Computer Graphic and Photographic Image Classification Using Transfer Learning Approach

To investigate the effect on the human visual system of viewing 3-dimensional (3-D) computer graphics (CG) images with an eyeglass-free rear-cross-lenticular-type 3-D display. Positive accommodation velocity (GRAD) during the accommodative step response was measured in ten healthy young adults before and after they viewed CG images. Although the distance between the viewer and the 3-D display was 600 mm, the apparent distance between the viewer and the virtual object was varied (515, 600, and 722 mm) by changing the visual disparity. A significant slowdown of average GRAD was observed by 60 min after a 30-min 3-D viewing of 3-D CG images [P<0.05, analysis of variance (ANOVA)] but not after a 30-min viewing of the CG images on a 2-D display or after a 15-min 3-D viewing. When the virtual object was at 722 mm, a significant slowdown of average GRAD was observed only at 30 min after the 30-min 3-D viewing (P<0.05, ANOVA). When the virtual object was at 515 mm, a significant slowdown of average GRAD was observed at 30 and 60 min after the 3-D viewing (P<0.05, ANOVA). The effect on the human visual system of 3-D viewing of 3-D CG images depends on both the duration of the viewing and the apparent distance between the viewer and the virtual objects.

We develop two different techniques to study volume mapping problem in Computer Graphics and Medical Imaging fields.The first one is to find a harmonic map from a 3 manifold to a 3D solid sphere and the second is a sphere carving algorithm which calculates the simplicial decomposition of volume adapted to surfaces.We derive the 3D harmonic energy equation and it can be easily extended to higher dimensions.We use a textrehedral mesh to represent the volume data.We demonstrate our method on various solid 3D models.We suggest that 3D harmonic mapping of volume can provide a canonical coordinate system for feature identification and registration for computer animation and medical imaging.

We present a method to create animations expressing the movement of volumetric smoke by combine still images of Computer Graphics (CG) with a dynamic luminance information. Volume rendering is one of the rendering methods considering absorption and scattering of light by a medium involved in the air such as smoke. It can express smoke more realistic more than normal rendering, and it takes time to create CG video with smoke. In this research, we express smoke motion of the video created using volume rendering by combining a still image by normal rendering with a brightness kinetic information. We experimented to compare perceptual quality of videos created by proposal method and using volume rendering. We used image quality evaluation index and questionnaire for evaluation of perceptual quality. Experiment results show the proposal method can shorten the creation time and create videos keeping perceptual quality of videos using volume rendering.

This article describes a mathematical method to distinguish computer graphics (CG) from photographic images (PG). Because white balance, CFA and PRNU noise artifacts are the intrinsic properties of optical imaging, we can use these artifacts to reflect camera imaging-specific to some extent. During experiment, we design a 135-D feature set and perform distinguishing process to capture these artifacts. Images selected from relative Columbia University image database are chosen as our experiment database. Experiment result indicates our mathematical method is capable to identify computer generated images from camera produced images with 95.43 % accuracy.

For computer-generated rainbow holograms (CGRHs), it is important to display surface model shaded images like computer graphics (CG). We have proposed a simple process to obtain 3-D data for CGRH from two CG images.

We developed a robot face that can mechanically create facial expressions that actualizes 3D computer graphic morphing techniques, especially around the mouth. Using the mechanism we expect robots to have a wider range of expressions in human-robot communication, not just emotion theory based expressions but expressions that are designed and created. The facial expression mechanism uses multiple control points that moves and traces the surface of the robot's face using combination of trajectories. The movements of control points used here are similar to the transferring vertices that changes expressions of graphical models seen in 3D-CG, therefore actualizes computer graphics. At the end of the paper we evaluate the actualization by overlapping the computer graphic expression images and the actual robot expressions and see the visual closeness of the two expressions.

PREFACECGDIP 2018 was held in Bangkok, Thailand from July 27-29, 2018. CGDIP 2018 was organized by the Asia Pacific Institute of Science and Engineering (APISE). The conference provides a useful and wide platform both to display the latest research and for the exchange of research results and thoughts in Computer Graphics and Digital Image Processing. The participants of the conference were from almost every part of the world, with backgrounds in either academia or industry, even well-known enterprise. The success and prosperity of the conference is reflected in the high level of the papers received.The proceedings are a compilation of the accepted papers and represent an interesting outcome of the conference. This book covers two chapters: 1. Applications & Visualization; 2. Image Processing, Detection and Recognition.We would like to acknowledge all of those who supported CGDIP 2018. Each individual and institutional help were very important for the success of this conference. Especially we would like to thank the organizing committee for their valuable advice in the organization and helpful peer review of the papers.We sincerely hope that CGDIP 2018 will be a forum for excellent discussions that will put forward new ideas and promote collaborative researches. We are sure that the proceedings will serve as an important research source of references and the knowledge, which will lead to not only scientific and engineering progress but also other new products and processes.Prof. Shahram Latifi, University of Nevada, Las Vegas, USA

This article discusses the development of an animated short film in which different rendering techniques were used, in order to compare them and find the best cost/benefit ratio. The short film is 16 minutes long and features scenes with complex landscapes and different types of framing.It is known that the rendering process was, until a few years ago, the most time-consuming process in the production of animations and visual effects scenes. Thus, a great effort has been spent on research to develop hardware and software solutions that perform this activity in an affordable time, maintaining the necessary quality to produce images in the shortest possible time.In the animated short film, V-Ray, Arnold Renderer and Unreal renderers were used in different sequences. Arnold, RenderMan and Unreal renderers were also compared in the same sequence. RenderMan, V-Ray and Arnold are renderers used in post-production and have an extensive portfolio of applications. Unreal opened the possibility of rendering in real time, without loss of quality, with the release of version 4.0 in 2014, and opened new paths for the so-called Virtual Production, by integrating live scenes with animated images in computer graphics, with realism and in real time, a trend that is definitely established with Unreal 5.0, from 2022.In this article, the production and rendering process of the animated short film will be described, and the different strategies adopted by renderers to obtain the finished image will be discussed.

