Search

Medical image enhancement is considered a challenging image-processing framework because the low quality of images resulting after acquisition and transmission seriously affects the clinical diagnosis and observation. In order to improve the medical image visual quality, a novel medical image enhancement algorithm that is based on contrast adaptive histogram equalization and pelican optimization algorithm is proposed in this work. The estimation process using our proposed model improves the efficiency of the operation and provides superior results in terms of image quality and contrast. There are three steps in the enhancement process. The primary step includes medical image generation using a Text-to-image generative model. Secondly, the estimation of the clip-limit, which controls the enhancing performance. Finally, the operation of enhancing the medical images using our proposed method. The simulation experiments prove that our proposed algorithm achieves superior performance qualitatively and quantitatively, compared with the state-of-the-art experimental methods, Upon a thorough examination and comparative analysis of performance parameters. Furthermore, the advantageous characteristic of this algorithm is its applicability in multiple types of images. Improving the quality of the medical images using our algorithm allows us to attain a superior visual impact on the processed image, and to increase the rate of conformity in the clinical diagnosis. Our proposed model illustrates the structure and forms of relevant details, contained in the medical images. This leads to an increase in overall contrast and enhances visual perception. [ABSTRACT FROM AUTHOR]

Image processing holds an indispensable role in various facets of our daily lives, professional undertakings, and educational pursuits, encompassing a gamut of tasks including image reconstruction, inpainting, super-resolution, colorization, and editing. In recent years, the advent of advanced models rooted in Generative Adversarial Networks (GANs) has showcased remarkable capabilities in the domain of image synthesis, catapulting the direct application of these cutting-edge models to image processing to the forefront of contemporary research. Within this context, GAN inversion, an emerging paradigm, assumes a pivotal role in the landscape of image processing tasks. This paper delves into the realm of image inversion based on the latent space of GAN models. In response to the inherent limitations of current GAN inversion methods, we introduce three innovations. Firstly, we depart from the conventional use of convolutional networks for generator implementation in existing GAN inversion techniques. Our approach employs generators entirely composed of fully connected layers, marking a significant departure from spatial convolutions and information propagation across pixels. Secondly, we leverage the distinct characteristic of generators engaged in conditional independent pixel synthesis. This feature is enhanced by fusing feature maps spanning contiguous strata of a feature pyramid network during the feature extraction process. Lastly, our framework offers a high degree of versatility, extending its applicability beyond image reconstruction to domains like image inpainting, super-resolution, and image colorization. Empirical results, based on the CelebFaces Attribute-HQ (CelebA-HQ) dataset, unequivocally demonstrate that GAN inversion, built on the principle of conditional independent pixel synthesis, yields superior reconstruction outcomes. Furthermore, it proves amenable to a plethora of tasks, including image inpainting, super-resolution, and image colorization. These advances open new vistas in image processing. [ABSTRACT FROM AUTHOR]

In recent years, Generative Adversarial Network (GAN) have shown great potential and achieved excellent performance on the task of generating optical images. However, when GAN is applied to Synthetic Aperture Radar (SAR) images, the differences in imaging mechanisms between SAR images and optical images make GAN susceptible to training instability and model collapse problems during training. In this paper, we propose a new end-to-end model called Dual Discriminator Modified Conditional Generative Adversarial Network (DDM-CGAN) to address these issues. First, two discriminators are designed to play an adversarial game against the generator in DDM-CGAN. One discriminator favors samples from real data, while the other rewards high scores for generated samples. Essentially, we designed a novel objective function by utilizing the dual discriminator to combine the respective advantages of alternative cost function and original cost function of the standard GAN. We theoretically prove that this objective function can optimize DDM-CGAN towards minimizing the Kullback–Leibler Divergence, thus avoiding the problem of non-convergence during model training. Second, we propose a modified gradient penalty, which makes the model training more stable. In addition, the introduction of a discriminative auxiliary classifier provides the generator with information about the target distribution, thus improving the diversity of the generated images. We perform comprehensive qualitative and quantitative experiments with the Gaofen-3 SAR image dataset. Our proposed DDM-CGAN is compared with the state-of-the-art SAR image generation methods. Experimental results demonstrate that the SAR images generated by DDM-CGAN achieves optimal results in terms of the similarity, statistical characteristics, and diversity. [ABSTRACT FROM AUTHOR]

