Image Morphing Research Articles

Image Morpher

The "Image Morphing with the Beier-Neely Method" research paper extensively explores image transformation techniques, with a special focus on the Beier- Neely approach. Image morphing, the art of seamlessly transforming one image into another, has garnered significant attention for its applications in animation, filmmaking, and scientific visualization. The research paper delves into the historical context and importance of image morphing, particularly emphasizing the role of the Beier-Neely method in addressing the limitations of earlier techniques. Classical image morphing methods, characterized by pixel-level interpolation, suffer from visual artifacts, manual correspondence definition, and sluggishness. These shortcomings set the stage for the introduction of the feature-based Beier-Neely method, which revolutionized image morphing by allowing control points on features, facilitating smooth transitions and natural transformations. This research papers objectives are clearly articulated, with the primary aim of implementing the Beier- Neely method to produce high-quality image morphs. The research paper proposes a system architecture that underscores the use of feature-based control points, Delaunay triangulation, affine transformations, and the significance of visual feedback. Additionally, it provides a detailed analysis of the mathematical foundations and algorithmic intricacies of the Beier-Neely method, elucidating the theoretical framework driving its effectiveness. Overall, the research paper provides a comprehensive exploration of image morphing techniques, highlighting the pivotal role played by the Beier-Neely method in advancing the field.. Key Words: Image Morphing, Beier-Neely Method, Seamless Transitions, Feature-based Control Points, System Architecture, Mathematical Foundations

Dynamic Healing Process Analysis: Image Morphing with Warping Technique for Nose and Esophagus Studies

In this study, image morphing technology is harnessed to investigate the dynamic processes of healing in both the nose and esophagus. The researchers employ a computer-assisted morphing approach to dynamically analyze mucosal processes during the healing study. The focal point of the proposed image morphing method is a specified warping technique that transforms the first image into the second, and vice versa. The metamorphosis unfolds with the first image initially completely deformed toward the second, gradually fading in, while the current image simultaneously becomes progressively distorted and fades out. This results in an initial series of photographs closely resembling the original. The pivotal middle image is crafted through the averaging of the first source image altered halfway toward the second and the second source picture deformed halfway away from the first. The subsequent images in the series resemble the second source picture. The significance of the center picture is underscored, as its visual appeal ensures the overall aesthetic quality of the entire animation sequence. To facilitate seamless transitions between frames, intermediate frames are generated. The proposed technique is substantiated through the use of realistic datasets for testing and validation, demonstrating its superior performance compared to state-of-the-art studies in the field. This comprehensive approach to image morphing not only advances our understanding of healing dynamics in the nose and esophagus but also presents a novel and effective methodology with broad applicability, surpassing the capabilities of current leading-edge studies. The proposed approach showed best performance against state-of-the works

Explainable few-shot learning with visual explanations on a low resource pneumonia dataset

The data hungry nature of neural networks acts as a barrier to their application in data-scarce scenarios like medical domain. Few-shot learning has attracted much interest recently in handling small-scale datasets. Along with the need to handle the issue of limited annotated data in each class, we also need to address the black-box nature of neural nets which hampers their application in risk-sensitive areas. Pneumonia identification in low resource scenarios along with explanations is a challenging task. Therefore, in this paper, we reveal a few-shot learning-based pneumonia classification technique along with deriving visual explanations to gain insights into the model’s decision-making process. Interpretation for models’ decisions is generated by computing the importance scores based on a comparison between the values of activated neurons and the reference values. We achieve a classification accuracy of 87% and 82% for covid-chestxray-dataset and RSNA Pneumonia dataset respectively, thereby utilising 20 images per category for our experiments. Evaluation of importance scores and the change in log odds scores obtained by image morphing task demonstrate that the proposed framework outperformed the other popular gradient-based methods.

Image Morphing Techniques: A Review

Nowadays image morphing has become one of the important techniques in applications that require a graphical representation of objects. Morphing tools have become very well known among users who work on multimedia applications such as art effects, virtual games, photo morphing, and social media, in addition to scientific and academic fields. There are many algorithms to apply morphing operations, including the basic and improved techniques, which share some essential stages, but vary in the algorithm details and the produced image qualities. Morphing techniques, in general, are based on image features and changing them through a warping process to produce another image or mixing two images to produce a new combined image. This paper provides an overview of different morphing techniques explaining how they work and discuss their features in some terms such as the morph visual quality, technical efficiency, and complexity, which can assist the researcher in the image morphing field to compare and identify morphing techniques that suit their working area.

