Continuous Contours Research Articles

Computer-aided recognition and assessment of a porous bioelastomer in ultrasound images for regenerative medicine applications

It is difficult to use a single edge operator in image processing to extract continuous and accurate contours of a porous bioelastomer due to the fuzzy boundary and complex background in ultrasound images. To solve this problem, this paper proposes a joint algorithm for bioelastomer contour detection and a texture feature extraction method for monitoring the degradation performance of bioelastomers. First, the mean-shift clustering method is utilized to obtain the clustering feature information of bioelastomers and native tissue from manually segmented images, and this information is used as the initial information in the image binarization algorithm for image partitioning. Second, Otsu's thresholding method and mathematical morphology are applied in the process of image binarization. Finally, the Canny edge detector is employed to extract the complete bioelastomers contour from the binary image. To verify the robustness of the proposed joint algorithm, the results using the proposed joint algorithm, where mean-shift clustering is replaced with k-means clustering are also obtained. The proposed joint algorithm based on mean-shift clustering outperforms the joint algorithm based on k-means clustering, as well as algorithms that directly apply the Canny, Sobel and Laplacian methods. Texture feature extraction is based on the computer-aided recognition of bioelastomers. The region of interest (ROI) is set in the scaffold region, and the first-order statistical features and second-order statistical features of the greyscale values of the ROI are extracted and analysed. The proposed joint algorithm can not only extract ideal bioelastomers contours from ultrasound images but also provide valuable feedback on the degradation behaviour of bioelastomers at implant sites.

Saliency-Based SAR Target Detection via Convolutional Sparse Feature Enhancement and Bayesian Inference

Traditional synthetic aperture radar (SAR) target detection methods use matched filtered SAR images as input, and the detection performance is restricted due to the high sidelobes and speckle noise of these images. Sparse SAR imaging methods developed in recent years provide the advantages of reducing sidelobes, noise, and clutter. The imaging results obtained with these methods could help improve the SAR target detection performance. In this article, to improve the target detection performance using sparse SAR images as input, we proposed a convolutional sparse feature enhancement method to meet the needs of Bayesian saliency detection. The proposed Bayesian saliency joint target detection method comprised the following three steps: first, to obtain sparse SAR images with continuous contours and fewer holes in the target area, we proposed a convolutional L1 sparse regularization method. Second, a regularization parameter optimization method was derived to quickly obtain optimal regularization parameters for saliency detection. Finally, target detection results were obtained through a superpixel-based Bayesian saliency joint detector. Extensive experiments verified that the proposed method could improve the SAR target detection accuracy in complex backgrounds.

Bilinear and Bicubic Interpolations for Image Presentation of Mechanical Stress and Temperature Distribution

Bilinear and bicubic interpolations were often used in digital elevation models (DEMs), image scaling, and image restoration, with the aid of spatial transform techniques. This paper resorts to bilinear and bicubic interpolations, along with the spatial transform of images, to present the temperature distribution on a plate with a circular hole. The Dirichlet boundary conditions were applied, a rectangular grid was created, and the nodal values were calculated using the finite difference method (FDM). These methods were also employed to represent the mechanical stress distribution on a plate with a circular hole, under the presence of uniaxial stress. In this case, the nodal values were calculated using the analytical method. Experimental results show that bicubic interpolation generated continuous contours, while bilinear interpolation had a discontinuity in some cases. The results were comparative to images for similar cases when solved through ANSYS.

Method for continuous multiscale representation of terrain contours using T‐spline technique

AbstractContours are the main graphical element for characterizing three‐dimensional terrain on a topographic map. Continuous multiscale representation of contours is crucial to meet users' needs for detailed information between fixed‐scale contours. Wherein shape of the contour should ideally progressively change as the scale continuously changes. However, the lack of a bridge between scale and shape deformation degrees is an obstacle in obtaining continuous multiscale contours. A novel method for continuous multiscale representation of contour based on T‐spline (CMRTS) is proposed. Multiscale contours are generated through interpolation of the T‐spline and constraint of the relationship between scale and shape similarity. First, a T‐spline surface is established using two fixed‐scale contours. Second, the T‐spline surface intersects a set of horizontal planes with gradual heights to generate intersecting lines. Finally, the quantitative relationship between the scale and shape similarity is determined to align each intersecting line with the corresponding scale and achieve continuous multiscale contours. A case study in Chongqing, China implements and evaluates the proposed method. Results indicate that shape changes of contours generated by CMRTS are more natural and progressive than those by two typical methods. Our method shows high potential and practicability for mapping continuous multiscale contours for real‐world terrain applications.