The advent of deep neural networks and improved computational power have brought a revolutionary transformation in the fields of computer vision and image processing. Within the realm of computer vision, there has been a significant interest in the area of synthetic image generation, which is a creative side of AI. Many researchers have introduced innovative methods to identify deep neural network‐based architectures involved in image generation via different modes of input, like text, scene graph layouts and so forth to generate synthetic images. Computer‐generated images have been found to contribute a lot to the training of different machine and deep‐learning models. Nonetheless, we have observed an immediate need for a comprehensive and systematic literature review that encompasses a summary and critical evaluation of current primary studies' approaches toward image generation. To address this, we carried out a systematic literature review on synthetic image generation approaches published from 2018 to February 2023. Moreover, we have conducted a systematic review of various datasets, approaches to image generation, performance metrics for existing methods, and a brief experimental comparison of DCGAN (deep convolutional generative adversarial network) and cGAN (conditional generative adversarial network) in the context of image generation. Additionally, we have identified applications related to image generation models with critical evaluation of the primary studies on the subject matter. Finally, we present some future research directions to further contribute to the field of image generation using deep neural networks. [ABSTRACT FROM AUTHOR]

This paper focuses on the development of an improved Generative Adversarial Network (GAN) specifically designed for generating color portraits from sketches. The construction of the system involves using a GPU (Graphics Processing Unit) computing host as the primary unit for model training. The tasks that require high-performance calculations are handed over to the GPU host, while the user host only needs to perform simple image processing and use the model trained by the GPU host to generate images. This arrangement reduces the computer specification requirements for the user. This paper will conduct a comparative analysis of various types of generative networks which will serve as a reference point for the development of the proposed Generative Adversarial Network. The application part of the paper focuses on the practical implementation and utilization of the developed Generative Adversarial Network for the generation of multi-skin tone portraits. By constructing a face dataset specifically designed to incorporate information about ethnicity and skin color, this approach can overcome a limitation associated with traditional generation networks, which typically generate only a single skin color. [ABSTRACT FROM AUTHOR]

Generative Adversarial Networks (GANs) are a type of deep learning architecture that uses two networks namely a generator and a discriminator that, by competing against each other, pursue to create realistic but previously unseen samples. They have become a popular research topic in recent years, particularly for image processing and synthesis, leading to many advances and applications in various fields. With the profusion of published works and interest from professionals of different areas, surveys on GANs are necessary, mainly for those who aim starting on this topic. In this work, we cover the basics and notable architectures of GANs, focusing on their applications in image generation. We also discuss how the challenges to be addressed in GANs architectures have been faced, such as mode coverage, stability, convergence, and evaluating image quality using metrics. [Display omitted] • A review on GANs for image generation, aiming at readers who are new to the area. • A comprehensive overview of GAN fundamentals, and methods to address the most common issues. • A detailed explanation of how various works applied GANs in image-based applications. • A discussion of future directions for this area. [ABSTRACT FROM AUTHOR]

We propose a novel method for generating gradually varying weathering effects from a single image. Time-variant weathering effects tend to appear simultaneously on one object. Compared to previous methods, our method is able to obtain gradually changing weathering effects through simple interactions while keeping texture variations and shading details. We first classify the weathering regions into several stages based on a weathering degree map extracted from the image. For each weathering stage, we automatically extract the corresponding weathering sample, from which a texture image is synthesized subsequently. Then, we generate weathering effects by fusing different textures according to the weathering degree of the image pixels. Finally, in order to maintain the intrinsic shape details of the object during the fusing process, we utilize a new shading-preserving method taking account of the weathering degrees. Experiments show that our method is able to produce visually realistic and time-variant weathering effects interactively. [ABSTRACT FROM AUTHOR]

