Image Morphing Research Articles

How do Task-dependent Attentional Demands Alter How Objects are Learned?

We learn to recognize objects in the world in environments whose attentional demands vary greatly. How does such learning depend upon task-dependent attentional demands? Object recognition needs to be tolerant, or invariant, with respect to position, size, and object view changes. In monkeys and humans, a key area for recognition is the anterior inferotemporal cortex (ITa). Recent neurophysiological data show that ITa cells with high object selectivity often have low position tolerance. We propose a neural model whose cells learn to simulate this tradeoff, as well as ITa responses to image morphs, while explaining how invariant recognition properties may arise gradually due to processes across multiple cortical areas, including the cortical magnification factor, multiple receptive field sizes, and top-down attentive matching and learning properties that may be tuned by task requirements to attend to either concrete or abstract visual features. The model predicts that data from the tradeoff and image morph tasks emerge from different task-dependent levels of attentive vigilance in the animals performing them. Computer simulations predict how receptive field properties would change under different task-sensitive vigilance levels. The model also predicts how vigilance may be controlled by mismatches between top-down learned expectations and bottom-up perceptual inputs, leading to acetylcholine release in neocortical circuits and an increase in vigilance. These results emphasize the importance of top-down attentional mechanisms in object learning and recognition, and of the need to carefully monitor task demands in studies of perceptual and cognitive processing.

Face Transformation With Harmonic Models by the Finite-Volume Method With Delaunay Triangulation

To carry out face transformation, this paper presents new numerical algorithms, which consist of two parts, namely, the harmonic models for changes of face characteristics and the splitting techniques for grayness transition. The main method in this paper is a combination of the finite-volume method (FVM) with Delaunay triangulation to solve the Laplace equations in the harmonic transformation of face images. The advantages of the FVM with Delaunay triangulation are given as follows: 1) easy to formulate the linear algebraic equations; 2) good in retaining the pertinent geometric and physical need; and 3) less central processing unit time needed. Numerical and graphical experiments have been conducted for the face transformation from a female (woman) to a male (man), and vice versa. The computed sequential errors are O(N⁻³/²), where N² is the division number of a pixel into subpixels. These computed errors coincide with the analysis on the splitting-shooting method (SSM) with piecewise constant interpolation in the previous paper of Li and Bai. In computation, the average absolute errors of restored pixel grayness can be smaller than 2 out of 256 grayness levels. The FVM is as simple as the finite-difference method (FDM) and as flexible as the finite-element method (FEM). Hence, the FVM is particularly useful when dealing with large face images with a huge number of pixels in shape distortion. The numerical transformation of face images in this paper can be used not only in pattern recognition but also in resampling, image morphing, and computer animation.

Relaxation method for conjugate image processing

Proposed is an efficient algorithm for transforming a greyscale image into its conjugate image, which was originally introduced for image morphing. While potential applications regarding image processing are very promising, its implementation has not been straightforward owing to high computational complexity. The algorithm is shown to be valid and efficient by examining simple and complex image patterns.

HANDEDNESS AND ASYMMETRY IN SCALE-EATING CICHLIDS: ANTISYMMETRIES OF DIFFERENT STRENGTH

Individual symmetry is believed to be advantageous and reflecting developmental stability, but frequency-dependent selection can also maintain polymorphisms of asymmetric phenotypes. There are many examples of so-called antisymmetry, where mirror image morphs occur at equal frequencies. With very few exceptions, these are caused by nongenetic variation. One notable exception is handedness and mouth bending variation in the scale-eating cichlid Perissodus microlepis, which has been suggested to be an example of antisymmetry determined by a single genetic locus of large effect. Here, we report that this handedness and mouth bending asymmetry are not jointly and exclusively determined by a single major locus. We found no evidence of a major locus for asymmetry and some support for a major handedness locus. Also, asymmetry is plastic in this species: it can change in adults. We suggest that behavioral handedness in this system precedes and guides morphological asymmetry.

An image morphing method for 3D reconstruction and FE-analysis of pore networks in thermal spray coatings

Using thermal spraying various surface coatings consisting of different material compositions can be manufactured. Besides different solid phases the resulting coating microstructure often contains a non-negligible amount of pores altering their mechanical properties. A common practice to analyze the porosity and composition of a coating is to create cross section images using standard light microscopy equipment or a scanning electron microscope. In this paper a method is presented to construct a three-dimensional multiphase model of the coating from a number of such cross section images by means of an image morphing technique. The resulting model can then be used for visualization purposes or further analysis e.g. within a finite element simulation. The described method has been applied to the construction of a finite element model of a porous coating sample which is used in a compaction simulation to determine its behavior in a rolling process. The required cross section images were obtained using a successive grinding and microscopy procedure. The material behavior of the porous material is modeled by using a modified Johnson–Cook material model formulation for an elasto-viscoplastic material. Comparison of 2D and 3D-simulation results are shown.