Gendering Post-1945 German History: Entanglements ed. by Karen Hagemann, Donna Harsch, and Friederike Brühöfener

Reviewed by: Gendering Post-1945 German History: Entanglements ed. by Karen Hagemann, Donna Harsch, and Friederike Brühöfener Tiarra Cooper Karen Hagemann, Donna Harsch, and Friederike Brühöfener, editors. Gendering Post-1945 German History: Entanglements. Berghahn Books, 2019. 408 pp. Paper, $145.00. Drawn from sixteen papers delivered at the 2015 German Studies Association conference, this five-part volume draws on Christoph Kleßmann's term entanglement in investigating the porous, divisive, and at times continuous national contours between West (FRG) and East (GDR) Germany. Composed of novel works by women and gender scholars, this collection contributes to growing scholarship that re-narrativizes German-German history as one that is both parallel and asymmetrically entangled. Looking to politics, culture, social movements, resistance, sexuality, and the media, this work probes these sites as shaped by gender. This volume's contributions bring to the surface the multifaceted ways in which East and West German family ideals—and, inherently, gender roles—were ubiquitous and influential; not only did they shape domestic policies, but they often constituted a marker of progress. [End Page 116] Whereas the socialist GDR touted the merits of a dual-earner family, its neighbor to the west sought a return to prewar values in promoting the male-breadwinner/female-homemaker model. These values are reflected in Jennifer Lynn's chapter, "Entangled Femininities: Contested Representations of Women in the East and West German Illustrated Press of the 1950s," which explores how West German magazines portrayed homemakers as universal, modern women. These depictions contrast with those in East German magazines, in which the female figure, imbued with ideological values, represented the progressive, superior counterpart to that in the West. These competing ideals are echoed in Leonie Treber's chapter, "The Big Cleanup: Men, Women, and Rubble Clearance in Postwar East and West Germany," in which she demonstrates that—in contrast to the widely circulated myth of the "rubble woman" of West Germany—it was in fact predominantly East German women who contributed to clearing rubble; officials in the West instead pursued stabilization of the family unit by returning to the male-breadwinner/female-homemaker model. Conversely, chapters in this collection highlight a unity between East and West German women in that—despite rhetoric—they all grappled with patriarchal gender norms in their everyday lives. The available avenues in which women were permitted to seek redress and political agency, however, emerged much differently on each side of the Iron Curtain. In "Domestic Abuse and Women's Lives: East and West Policies during the 1960s and 1970s," Jane Freeland explores how women, when confronted with violent home lives, sought rectification within the confines of their respective states. In the FRG, women located this violence as rooted in patriarchal inequality more generally and thematized domestic abuse in the women's movement, culminating in grassroots services and shelters. GDR officials, however, denounced domestic abuse as a capitalist relic antithetical to socialism. Though judges and courts—in addition to workplace collectives and marital-counseling services—condemned violence in the home, the disharmonious marriage became a question of the husband's commitment to socialism—not his propensity for violence. The instrumental power of state ideology in shaping women's rights to equality and citizenship reemerges in Alexandria Ruble's "Children, Church, and Rights: East and West German Protests against Family Law Reforms in the 1950s." Having inherited a 1900 Civil Code that relegated women to second-class citizens in matters of marriage, property, and parenting, both the FRG and GDR sought to reconcile state ideals with church advocacy [End Page 117] and demands for reform. East Germany, though having sought immediate reform to fulfill ideological promises of equality, eschewed public conflict and retired reform for ten years. In contrast, reform-minded FRG officials pushed reform through the delegation of a subcommittee in the interest of liberalization. This volume achieves a tremendous feat in its breadth, though its forte lies in its diverse contexts, uses, and understandings of gender—including its co-constituency with race and sexuality. Though extensive, its impressive scope can at times fall short due to gaps in scholarship—a shortcoming that the editors are transparent in conveying. While the absence of research on...