Image as a medium of visual information transmission have the advantages of vividness, intuition and easy understanding. They play an important role in information transmission and utilization. In recent years, due to the rapid development of deep learning technology in the field of image processing, image generative model based on neural network has become one of the current research hotspots. In the field of deep learning, unsupervised learning model has received more and more attentions, especially in the field of deep generative models, which has made breakthrough progress [1]. Among them, Variational Auto-Encoder (VAE), Generative Adversarial Network (GAN), and Diffusion Model are the three most representative research methods in the field of unsupervised learning. They have been applied more and more in the field of deep generative models. Especially, the high-quality image generative models based on the generative adversarial network continue to be hot. The diffusion model is a rising star, which is favored by more and more researchers. This paper first summarizes the main research work, improvement mechanism and features of image generation methods based on VAE and GAN, then introduces the principle of the rising diffusion model and its representative models. Finally, the advantages and limitations of the above methods are compared and analyzed, and prospects for future research are put forward. [ABSTRACT FROM AUTHOR]

In CycleGAN, an image-to-image translation architecture was established without the use of paired datasets by employing both adversarial and cycle consistency loss. The success of CycleGAN was followed by numerous studies that proposed new translation models. For example, StarGAN works as a multi-domain translation model based on a single generator–discriminator pair, while U-GAT-IT aims to close the large face-to-anime translation gap by adapting its original normalization to the process. However, constructing robust and conditional translation models requires tradeoffs when the computational costs of training on graphic processing units (GPUs) are considered. This is because, if designers attempt to implement conditional models with complex convolutional neural network (CNN) layers and normalization functions, the GPUs will need to secure large amounts of memory when the model begins training. This study aims to resolve this tradeoff issue via the development of Multi-CartoonGAN, which is an improved CartoonGAN architecture that can output conditional translated images and adapt to large feature gap translations between the source and target domains. To accomplish this, Multi-CartoonGAN reduces the computational cost by using a pretrained VGGNet to calculate the consistency loss instead of reusing the generator. Additionally, we report on the development of the conditional adaptive layer-instance normalization (CAdaLIN) process for use with our model to make it robust to unique feature translations. We performed extensive experiments using Multi-CartoonGAN to translate real-world face images into three different artistic styles: portrait, anime, and caricature. An analysis of the visualized translated images and GPU computation comparison shows that our model is capable of performing translations with unique style features that follow the conditional inputs and at a reduced GPU computational cost during training.

Generative adversarial networks (GAN) has become a popular research direction in the field of deep learning. The unique adversarial idea of GAN comes from the two-player zero-sum game in game theory. How to solve the problems of unstable GAN training, poor quality of generated samples, inadequate evaluation system, poor interpretability and other issues is critical and difficult in current GAN research. This paper investigates the research background and development trend of GAN. First, the basic idea and algorithm implementation of GAN are described, the advantages and disadvantages of GAN are analyzed, a more systematic classification of existing improved methods is made, and some typical optimization methods and derivative models of GAN are sorted out from two categories based on structure change and loss function variants respectively. Next, the similarities and differences between GAN and other generative models are compared, and their respective advantages and disadvantages are introduced. Then, this paper compares the performance of GAN and its derivative models, and summarizes their operation mechanism, advantages, limitations and applicable scenarios. The applications of GAN in the field of image generation are introduced. Finally, the mainstream evaluation indicators of GAN are listed, the main problems still faced in GAN research are analyzed and corresponding solutions are given. The listed mainstream solutions are compared and analyzed in terms of solution effects and applicability, and the future research direction is prospected.

In CycleGAN, an image-to-image translation architecture was established without the use of paired datasets by employing both adversarial and cycle consistency loss. The success of CycleGAN was followed by numerous studies that proposed new translation models. For example, StarGAN works as a multi-domain translation model based on a single generator–discriminator pair, while U-GAT-IT aims to close the large face-to-anime translation gap by adapting its original normalization to the process. However, constructing robust and conditional translation models requires tradeoffs when the computational costs of training on graphic processing units (GPUs) are considered. This is because, if designers attempt to implement conditional models with complex convolutional neural network (CNN) layers and normalization functions, the GPUs will need to secure large amounts of memory when the model begins training. This study aims to resolve this tradeoff issue via the development of Multi-CartoonGAN, which is an improved CartoonGAN architecture that can output conditional translated images and adapt to large feature gap translations between the source and target domains. To accomplish this, Multi-CartoonGAN reduces the computational cost by using a pretrained VGGNet to calculate the consistency loss instead of reusing the generator. Additionally, we report on the development of the conditional adaptive layer-instance normalization (CAdaLIN) process for use with our model to make it robust to unique feature translations. We performed extensive experiments using Multi-CartoonGAN to translate real-world face images into three different artistic styles: portrait, anime, and caricature. An analysis of the visualized translated images and GPU computation comparison shows that our model is capable of performing translations with unique style features that follow the conditional inputs and at a reduced GPU computational cost during training. [ABSTRACT FROM AUTHOR]