Image Morphing and Warping: Application to Speech Simulation Using a Single Image

In this paper, we propose a fully automatic real time one image face gesture simulation using image morphing. Given a single image of a subject, we create several facial expressions of the face by morphing the image based on prior information stored in a data bank. The process involves the automatic detection of the control points both on the target image and the source data. The source data is a string of frames containing the desired facial expressions. A face detection neural network and a lips contour detector using edges and the SNAKES algorithm are employed to detect the face position and features. Five control points and the lips contour, for both the source and target images, are then extracted based on the facial features. Triangulation method is then used to match and warp the source image to the target image using the control points. In this experiment, using one expressionless face portrait, we create an animation to make it appear like the subject is pronouncing the five Japanese vowels. The final results shows the effectiveness of our method.

A rational B-spline hypervolume for multidimensional multivariate modeling

This paper proposes a rational B-spline hypervolume that represents a volume object which has multiple attributes defined in a multidimensional space. This representation provides a mathematical framework for modeling and visualizing a multidimensional multivariate object as well as analyzing the object interiors to extract its intrinsic features that are directly inaccessible. We discuss the NURBS extension procedure showing that the proposed hypervolume is a generalized volume function not depending on the domain dimensionality and its range dimensionality. Useful expressions arising in connection with a computational treatment are presented for geometric and mathematical analysis of a volume object based on the proposed hypervolume. We also describe the approximation and interpolation algorithms of the proposed hypervolume. Finally, we show various applications such as grid generation, flow visualization, implicit surface modeling, and image morphing. They demonstrate the usefulness and the extensibility of the proposed hypervolume.

TIMER: Tensor Image Morphing for Elastic Registration

We propose a novel diffusion tensor imaging (DTI) registration algorithm, called Tensor Image Morphing for Elastic Registration (TIMER), which leverages the hierarchical guidance of regional distributions and local boundaries, both extracted directly from the tensors. Currently available DTI registration methods generally extract tensor scalar features from each tensor to construct scalar maps. Subsequently, regional integration and other operations such as edge detection are performed to extract more features to guide the registration. However, there are two major limitations with these approaches. First, the computed regional features might not reflect the actual regional tensor distributions. Second, by the same token, gradient maps calculated from the tensor-derived scalar feature maps might not represent the actual tissue tensor boundaries. To overcome these limitations, we propose a new approach which extracts regional and edge information directly from a tensor neighborhood. Regional tensor distribution information, such as mean and variance, is computed in a multiscale fashion directly from the tensors by taking into account the voxel neighborhood of different sizes, and hence capturing tensor information at different scales, which in turn can be employed to hierarchically guide the registration. Such multiscale scheme can help alleviate the problem of local minimum and is also more robust to noise since one can better determine the statistical properties of each voxel by taking into account the properties of its surrounding. Also incorporated in our method is edge information extracted directly from the tensors, which is crucial to facilitate registration of tissue boundaries. Experiments involving real subjects, simulated subjects, fiber tracking, and atrophy detection indicate that TIMER performs better than the other methods (Yang et al., 2008; Zhang et al., 2006).

A Simple Criterion for Nodal 3-connectivity in Planar Graphs

This paper gives a simple characterisation of nodally 3-connected planar graphs, which have the property that barycentric mappings, and more generally convex combination mappings, are embeddings. This has applications in numerical analysis (grid generation), and in computer graphics (image morphing, surface triangulations, texture mapping): see [Michael S. Floater (2002). Convex combination maps. In Algorithms for Approximation IV, 18–23, J. Levesley, I.J. Anderson, and J.C. Mason (eds), University of Huddersfield; Geoffrey White (2004). Mesh parametrization for texture mapping. Undergraduate computer science project, Oxford University].

Fast tensor image morphing for elastic registration.