A Global Continuous Multi-Scale Terrain Contour Simplification Method Based on the Level Set

Multi-scale spatial representation has been widely used in geographic information and online mapping systems. Terrain contour, which provides a reference for understanding and monitoring the Earth’s surface, is an important data category. For the multi-scale representation of contour lines, simplification is a fundamental step in providing different levels of detail for linear features. However, achieving a global continuous multi-scale simplification of contours remains a challenge. Therefore, based on the concept of level set, a novel contour simplification method labeled the continuous changing surface model (CCSM) was proposed in this paper. The CCSM was built by using a non-uniform rational B-spline constrained with characteristics and was then intersected with a set of horizontal planes with progressive height values. The generated intersection lines are considered continuous multi-scale simplified contours. Experiments were conducted on a 1:50,000 real contour dataset to verify the effectiveness of CCSM. Results showed that the changes in the shape of the simplified contours generated by CCSM are more natural and progressive than those generated by two other significant simplification methods. CCSM can also effectively balance local and global structures and has potential applications in obtaining a continuous multi-scale representation of terrain contours.

The role of sensory uncertainty in simple contour integration.

Perceptual organization is the process of grouping scene elements into whole entities. A classic example is contour integration, in which separate line segments are perceived as continuous contours. Uncertainty in such grouping arises from scene ambiguity and sensory noise. Some classic Gestalt principles of contour integration, and more broadly, of perceptual organization, have been re-framed in terms of Bayesian inference, whereby the observer computes the probability that the whole entity is present. Previous studies that proposed a Bayesian interpretation of perceptual organization, however, have ignored sensory uncertainty, despite the fact that accounting for the current level of perceptual uncertainty is one of the main signatures of Bayesian decision making. Crucially, trial-by-trial manipulation of sensory uncertainty is a key test to whether humans perform near-optimal Bayesian inference in contour integration, as opposed to using some manifestly non-Bayesian heuristic. We distinguish between these hypotheses in a simplified form of contour integration, namely judging whether two line segments separated by an occluder are collinear. We manipulate sensory uncertainty by varying retinal eccentricity. A Bayes-optimal observer would take the level of sensory uncertainty into account—in a very specific way—in deciding whether a measured offset between the line segments is due to non-collinearity or to sensory noise. We find that people deviate slightly but systematically from Bayesian optimality, while still performing “probabilistic computation” in the sense that they take into account sensory uncertainty via a heuristic rule. Our work contributes to an understanding of the role of sensory uncertainty in higher-order perception.

Variability of formant values at different time points of vowels

Vowel inherent spectral change research has led to two apparently contradictory conclusions about the appropriate representation of vowels: perception studies support a dual-target model of vowels, while production studies focus on calculating higher-fidelity continuous formant contours. This study explores production data in a new way by analyzing where in vowel duration variability is lowest across tokens. Portions of vowels that are less variable across tokens are assumed reflect greater importance to or planning by speakers. Born-and-raised Wisconsinites aged 18–30 were recorded reading a word-in-frame reading list eliciting 30 tokens of 14 American English vowels in the context /hVd/. F1 and F2 were sampled at 50 evenly spaced intervals for each vowel, covering the entire duration. For every speaker, the standard deviations of F1 and F2 were taken separately at every sample. Variability was analyzed as a function of time point. An upturned parabola pattern suggests a single target, a downturned parabola pattern suggests a dual target, and a horizontal pattern suggests continuous specification. For monophthongs, variability is found to be convex, and it is concave for diphthongs. This analysis does not support a dual-target model for monophthongs.

Heritability of human visual contour integration-an integrated genomic study.

Contour integration, a key visual function to deal with occlusion and discontinuity in natural scenes, is essential to human survival. However, individuals are not equally well equipped with this ability. In particular, contour integration deficiencies are commonly detected in patients with mental disorders, especially schizophrenia. To understand the underlying sources of these individual differences, the current study investigated the genetic basis of contour integration in humans. A total of 2619 normal participants were tested on their ability to detect continuous contours embedded in a cluttered background. Quantitative genomic analysis was performed, involving heritability estimation based on single nucleotide polymorphisms (SNPs) and association testing at SNP, gene, and pathway levels. Heritability estimation showed that common SNPs contributed 49.5% (standard error of the mean = 15.6%) of overall phenotypic variation, indicating moderate heritability of contour integration. Two-stage genome-wide association analysis (GWAS) detected four SNPs reaching genome-wide significance in the discovery test (N = 1931) but not passing the replication test (N = 688). Gene-level analysis further revealed a significant genome-wide association of a microRNA-encoding gene MIR1178 in both the discovery and replication cohorts. Another gene poly(A)-binding protein nuclear 1 like, cytoplasmic (PABPN1L) showed suggestive significance in the discovery cohort (p < 1 × 10-4) and was replicated in the replication cohort (p = 0.009). The pathway analysis did not detect any significant pathway. Taken together, this study identified significant gene associations with contour integration and provided support for a genetic transmission of the ability to perceive continuous contours in the environment.