We present a variational autoencoder (VAE) learning framework with introspective training for conditional image synthesis, and explore conditional capsule encoder by class-wise mask label insertion for this framework. Our model only consists of encoder (E), generator (G) and classifier (C), where E and G can be adversarially optimized, and C helps to boost conditional generation, improve authenticity and provide generation measures for E and G. Discriminator is not necessary in our framework and its absence makes our model more concise with fewer artifacts and pattern collapse problems. To compensate for the blurry weakness of VAE-like models, feature matching is introduced into loss functions by means of C to offer more reasonable measures between real and synthesized images. Moreover, in consideration of the key role of E in autoencoders as well as the interesting characteristics of capsule structure, conditional capsule encoder is preliminary explored in the image synthesis model. Class labels participate conditional encoding by masking high-level capsules of other categories, and capsule loss for the encoder is added to facilitate conditional synthesis. Experiments on MNIST and Fashion-MNIST data sets show that our model achieves real conditional synthesis performances with better diversity and fewer artifacts. And conditional capsule encoder also reveals interesting synthesis effects.

In the research of computer vision, artificial controllability of image synthesis is a significant and challenging task. At present, there are two available methods. One is to utilize a simple contour to determine the shape of the synthetic object. This method has a promising effect, but it can only control the shape information of the synthetic object, but not the specific content. The other is to employ the text description to synthesize the corresponding image, which effectively controls the specific content of the synthesis, but it cannot do anything for the synthesized shape. In this paper, we propose a highly flexible and human customizable image synthesis model based on simple contour and natural language description, in which the specific content of contour and text description can be determined artificially. The contour determines basic synthetic object shape, and the natural language describes specific object content. Based on these, highly authentic and customizable images can be synthesized. The experiments are executed in the Caltech-UCSD Birds (CUB) and Oxford-102 flower datasets, and the experimental results demonstrate the effectiveness and superiority of our method. The results not only maintain the contour but also conform to the natural language description. Simultaneously, the high-quality image synthesis results, based on artificial hand-drawing contour and text description, are displayed to illustrate the high flexibility and customizability of our model.

Real-world images usually contain multiple objects, as a result, generating an image from a multi-instance sketch is an attractive research topic. However, existing generative networks usually produce a similar texture on different instances for those methods focus on learning the distribution of the whole image. To address this problem, we propose a progressive instance texture reserved generative approach to generate more convincible images by decoupling the generation of the instances and the whole image. Specifically, we create an instance generator to synthesize the primitive color distribution and the detailed texture for each instance. Then, an image generator is designed to combine all of these instances to synthesize an image retaining texture and color. Besides, to generate more significant details, such as eyes, ears, and so on, we propose a novel technique called discriminative sketch augmentation, which can provide structural constraint by obtaining the sketch of the discriminative region. The extensive experiments demonstrate that our model not only generates convincing images but also achieves higher inception score and lower Fréchet Inception Distance on the MS-COCO dataset.

Generating realistic images with the guidance of reference images and human poses is challenging. Despite the success of previous works on synthesizing person images in the iconic views, no efforts are made towards the task of pose-guided image synthesis in the non-iconic views. Particularly, we find that previous models cannot handle such a complex task, where the person images are captured in the non-iconic views by commercially-available digital cameras. To this end, we propose a new framework – Multi-branch Refinement Network (MR-Net), which utilizes several visual cues, including target person poses, foreground person body and scene images parsed. Furthermore, a novel Region of Interest (RoI) perceptual loss is proposed to optimize the MR-Net. Extensive experiments on two non-iconic datasets, Penn Action and BBC-Pose, as well as an iconic dataset – Market-1501, show the efficacy of the proposed model that can tackle the problem of pose-guided person image generation from the non-iconic views. The data, models, and codes are downloadable from https://github.com/loadder/MR-Net. [ABSTRACT FROM AUTHOR]