Bionic Design Model for Co-creative Product Innovation Based on Deep Generative and BID

Bio-inspired design (BID) is an abstract process, if we can visualize the process of fusing abstract biological inspiration with figurative product shapes, and combine it with artificial intelligence technology to express the designer’s creativity, it will greatly improve the efficiency and accuracy of product shape bionic design. To address this problem, we combine BID with deep generative (DG) model to build a co-creative deep generative bio-inspired design (DGBID) model. Firstly, the designers used perceptual engineering and eye-movement experiments to select the bionic creature that best fits the bionic product and the suitable bionic product and bionic image, respectively. Then, the images are embedded into the potential space of StyleGAN, and the potential relationship between the two is visualized using StyleGAN’s image morphing technique, which generates a new bionic fusion scheme. Finally, the contour lines of the solution are extracted as a reference, the designer is involved in the optimization of the scheme as a sketch, and the hand-drawn sketch is transformed into a real product solution using style migration techniques. The entire bionic design experiment process is a co-creative approach with artificial intelligence technology as the lead and designer participation. The feasibility of the method is verified using the side view of a car as a bionic product. The results show that the integration of bionic technology with deep generative model technology can accelerate the innovation and development of bionic products and provide designers with design references and rapid-generation tools.

Spartacus and His Early Soviet Theatrical Representation

Spartacus became one of the key figures of Soviet dramaturgy in the 1920s. He was presented as the only ancient predecessor of the Bolsheviks and his theatrical image significantly shaped the later icon of the gladiator as a brave leader of the oppressed masses and a hero acting in the name of the proletariat. This article explores the image of Spartacus in early Soviet theater and mass performance and outlines the correlation between the template of Spartacus’ portrayal, Raffaello Giovagnoli’s novel Spartaco (1874), and the first dramatic adaptations by Vladimir Mazurkevich (1920) and Vladimir Volkenstein (1921). The article examines the use of the ancient hero in Bolshevik propaganda and traces the ways in which Spartacus’ image morphs and maps onto wider shifts of Soviet political and cultural policy in the early decades of the USSR.

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation.

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semantics including color, spatial coherence, textures, and high-level concepts. This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images. As shown in Fig. 1, the deep generative prior (DGP) provides compelling results to restore missing semantics, e.g., color, patch, resolution, of various degraded images. It also enables diverse image manipulation including random jittering, image morphing, and category transfer. Such highly flexible restoration and manipulation are made possible through relaxing the assumption of existing GAN inversion methods, which tend to fix the generator. Notably, we allow the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN. We show that these easy-to-implement and practical changes help preserve the reconstruction to remain in the manifold of nature images, and thus lead to more precise and faithful reconstruction for real images. Code is available at https://github.com/XingangPan/deep-generative-prior.

Використання графічних 3D-зображень облич для експрес-діагностування та побудови біомедичних засобів

The article discusses the use of graphic images for rapid diagnosis and the construction of biomedical software. Diagnostic features of morphological analysis of images of the human face for plastic and reconstructive operations are determined. The use of 3D images for the diagnosis of genetic diseases is considered. Recommendations for the use of three-dimensional modeling in this field have been developed. The use of morphing of 3D images of the human face for diagnostic tasks is proposed. A method of analyzing the compliance of age-related changes in the child's development with established norms based on the use of image morphing is proposed, which makes it possible to increase the efficiency of express diagnosis. The main requirements for the construction of software analogs of biomedical devices using 3-D models are defined, which is the basis for the construction of computerized modern bimedical devices and systems.

Cortically Based Optimal Transport

We introduce a model for image morphing in the primary visual cortex V1 to perform completion of missing images in time. We model the output of simple cells through a family of Gabor filters and the propagation of the neural signal accordingly to the functional geometry induced by horizontal connectivity. Then we model the deformation between two images as a path relying two different outputs. This path is obtained by optimal transport considering the Wasserstein distance geodesics associated to some probability measures naturally induced by the outputs on V1. The frame of Gabor filters allows to project back the output path, therefore obtaining an associated image stimulus deformation. We perform a numerical implementation of our cortical model, assessing its ability in reconstructing rigid motions of simple shapes.

