는 기법은 인접 영상을 반복적으로 영역화한다. 영역화는 마르코프 랜덤 장에서의 에너지 최소화를 통해 이루어지는데, 전파되는 신호는 각 픽셀에 대한 에너지를 정의하는 바탕이 되며, 픽셀, 픽셀 패치, 그리고 영상 전체로부터 비롯되었는가에 따라 낮은 단계, 중간 단계, 그리고 높은 단계의 신호로 지칭된다. 또한 에너지 최소화 틀 안에서 전파된 신호를 통해 정의되는 에너지 역시 낮은 단계, 중간 단계, 그리고 높은 단계의 세 단계로 정의한다. 이런 과정을 통해 전파된 신호를 최대한 다양하게 활용하고, 이를 통해 다양한 영상에 영역화 결과가 일관되게 유지된다. 다양한 동일 장면 영상들에 제안하는 기법을 적용하여 성능을 평가하고, 픽셀 패치를 바탕으로 하는 중간 단계 신호만을 이용한 결과와 제안하는 다중 신호를 적용하는 기법의 결과를 비교한다. So far, many methods for segmenting single images or video have been proposed, but few methods have dealt with multiple images with analogous content. These images, which we term consistent scene images, include concurrent images of a scene and gathered images of a similar foreground, and may be collectively utilized to describe a scene or as input images for multi-view stereo. In this paper, we present a method to segment these images with minimum user input, specifically, manual segmentation of one image, by iteratively propagating information via multi-level cues with adaptive confidence depending on the nature of the images. Propagated cues are used as the bases to compute multi-level potentials in an MRF framework, and segmentation is done by energy minimization. Both cues and potentials are classified as low-, mid-, and high- levels based on whether they pertain to pixels, patches, and shapes. A major aspect of our approach is utilizing mid-level cues to compute low- and mid- level potentials, and high-level cues to compute low-, mid-, and high- level potentials, thereby making use of inherent information. Through this process, the proposed method attempts to maximize the amount of both extracted and utilized information in order to maximize the consistency of the segmentation. We demonstrate the effectiveness of the proposed method on several sets of consistent scene images and provide a comparison with results based only on mid-level cues [1].