We introduce BSD-GAN, a novel multi-branch and scale-disentangled training method which enables unconditional Generative Adversarial Networks (GANs) to learn image representations at multiple scales, benefiting a wide range of generation and editing tasks. The key feature of BSD-GAN is that it is trained in multiple branches, progressively covering both the breadth and depth of the network, as resolutions of the training images increase to reveal finer-scale features. Specifically, each noise vector, as input to the generator network of BSD-GAN, is deliberately split into several sub-vectors, each corresponding to, and is trained to learn, image representations at a particular scale. During training, we progressively “de-freeze” the sub-vectors, one at a time, as a new set of higher-resolution images is employed for training and more network layers are added. A consequence of such an explicit sub-vector designation is that we can directly manipulate and even combine latent (sub-vector) codes which model different feature scales. Extensive experiments demonstrate the effectiveness of our training method in scale-disentangled learning of image representations and synthesis of novel image contents, without any extra labels and without compromising quality of the synthesized high-resolution images. We further demonstrate several image generation and manipulation applications enabled or improved by BSD-GAN. [ABSTRACT FROM AUTHOR]

Style transfer is a task of migrating a style from one image to another. Recently, Full Convolutional Network (FCN) is adopted to create stylized images and make it possible to perform style transfer in real-time on advanced GPUs. However, problems are still existing in memory usage and time-consumption when processing high-resolution images. In this work, we analyze the architecture of the style transfer network and divide it into three parts: feature extraction, style transfer, and image reconstruction. And a novel way is proposed to accelerate the style transfer operation and reduce the memory usage at run-time by conducting the super-resolution style transfer network (SRSTN), which can generate super-resolution stylized images. Compared with other style transfer networks, SRSTN can produce competitive quality resulting images with a faster speed as well as less memory usage. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GANs) have been widely used for the image-to-image translation task. While these models rely heavily on the labeled image pairs, recently some GAN variants have been proposed to tackle the unpaired image translation task. These models exploited supervision at the domain level with a reconstruction process for unpaired image translation. On the other hand, parallel works have shown that leveraging perceptual loss functions based on high-level deep features could enhance the generated image quality. Nevertheless, as these GAN-based models either depended on the pretrained deep network structure or relied on the labeled image pairs, they could not be directly applied to the unpaired image translation task. Moreover, despite the improvement of the introduced perceptual losses from deep neural networks, few researchers have explored the possibility of improving the generated image quality from classical image quality measures. To tackle the above two challenges, in this paper, we propose a unified quality-aware GAN-based framework for unpaired image-to-image translation, where a quality-aware loss is explicitly incorporated by comparing each source image and the reconstructed image at the domain level. Specifically, we design two detailed implementations of the quality loss. The first method is based on a classical image quality assessment measure by defining a classical quality-aware loss to ensure similar quality score between an original image and the reconstructed image at the domain level. The second method proposes an adaptive deep network based loss that compares the high level content structure between each original image and its reconstructed image from the generator. Finally, extensive experimental results on many real-world datasets clearly show the quality improvement of our proposed framework, and the superiority of leveraging classical image quality measures for unpaired image translation compared to the deep network based model. [ABSTRACT FROM AUTHOR]

The development, benchmarking and validation of aerial Persistent Surveillance (PS) algorithms requires access to specialist Wide Area Aerial Surveillance (WAAS) datasets. Such datasets are difficult to obtain and are often extremely large both in spatial resolution and temporal duration. This paper outlines an approach to the simulation of complex urban environments and demonstrates the viability of using this approach for the generation of simulated sensor data, corresponding to the use of wide area imaging systems for surveillance and reconnaissance applications. This provides a cost-effective method to generate datasets for vehicle tracking algorithms and anomaly detection methods. The system fuses the Simulation of Urban Mobility (SUMO) traffic simulator with a MATLAB controller and an image generator to create scenes containing uninterrupted door-to-door journeys across large areas of the urban environment. This ‘pattern-of-life’ approach provides three-dimensional visual information with natural movement and traffic flows. This can then be used to provide simulated sensor measurements (e.g. visual band and infrared video imagery) and automatic access to ground-truth data for the evaluation of multi-target tracking systems. [ABSTRACT FROM AUTHOR]