We propose a novel algorithm, called Fast Tensor Image Morphing for Elastic Registration or F-TIMER. F-TIMER leverages multiscale tensor regional distributions and local boundaries for hierarchically driving deformable matching of tensor image volumes. Registration is achieved by aligning a set of automatically determined structural landmarks, via solving a soft correspondence problem. Based on the estimated correspondences, thin-plate splines are employed to generate a smooth, topology preserving, and dense transformation, and to avoid arbitrary mapping of non-landmark voxels. To mitigate the problem of local minima, which is common in the estimation of high dimensional transformations, we employ a hierarchical strategy where a small subset of voxels with more distinctive attribute vectors are first deployed as landmarks to estimate a relatively robust low-degrees-of-freedom transformation. As the registration progresses, an increasing number of voxels are permitted to participate in refining the correspondence matching. A scheme as such allows less conservative progression of the correspondence matching towards the optimal solution, and hence results in a faster matching speed. Results indicate that better accuracy can be achieved by F-TIMER, compared with other deformable registration algorithms, with significantly reduced computation time cost of 4-14 folds.

Unsupervised morphing by conjugate image processing

Unsupervised image morphing is a very challenging task in machine learning, whereas it is relatively easy and common for the human brain. Even a simple deformation of an object such as a translation or scaling operation follows a complex curved trace in a high-dimensional image space. The learning of such a complex curved manifold needs human assistance or sufficiently dense intermediate data points. Presented is a novel transformation framework with which a curved manifold describing the deformation of images turns into a simple linear structure in the transformed space. Therefore, image morphing can be achieved by simple linear superposition using the conjugate image representation.

Space-Time Light Field Rendering

In this paper, we propose a novel framework called space-time light field rendering, which allows continuous exploration of a dynamic scene in both space and time. Compared to existing light field capture/rendering systems, it offers the capability of using unsynchronized video inputs and the added freedom of controlling the visualization in the temporal domain, such as smooth slow motion and temporal integration. In order to synthesize novel views from any viewpoint at any time instant, we develop a two-stage rendering algorithm. We first interpolate in the temporal domain to generate globally synchronized images using a robust spatial-temporal image registration algorithm followed by edge-preserving image morphing. We then interpolate these software-synchronized images in the spatial domain to synthesize the final view. In addition, we introduce a very accurate and robust algorithm to estimate subframe temporal offsets among input video sequences. Experimental results from unsynchronized videos with or without time stamps show that our approach is capable of maintaining photorealistic quality from a variety of real scenes.

An Image Morphing Technique Based on Optimal Mass Preserving Mapping

Image morphing, or image interpolation in the time domain, deals with the metamorphosis of one image into another. In this paper, a new class of image morphing algorithms is proposed based on the theory of optimal mass transport. The L(2) mass moving energy functional is modified by adding an intensity penalizing term, in order to reduce the undesired double exposure effect. It is an intensity-based approach and, thus, is parameter free. The optimal warping function is computed using an iterative gradient descent approach. This proposed morphing method is also extended to doubly connected domains using a harmonic parameterization technique, along with finite-element methods.

Frostbite in a Mountain Climber Treated with Hyperbaric Oxygen: Case Report

We describe a case of frostbite to all fingers of a mountain climber, treated with hyperbaric oxygen (HBO). All fingers eventually healed to full function, with only some cosmetic deformity to the tip of the most severely affected finger. Because few cases of frostbite treated with HBO have been reported, we hope that such case reports will stimulate future research in this area. It is hoped that multiple anecdotal cases may help guide future research in this area. Sequential digital photographs were taken at various stages of healing during HBO treatments. We raise the possibility of photographic techniques and standards that may facilitate planning of therapy for frostbite with improved treatment comparisons, resulting in more consistency in the future. For example, a graphical software application is described that allows morphing of sequential images to demonstrate healing progress in a concise movie format. The morphing allows concise demonstration of healing to the referring provider and patient and helps in teaching and research on frostbite treatment outcomes.

Medical Applications of Digital Image Morphing

The authors present a unique medical technical application for illustrating the success and/or failure of the physiological healing process as a dynamically morphed video. Two examples used in this report include the healing of a severely fractured humerus from an explosion in Iraq and the other of dramatic tissue destruction from a poisonous spider bite. For the humerus, several sequential x-rays obtained throughout orthopedic surgical procedures and the healing process were morphed together representing a time-lapsed video of the healing process. The end result is a video that demonstrates the healing process in an animation that radiologists envision and report to other clinicians. For the brown recluse spider bite, a seemingly benign skin lesion transforms into a wide gaping necrotic wound with dramatic appearance within days. This novel technique is not presented for readily apparent clinical advantage, rather, it may have more immediate application in providing treatment options to referring providers and/or patients, as well as educational value of healing or disease progression over time. Image morphing is one of those innovations that is just starting to come into its own. Morphing is an image processing technology that transforms one image into another by generating a series of intermediate synthetic images. It is the same process that Hollywood uses to turn people into animals in movies, for example. The ability to perform morphing, once restricted to high-end graphics workstations, is now widely available for desktop computers. The authors describe how a series of radiographic images were morphed into a short movie clip using readily available software and an average laptop. The resultant video showed the healing process of an open comminuted humerus fracture that helped demonstrate how amazingly the human body heals in a case presentation in a time-lapse fashion.