A modified convolutional neural network for face sketch synthesis

A novel deep learning method for face sketch synthesis is proposed in this work. It builds a lightweight neural network which contains two convolutional layers, a pooling layer and a multilayer perceptron convolutional layer to learn a mapping from face photos to sketches. Unlike conventional example-based methods which need to solve complex optimization problems, the proposed method only computes convolution and pooling operations, hence significantly improves the synthesis efficiency. Besides, due to the global feature extraction of the convolutional layer, it achieves more continuous and faithful facial contours. Experiments on three benchmark datasets demonstrate that compared with several state-of-the-arts, the proposed method achieves highly competitive numerical results and is more robust to illumination and expression variations.

GPU based contouring method on grid DEM data

This paper presents a novel method to generate contour lines from grid DEM data based on the programmable GPU pipeline. The previous contouring approaches often use CPU to construct a finite element mesh from the raw DEM data, and then extract contour segments from the elements. They also need a tracing or sorting strategy to generate the final continuous contours. These approaches can be heavily CPU-costing and time-consuming. Meanwhile the generated contours would be unsmooth if the raw data is sparsely distributed. Unlike the CPU approaches, we employ the GPU's vertex shader to generate a triangular mesh with arbitrary user-defined density, in which the height of each vertex is calculated through a third-order Cardinal spline function. Then in the same frame, segments are extracted from the triangles by the geometry shader, and translated to the CPU-side with an internal order in the GPU's transform feedback stage. Finally we propose a “Grid Sorting” algorithm to achieve the continuous contour lines by travelling the segments only once. Our method makes use of multiple stages of GPU pipeline for computation, which can generate smooth contour lines, and is significantly faster than the previous CPU approaches. The algorithm can be easily implemented with OpenGL 3.3 API or higher on consumer-level PCs.

Chronic exposure to aircraft noise and self-measured blood pressure – field study (adults) in the vicinity of a large airport in Germany

Introduction: Based on the concept that noise may trigger repeatedly unavoidable autonomous physiological reactions, which each can cause an increase of blood pressure, the study examined the effects of chronic aircraft noise on self-measured blood pressure (SBPM). Methods: Study region includes areas near a large airport within the 40 dB(A) equivalent continuous sound level contours of aircraft noise for day and night-time, targeting on voluntary adults residing in the defined region. Noise exposure (equivalent continuous sound level LpAeq,18-06h) of the 12 months ahead of measurements was assigned to respective addresses of participants. Telemedical blood pressure devices handed to study participants were issued for SBPM. After being trained, participants performed 2 daily measurements for a 21-day period. Ahead of coaching, a questionnaire with reference to current health, medications, lifestyle, individual factors, as well as noise sensitivity was completed. Multiple linear regression model was calculated to investigate the association between the LpA,eq,18-06h and main outcome systolic BP including age, gender, social status, pack years, and physical activity. Results: Data analyses included n=844 (58.4% w; 41.6% m). BP values (mean of morning readings [mmHg]) were systolic/diastolic 118.1/72.3 in women and 125.4/78.8 in men. Multiple linear regressions result [mmHg×dB-1] b=0.11; 95%CI [-0.01;0.23] for systolic and b=0.06; 95%CI [-0.04; 0.16] for diastolic values. Conclusions: The results of our study － small positive effect estimators without statistical significance － are overall comparable to previously conducted scientific research concerning air traffic noise and continuous BP values. However, no statistically significant correlations between air traffic noise and hypertension as in the HYENA study were found. A direct quantitative comparison with the results of this study may be allowed only to a limited extent, due to methodical differences.

A Metaanalysis of Perceptual Organization in Schizophrenia, Schizotypy, and Other High-Risk Groups Based on Variants of the Embedded Figures Task.