In this paper, we proposed stereoscopic image generation methods of adjusting the depth value of edge pixels and improved hole filling procedures. For the conventional system, the smooth of depth map can reduce the incidence of image holes, but cause geometric distortions of the image depth. To solve the problems, the depth map is first expanded to refine the accuracy of image depth and the quality of images. Next, we derive a hardware-oriented method for 3D warping. Finally, appropriate blocks are searched to enhance the performance of image by improving hole-filling procedures. The experimental results demonstrate the proposed methods have great performance and practicability. [ABSTRACT FROM AUTHOR]

Taking advantage of the statistical learning-based point of view, several approaches of frontal face image synthesis have received remarkable achievement. However, the existing methods mainly utilize either ordinary least squares (OLS) or fixed l1-norm penalized sparse regression to estimate the solution. For the former, the solution is unstable when the linear equations system is ill-conditioned. For the latter, sparsity is only considered, while the significance of local similarity between input image and each training sample is ignored. Thus the synthesized result fails to faithfully approximate the ground truth. Moreover, these traditional methods cannot ensure the consistency between corresponding patches in frontal and profile faces. To address these problems, we present a unified regularization framework (URF) by imposing two regularization terms onto the solution. Firstly, we introduce an l2-norm constraint and impose a diagonal weights matrix onto it, in which each diagonal entry is defined by the spatial distance between input image patch and individual patch in training set. Secondly, to mitigate the aforementioned inconsistency problem, we present a neighborhood consistency regularization term, motivated by manifold learning. Finally, we generalize our framework to the lq-norm penalized case. By adjusting the shrinkage parameter q, the framework gets more flexibility to choose a reasonable sparse domain. Extensive experiments on CMU Multi-PIE database and CAS-PEAL-R1 database verify the efficacy of our method. [ABSTRACT FROM AUTHOR]

Message hiding in texture image synthesis is a novel steganography approach by which we resample a smaller texture image and synthesize a new texture image with a similar local appearance and an arbitrary size. However, the mirror operation over the image boundary is flawed and is easy to attack. We propose an attacking method on this steganography, which can not only detect the stego-images but can also extract the hidden messages. [ABSTRACT FROM AUTHOR]

We propose a ghost-free high dynamic range (HDR) image synthesis algorithm using a low-rank matrix completion framework, which we call RM-HDR. Based on the assumption that irradiance maps are linearly related to low dynamic range (LDR) image exposures, we formulate ghost region detection as a rank minimization problem. We incorporate constraints on moving objects, i.e., sparsity, connectivity, and priors on under- and over-exposed regions into the framework. Experiments on real image collections show that the RM-HDR can often provide significant gains in synthesized HDR image quality over state-of-the-art approaches. Additionally, a complexity analysis is performed which reveals computational merits of RM-HDR over recent advances in deghosting for HDR. [ABSTRACT FROM AUTHOR]

This paper presents a proposal of a music image generator for users to grasp music easily and instantaneously on consumer electronics devices such as music players and smartphones. It provides users faster and more efficient music browsing functionality using a technique that automatically generates a music image that matches lyric contents. More specifically, a scene theme such as an event or place is extracted from lyrics using text mining techniques. A suitable music image is then created dynamically to match this extracted scene theme. This image generation is achieved by synthesizing multiple image materials to express the extracted scene theme flexibly. For choosing image materials, scene knowledge that has representative scene object compositions is proposed. Using this knowledge, the image synthesizer can select appropriate materials. Finally, the performance of the proposed automatic knowledge creation method is evaluated by comparison with manually created knowledge. Based on optimal parameters calculated in the evaluation, some examples of music images for well-known music lyrics are presented. In addition, the implemented system applying the proposed generator onto a server-side and a consumer-side consumer electronics device is also described [ABSTRACT FROM PUBLISHER]

Abstract: A classical image processing problem is converting color images to gray. This paper presents a Virtual Luminance Axis (VLA) to provide users a friendly interface to control the conversion process. The user selects several interesting color regions by drawing a few brush strokes, and then tunes the maximum and minimum of the corresponding band for each kind of color on the VLA. Our algorithm derives global mapping of the color space onto the VLA as close as possible. In this way, the user can “tune” the resulting image to produce the ideal effects he desires. Quantization and interpolating techniques are employed to accelerate the computation. The experiments show that the final gray is transferred as user defines. [Copyright &y& Elsevier]