Face Morphing, a Modern Threat to Border Security: Recent Advances and Open Challenges

Face morphing poses a serious threat to Automatic Border Control (ABC) and Face Recognition Systems (FRS) in general. The aim of this paper is to present a qualitative assessment of the morphing attack issue, and the challenges it entails, highlighting both the technological and human aspects of the problem. Here, after the face morphing attack scenario is presented, the paper provides an overview of the relevant bibliography and recent advances towards two central directions. First, the morphing of face images is outlined with a particular focus on the three main steps that are involved in the process, namely, landmark detection, face alignment and blending. Second, the detection of morphing attacks is presented under the prism of the so-called on-line and off-line detection scenarios and whether the proposed techniques employ handcrafted features, using classical methods, or automatically generated features, using deep-learning-based methods. The paper, then, presents the evaluation metrics that are employed in the corresponding bibliography and concludes with a discussion on open challenges that need to be address for further advancing automatic detection of morphing attacks. Despite the progress being made, the general consensus of the research community is that significant effort and resources are needed in the near future for the mitigation of the issue, especially, towards the creation of datasets capturing the full extent of the problem at hand and the availability of reference evaluation procedures for comparing novel automatic attack detection algorithms.

Identity preserving multi-pose facial expression recognition using fine tuned VGG on the latent space vector of generative adversarial network.

Facial expression is the crucial component for human beings to express their mental state and it has become one of the prominent areas of research in computer vision. However, the task becomes challenging when the given facial image is non-frontal. The influence of poses on facial images is alleviated using an encoder of a generative adversarial network capable of learning pose invariant representations. State-of-art results for image generation are achieved using styleGAN architecture. An efficient model is proposed to embed the given image into the latent vector space of styleGAN. The encoder extracts high-level features of the facial image and encodes them into the latent space. Rigorous analysis of semantics hidden in the latent space of styleGAN is performed. Based on the analysis, the facial image is synthesized, and facial expressions are recognized using an expression recognition neural network. The original image is recovered from the features encoded in the latent space. Semantic editing operations like face rotation, style transfer, face aging, image morphing and expression transfer can be performed on the image obtained from the image generated using the features encoded latent space of styleGAN. L2 feature-wise loss is applied to warrant the quality of the rebuilt image. The facial image is then fed into the attribute classifier to extract high-level features, and the features are concatenated to perform facial expression classification. Evaluations are performed on the generated results to demonstrate that state-of-art results are achieved using the proposed method.

Neural crossbreed

We propose Neural Crossbreed, a feed-forward neural network that can learn a semantic change of input images in a latent space to create the morphing effect. Because the network learns a semantic change, a sequence of meaningful intermediate images can be generated without requiring the user to specify explicit correspondences. In addition, the semantic change learning makes it possible to perform the morphing between the images that contain objects with significantly different poses or camera views. Furthermore, just as in conventional morphing techniques, our morphing network can handle shape and appearance transitions separately by disentangling the content and the style transfer for rich usability. We prepare a training dataset for morphing using a pre-trained BigGAN, which generates an intermediate image by interpolating two latent vectors at an intended morphing value. This is the first attempt to address image morphing using a pre-trained generative model in order to learn semantic transformation. The experiments show that Neural Crossbreed produces high quality morphed images, overcoming various limitations associated with conventional approaches. In addition, Neural Crossbreed can be further extended for diverse applications such as multi-image morphing, appearance transfer, and video frame interpolation.

Image Morphing in Deep Feature Spaces: Theory and Applications

This paper combines image metamorphosis with deep features. To this end, images are considered as maps into a high-dimensional feature space and a structure-sensitive, anisotropic flow regularization is incorporated in the metamorphosis model proposed by Miller and Younes (Int J Comput Vis 41(1):61–84, 2001) and Trouvé and Younes (Found Comput Math 5(2):173–198, 2005). For this model, a variational time discretization of the Riemannian path energy is presented and the existence of discrete geodesic paths minimizing this energy is demonstrated. Furthermore, convergence of discrete geodesic paths to geodesic paths in the time continuous model is investigated. The spatial discretization is based on a finite difference approximation in image space and a stable spline approximation in deformation space; the fully discrete model is optimized using the iPALM algorithm. Numerical experiments indicate that the incorporation of semantic deep features is superior to intensity-based approaches.

Image Morphing With Perceptual Constraints and STN Alignment

AbstractIn image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set and maintain a well‐paced visual transition from one to the next. In this paper, we propose a conditional generative adversarial network (GAN) morphing framework operating on a pair of input images. The network is trained to synthesize frames corresponding to temporal samples along the transformation, and learns a proper shape prior that enhances the plausibility of intermediate frames. While individual frame plausibility is boosted by the adversarial setup, a special training protocol producing sequences of frames, combined with a perceptual similarity loss, promote smooth transformation over time. Explicit stating of correspondences is replaced with a grid‐based freeform deformation spatial transformer that predicts the geometric warp between the inputs, instituting the smooth geometric effect by bringing the shapes into an initial alignment. We provide comparisons to classic as well as latent space morphing techniques, and demonstrate that, given a set of images for self‐supervision, our network learns to generate visually pleasing morphing effects featuring believable in‐betweens, with robustness to changes in shape and texture, requiring no correspondence annotation.