Current research on perceptual organization in schizophrenia frequently employs shapes with regularly sampled contours (fragmented stimuli), in noise fields composed of similar elements, to elicit visual abnormalities. However, perceptual organization is multi-factorial and, in earlier studies, continuous contours have also been employed in tasks assessing the ability to extract shapes from a background. We conducted a systematic review and meta-analysis of studies using closed-contour stimuli, including the Embedded Figures Test (EFT) and related tasks, both in people with schizophrenia and in healthy schizotypes and relatives, considered at increased risk for psychosis. Eleven studies met the selection criteria for inclusion in the meta-analysis, including six that used a between-groups study design (i.e., perceptual organization abilities of schizophrenia/high-risk groups were compared to healthy or clinical controls), and five that treated schizophrenia symptoms or schizotypy traits and indices of perceptual organization as continuous variables. Effect sizes and heterogeneity statistics were calculated, and the risk of publication bias was explored. A significant, moderate effect for EFT performance was found with studies that compared performance of schizophrenia/high-risk groups to a healthy or patient comparison group (d = −0.523, p < 0.001). However, significant heterogeneity was also found amongst the schizotypy, but not schizophrenia studies, as well as studies using accuracy, but not reaction time as a measure of performance. A non-significant correlation was found for the studies that examined schizophrenia symptoms or schizotypy traits as continuous variables (r = 0.012, p = 0.825). These results suggest that deficits in perceptual organization of non-fragmented stimuli are found when differences between schizophrenia/high-risk groups and comparison groups are maximized. These findings should motivate further investigation of perceptual organization abilities with closed-contour stimuli both in schizophrenia and high-risk groups, which is pertinent to current initiatives to improve the assessment and treatment of cognition in schizophrenia.

Composite modified Luneburg model of human eye lens.

A new lens model based on the gradient-index Luneburg lens and composed of two oblate half spheroids of different curvatures is presented. The spherically symmetric Luneburg lens is modified to create continuous isoindicial contours and to incorporate curvatures that are similar to those found in a human lens. The imaging capabilities of the model and the changes in the gradient index profile are tested for five object distances, for a fixed geometry and for a fixed image distance. The central refractive index decreases with decreasing object distance. This indicates that in order to focus at the same image distance as is required in the eye, a decrease in refractive power is needed for rays from closer objects that meet the lens surface at steeper angles compared to rays from more distant objects. This ensures a highly focused image with no spherical aberration.

Modeling spatiotemporal boundary formation

Spatiotemporal boundary formation (SBF) refers to perception of continuous contours, shape, and global motion from sequential transformations of widely separated surface elements. How such minimal information in SBF can produce whole forms and the nature of the computational processes involved remain mysterious. Formally, it has been shown that orientations and motion directions of local edge fragments can be recovered from small sets of element changes (Shipley & Kellman, (1997). Vision Research, 37, 1281–1293). Little experimental work has examined SBF in simple situations, however, and no model has been able to predict human SBF performance. We measured orientation discrimination thresholds in simple SBF displays for thin, oriented bars as a function of element density, number of element transformations, and frame duration. Thresholds decreased with increasing density and number of transformations, and increased with frame duration. An ideal observer model implemented to give trial-by-trial responses in the same orientation discrimination task exceeded human performance. In a second group of experiments, we measured human precision in detecting inputs to the model (spatial, temporal, and angular inter-element separation). A model that modified the ideal observer by added encoding imprecision for these parameters, directly obtained from Exp. 2, and that included two integration constraints obtained from previous research, closely fit human SBF data with no additional free parameters. These results provide the first empirical support for an early stage in shape formation in SBF based on the recovery of local edge fragments from spatiotemporally sparse element transformation events.

Moving object detection and tracking from video captured by moving camera

This paper presents an effective method for the detection and tracking of multiple moving objects from a video sequence captured by a moving camera without additional sensors. Moving object detection is relatively difficult for video captured by a moving camera, since camera motion and object motion are mixed. In the proposed method, the feature points in the frames are found and then classified as belonging to foreground or background features. Next, moving object regions are obtained using an integration scheme based on foreground feature points and foreground regions, which are obtained using an image difference scheme. Then, a compensation scheme based on the motion history of the continuous motion contours obtained from three consecutive frames is applied to increase the regions of moving objects. Moving objects are detected using a refinement scheme and a minimum bounding box. Finally, moving object tracking is achieved using a Kalman filter based on the center of gravity of a moving object region in the minimum bounding box. Experimental results show that the proposed method has good performance.

Techniques to derive geometries for image-based Eulerian computations.