Abstract: Databases of human iris images are created and distributed for the purposes of testing iris identification algorithms. For logistical and privacy reasons, these databases are often too small to fulfill their potential applications. In this work we develop a novel multiresolution approach to augment iris image databases. First, using a multiresolution obtained from reverse subdivision we decompose the example iris images into a set of lower resolution components. The components are a complete representation of the original image and consist of a low resolution approximation and a set of characteristics. To generate synthetic iris images we combine a set of components chosen from the original images. To ensure a unique, yet realistic, iris image each component of a synthetic image is chosen from different iris images. We quantitatively validate our approach by employing a classical iris recognition algorithm to compare our synthetic images with those that were used to create them. The results demonstrate that our approach is effective at augmenting iris image databases with iris images that are unique, yet exhibit both visually and statistically realistic characteristics. [ABSTRACT FROM AUTHOR]

The goal of a remote-sensing system is to gather data about the geography it is imaging. In order to gain knowledge of the Earth's landscape, analysts develop postprocessing algorithms to extract information from the collected data. The algorithms are designed for a variety of application areas such as the following: the classification of various ground covers in a scene, the identification of specific targets of interest, or the detection of anomalies in an image. Traditional algorithm testing uses sets of extensively ground-truthed test images. However, the lack of well-characterized test data sets, as well as the significant cost and time issues associated with assembling the data sets, contributes to the limitations of this approach. This paper uses a synthetic-image-generation model in cooperation with a factorialdesigned experiment to create a family of images with which to rigorously test the performance of hyperspectral algorithms. The factorial-designed experimental approach allowed the joint effects of the sensor's view angle, time of day, atmospheric visibility, and the size of the targets to be studied with respect to algorithm performance. A head-to-head performance comparison of the two tested spectral processing algorithms was also made. Finally, real images are processed using the algorithmic settings employed in the designed experiments to validate the approach. [ABSTRACT FROM AUTHOR]

Video image quality improving technologies produce remarkable achievements as display devices make rapid progress. However, there exist some limitations on intensity representation of display and acquisition devices to reproduce the real world video images. Various contrast enhancement (CE) algorithms have been developed and applied to overcome those limitations but there are many drawbacks such as color information change, loss of the lighting information, and excessive enhancement. This paper proposes a CE algorithm based on high dynamic range (HDR) imaging. First, an input image is determined whether or not it requires CE in a pre-processing step using the proposed auto exposure algorithm. Then, multiple images are generated by applying the intensity mapping function to an input image. At last, an HDR image is constructed with multiple images, in which registration of multiple images is not required. So, the proposed CE algorithm could increase the dynamic range and thus increase the contrast of an input image. The proposed CE method makes use of different intensity information from multiple images, therefore, the performance of the proposed method is better than that of existing CE algorithms. Experiments with three real images show the effectiveness of the proposed CE algorithm. [ABSTRACT FROM AUTHOR]

This paper proposed a method of generating seamless textures by means of a genetic algorithm (GA). When the texture of a large region is built up from textures in regions of finite size, textural discontinuities usually arise at the boundaries between these regions. A seamless texture is one in which such discontinuities do not occur. A fractal method has been proposed for the generation of seamless textures, but in that method it is difficult to predict what seamless texture will be generated. Pattern generation cannot be controlled in such a way that a texture similar to an already generated seamless texture will be produced. In this paper an attempt is made to solve this problem by applying the GA to texture generation, yielding seamless textures that are similar to seamless textures previously generated. This method can also be used to generate multiple seamless textures. By using the proposed method, a texture with a user-selected pattern can be generated from simultaneously displayed seamless textures. In addition, to avoid monotonous behavior due to the arrangement of textures of a single kind, a method of generating seamless textures with the same boundary but with different internal pattern (group texture) is proposed. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(2): 91–99, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.1229 [ABSTRACT FROM AUTHOR]

Last month I celebrated my fourth anniversary of writing Programming on Purpose. I described my evolution from physicist to programmer. It seems only natural to begin my fifth year by […]