Automatically Controlled Morphing of 2D Shapes with Textures

This paper deals with 2D image transformations from a perspective of a 3D heterogeneous shape modeling and computer animation. Shape and image morphing techniques have attracted a lot of attention ...

Convergence of the Time Discrete Metamorphosis Model on Hadamard Manifolds

Continuous image morphing is a classical task in image processing. The metamorphosis model proposed by Trouve, Younes, and coworkers [M. I. Miller and L. Younes, Int. J. Comput. Vis., 41 (2001), pp...

Correcting Position Error in Precipitation Data Using Image Morphing

Rainfall estimates based on satellite data are subject to errors in the position of the rainfall events in addition to errors in their intensity. This is especially true for localized rainfall events such as the convective rainstorms that occur during the monsoon season in sub-Saharan Africa. Many satellite-based estimates use gauge information for bias correction. However, bias adjustment methods do not correct the position errors explicitly. We propose to gauge-adjust satellite-based estimates with respect to the position using a morphing method. Image morphing transforms an image, in our case a rainfall field, into another one, by applying a spatial transformation. A benefit of this approach is that it can take both the position and the intensity of a rain event into account. Its potential is investigated with two case studies. In the first case, the rain events are synthetic, represented by elliptic shapes, while the second case uses real data from a rainfall event occurring during the monsoon season in southern Ghana. In the second case, the satellite-based estimate IMERG-Late (Integrated Multi-Satellite Retrievals for GPM ) is adjusted to gauge data from the Trans-African Hydro-Meteorological Observatory (TAHMO) network. The results show that the position errors can be corrected, while preserving the higher spatial variability of the satellite-based estimate.

Generation of Telugu Emotional Speech from Neutral Speech by using Voice Morphing Algorithm

Voice morphing is the conversion of one voice signal into another voice signal i.e. source voice signal into target voice signal. Like image morphing, the aim of speech morphing is to preserve the pooled properties of the source signal and target signal during the generation of a smooth conversion between them. The major properties of speech signal are its pitch and envelope information. Pitch, duration and intensity of speech signal parameters are considered to get emotional voice from neutral or emotion. We are using TD-PSOLA technique to extract the prosodic parameters and during the training phase.

Quantifying Facial Expression Intensity and Signal Use in Deaf Signers.

We live in a world of rich dynamic multisensory signals. Hearing individuals rapidly and effectively integrate multimodal signals to decode biologically relevant facial expressions of emotion. Yet, it remains unclear how facial expressions are decoded by deaf adults in the absence of an auditory sensory channel. We thus compared early and profoundly deaf signers (n= 46) with hearing nonsigners (n= 48) on a psychophysical task designed to quantify their recognition performance for the six basic facial expressions of emotion. Using neutral-to-expression image morphs and noise-to-full signal images, we quantified the intensity and signal levels required by observers to achieve expression recognition. Using Bayesian modeling, we found that deaf observers require more signal and intensity to recognize disgust, while reaching comparable performance for the remaining expressions. Our results provide a robust benchmark for the intensity and signal use in deafness and novel insights into the differential coding of facial expressions of emotion between hearing and deaf individuals.

Facial image comparisons of morphed facial imagery

ABSTRACTFacial image morphing is a technique whereby two or more faces are blended together to create a new face (the morph). Apps and open source software are now freely available to create morphs. While morph creation is predominantly for entertainment value, it is also a method being used to create facial imagery for use on fraudulent identity documents. This study sought to answer two questions. First, would participants accept a morph persona (an identity created using only morphed facial imagery) as a credible identity? Second, could participants match faces that had been used to create a morph (so-called constituent faces)? Results showed that morph personas were credible, being correctly matched more often than alternative images of real people. Further, results showed that propensity to declare a constituent face a match to its morph was dependent on the type of morph, with morphs made using two faces more likely to yield matches than those made using eight or 16 faces. A follow up similarity study on faces selected showed that even if a constituent face was selected it would more than likely have been ruled out as a match following a more thorough one-to-one comparison.