The performance of three frequently used level set-based segmentation methods is examined for the purpose of defining features and boundary conditions for image-based Eulerian fluid and solid mechanics models. The focus of the evaluation is to identify an approach that produces the best geometric representation from a computational fluid/solid modeling point of view. In particular, extraction of geometries from a wide variety of imaging modalities and noise intensities, to supply to an immersed boundary approach, is targeted. Two- and three-dimensional images, acquired from optical, X-ray CT, and ultrasound imaging modalities, are segmented with active contours, k-means, and adaptive clustering methods. Segmentation contours are converted to level sets and smoothed as necessary for use in fluid/solid simulations. Results produced by the three approaches are compared visually and with contrast ratio, signal-to-noise ratio, and contrast-to-noise ratio measures. While the active contours method possesses built-in smoothing and regularization and produces continuous contours, the clustering methods (k-means and adaptive clustering) produce discrete (pixelated) contours that require smoothing using speckle-reducing anisotropic diffusion (SRAD). Thus, for images with high contrast and low to moderate noise, active contours are generally preferable. However, adaptive clustering is found to be far superior to the other two methods for images possessing high levels of noise and global intensity variations, due to its more sophisticated use of local pixel/voxel intensity statistics. It is often difficult to know a priori which segmentation will perform best for a given image type, particularly when geometric modeling is the ultimate goal. This work offers insight to the algorithm selection process, as well as outlining a practical framework for generating useful geometric surfaces in an Eulerian setting.

Semantic Features of ‘Stepped' versus ‘Continuous' Contours in German Intonation

This study analyses the meaning spaces of German pitch contours using two modes of melodic movement: continuous or in steps of sustained pitch. Both the continuous and stepped movements are represented by a set of five basic patterns, the latter being derived from the former. Thirty-six German native speakers judged the pattern sets on a 12-scale semantic differential. The semantic profiles confirm that stepped contours can be conceived of as stylized intonation, in a formal as well as in a functional sense. On the one hand, continuous (non-stylized) and stepped (stylized) contours are assigned different overall meanings (especially on the scales astonished - commonplace and interested - not interested). On the other hand, listeners organize the two contour sets in a similar fashion, which speaks in favour of parallel pattern inventories of continuous and stepped movement, respectively. However, the meaning space of the stylized patterns is affected by formal restrictions, for instance in the step transformation of continuous rises.

Denoising method of X-ray phase contrast DR image for TRISO-coated fuel particles

TRISO (tristructural-isotropic) fuel is a type of micro fuel particles used in high-temperature gas-cooled reactors (HTGRs). Among the quality evaluation methods for such particles, in-line phase contrast imaging technique (PCI) is more feasible for nondestructive measurement. Due to imaging hardware limitations, high noise level is a distinct feature of PCI images, and as a result, the dimensional measurement accuracy of TRISO-coated fuel particles decreases. Therefore, we propose an improved denoising hybrid model named as NL P–M model which introduces non-local theory and retains the merits of the Perona–Malik (P–M) model. The improved model is applied to numerical simulation and practical PCI images. Quantitative analysis proves that this new anisotropic diffusion model can preserve edge or texture information effectively, while ruling out noise and distinctly decreasing staircasing artifacts. Especially during the process of coating layer thickness measurement, the NL P–M model makes it easy to obtain continuous contours without noisy points or fake contour segments, thus enhancing the measurement accuracy. To address calculation complexity, a graphic processing unit (GPU) is adopted to realize the acceleration of the NL P–M denoising.

An improved method of 3D contours extraction from industrial computed tomography volume data

An improved method of 3D contours extraction is presented in this paper. To simplify and improve the two steps operation of traditional wavelet algorithm, an improved method for 2D contours extraction called 2D-IMCE is developed based on stationary wavelet transform. This method can gain complete, fine and continuous contours by only one step through automatically percolating non-contour points without thresholding and human–machine interactions. To inherit superiority of 2D-IMCE, an extended way of it for 3D contours extraction named Fuse-2D-IMCE is derived. It utilizes satisfactory 2D contours to approximate 3D ones based on fusion operation. Firstly, industrial CT volume data are divided into three groups of slices corresponding to three mutual perpendicular directions. Secondly, in each slice group, 2D contours are extracted by 2D-IMCE. Finally, 3D contours are obtained by fusing all 2D ones of three directions. Experimental results demonstrate that the Fuse-2D-IMCE method can effectively extract 3D contours from industrial CT volume data.