Cross Dissolve Without Cross Fade: Preserving Contrast, Color and Salience in Image Compositing

Abstract Linear interpolation is the standard image blending method used in image compositing. By averaging in the dynamic range, it reduces contrast and visibly degrades the quality of composite imagery. We demonstrate how to correct linear interpolation to resolve this longstanding problem. To provide visually meaningful, high level control over the compositing process, we introduce three novel image blending operators that are designed to preserve key visual characteristics of their inputs. Our contrast preserving method applies a linear color mapping to recover the contrast lost due to linear interpolation. Our salience preserving method retains the most informative regions of the input images by balancing their relative opacity with their relative saliency. Our color preserving method extends homomorphic image processing by establishing an isomorphism between the image colors and the real numbers, allowing any mathematical operation defined on real numbers to be applied to colors without losing its algebraic properties or mapping colors out of gamut. These approaches to image blending have artistic uses in image editing and video production as well as technical applications such as image morphing and mipmapping. Categories and Subject Descriptors (according to ACM CCS): I.3.3 [Computer Graphics]: Picture/Image Generation

A parallel application for 3D reconstruction of coronal loops using image morphing

This paper presents an approach for 3D reconstruction of X-ray tomographic images of coronal loops, observed on the solar atmosphere by the Japanese satellite Yohkoh. In this approach, the intermediate cross-sections images of the magnetic loop are generated with image morphing controlled by a Bezier curve in arc shape. Due to the high computational costs involved in the processing and visualization of solar images, a parallel application for 3D reconstruction of a coronal loop was implemented to execute in the Atlas parallel system.

Defocus morphing in real aperture images

A new concept called defocus morphing in real aperture images is introduced. View morphing is an existing example of shape-preserving image morphing based on the motion cue. It is proved that images can also be morphed based on the depth-related defocus cue. This illustrates that the morphing operation is not necessarily a geometric process alone; one can also perform a photometry-based morphing wherein the shape information is implicitly buried in the image intensity field. A theoretical understanding of the defocus morphing process is presented. It is shown mathematically that, given two observations of a three-dimensional scene for different camera parameter settings, we can obtain a virtual observation for any camera parameter setting through a simple nonlinear combination of these observations.

Texture metamorphosis driven by texton masks

Image morphing has been extensively studied in computer graphics and it can be summarized as follows: given two input images, morphing algorithms produce a sequence of inbetween images which transforms the source image into the target image in a visually pleasant way. In this paper, we propose an algorithm, based on recent advances from texture-from-sample ideas, which synthesizes a metamorphosis sequence targeted specifically for textures. We use the idea of binary masks—or texton masks—to control and drive the morphing sequence. Our solution provides an automatic mapping from source texels into target texels and thus guarantees a coherent and visually smoothing transition from the source texture into the target texture. We compare our morphing results with prior work and with simple interpolation between corresponding pixels in the same source and target images.

Angle resolved imaging of polymer blend systems: From images to a 3D volume of material morphology

ARXPS has been widely used for thickness calculations, discerning molecular orientation, and estimating both surface enrichment and concentration gradients. For multicomponent heterogeneous samples, not only the average concentration, but also morphology and chemical heterogeneity are important. In this work we demonstrate the results of combining ARXPS and imaging for analysis of polymer blend samples. Challenges in combining the two approaches include locating the same area for image acquisition at multiple take-off angles, the small depth of focus in imaging mode, and the geometrical transformation of images with changing take-off angle. The conversion of the original photoelectron images to a volume representing the top 3–10 nm of the polymer blend requires spatial image transformation to correct for geometry or image warping, automatic image registration, mapping images to concentration with the assistance of AR small area spectroscopy, image morphing and visualization. AR images were used to create volumes from the top 3–10 nm of blends of polyvinylchloride (PVC) and polymethylmethacrylate (PMMA). These volumes allow for the visualization and estimation of the degree of surface segregation and separation of polymer phases.