An understanding of light and its interaction with matter is essential to produce images. As the modeling of light sources, light transport and light reflection improves, it becomes possible to render images with increasing realism. The central motivation behind this thesis is to improve realism in computer graphics images by more accurate local shading models and to assist the user to obtain the desired lighting effects with these more complex models. The first part of the thesis addresses the problem of rendering surfaces illuminated by extended (linear and area) light sources. To compute the light reflected by a surface element in a given direction, one needs to determine the unoccluded regions (shadowing) of each light source and then to compute the light reflection (shading) from each of these regions. Traditionally, point light sources are distributed on the lights to approximate both the shadowing and the shading. Instead, an efficient analytical solution is developed for the shading. Shadowing from extended light sources is a fairly expensive process. To give some insights on the complexity of computing shadows, some properties of shadows and algorithms are presented. To reduce the cost of computing shadows from linear light sources, two acceleration schemes, extended from ray tracing, are introduced and evaluated. The second part of this thesis addresses the problem of achieving a desired shading effect by building up systems of constraints. This approach is called inverse shading. It allows a user to obtain a desired lighting effect by interacting directly with the scene model. An interactive modeling system has been built to study the introduction of rendering issues into the modeling process itself. Two rendering aspects are considered: shading and shadows. By specifying a highlight position and size, the unique direction of a directional light source as well as the surface glossiness are determined. Interactively moving this highlight on the surface redefines the light direction while changing its size redefines the surface glossiness. By manipulating shadow volumes (the volume within which a particular light cannot be completely seen), the light source definition and position can be modified. By assigning colours to various points in a 3D scene, information about the colour of a surface as well as other surface characteristics can be deduced. This relatively new concept of defining the causes by manipulating the effects is expected to have a major impact on the design of future computer graphics modeling systems. It begins a new family of tools for the design of more intuitive user interfaces.

To develop new types of surgical flaps that utilize portions of the skin and subcutaneous tissue (e.g., a thin flap or an adipofascial flap), three-dimensional investigation of the vasculature in the skin and subcutaneous tissue has been anticipated. In the present study, total-body arterial injection and three-dimensional imaging of the arteries by computer graphics were performed. The full-thickness skin and subcutaneous adipofascial tissue samples, which were obtained from fresh human cadavers injected with radio-opaque medium, were divided into three distinct layers. Angiograms of each layer were introduced into a personal computer to construct three-dimensional images. On a computer monitor, each artery was shown color-coded according to the three portions: the deep adipofascial layer, superficial adipofascial layer, and dermis. Three-dimensional computerized images of each artery in the skin and subcutaneous tissue revealed the components of each vascular plexus and permitted their classification into six types. The distribution of types in the body correlated with the tissue mobility of each area. Clinically, appreciation of the three-dimensional structure of the arteries allowed the development of several new kinds of flaps.

Comparative analysis of deep convolution neural network models on small scale datasets

The purpose of this volume is to present current work of the Intelligent Computer Graphics community, a community growing up year after year. Indeed, if at the beginning of Computer Graphics the use of Artificial Intelligence techniques was quite unknown, more and more researchers all over the world are nowadays interested in intelligent techniques allowing substantial improvements of traditional Computer Graphics methods. The other main contribution of intelligent techniques in Computer Graphics is to allow invention of completely new methods, often based on automation of a lot of tasks assumed in the past by the user in an imprecise and (human) time consuming manner. This volume contains both invited and selected extended papers from the last 3IA Conference (3IA2008), together with an introduction presenting the area of Intelligent Computer Graphics and various Computer Graphics areas where introduction of intelligent techniques permitted to resolve important problems. We hope that this volume will be interesting for the reader and that it will convince him (her) to use, or to invent, intelligent techniques in Computer Graphics and, maybe, to join the Intelligent Computer Graphics community.

A Cultural History of Computer Graphics presents a fundamentally new approach to analyzing digital images aesthetically through the example of 3D computer graphics (CG). While numerous methods for creating digital imagery have long existed, the advent of AI-generated content is causing a rise in debates and conflict. It is becoming increasingly difficult to aesthetically&nbsp;differentiate digital photographs, CG and AI images, and yet, because these types of images carry different cultural or even political implications, it is becoming increasingly important to do so. In response to the need of new methods to culturally decode digital imagery, this book starts from the production process and describes computer graphics as an independent method of expression, containing a specific ideological concept of realism. Through this study, it becomes clear that a particular understanding of the world is inscribed in computer graphics software and, consequently, the image creation process. As the image surface does not reveal much about these cultural artifacts, it becomes necessary to focuson the historical development of this imaging practice and analyze it production-aesthetically.&nbsp;In its own unique way, this is true for every digital imaging method. Each&nbsp;embodies its own sense of the world that is only accessible through their production aesthetics. This book will be of great interest to researchers of computer graphics, 3D image generation and the cultural history of computer-generated imagery.

Chapter 46 - Image generation by Blaschke products in the unit disk

Geometric methods are widely used in solving functional analysis problems. A large number of tasks described by functional dependencies can be reduced to a geometric formulation. A method of functional voxel modeling based on a linear approximation of the functional dependence under study is considered. The parameters of this approximation are considered as local geometric characteristics of the function under study. The method of functional voxel modeling allows us to calculate local geometric characteristics reflecting the characteristic features of the existing functional dependence and represent them with voxel structures. A graphical image corresponding to a geometric model and reflecting some of its properties based on local geometric characteristics is called a graphical M-image. An original approach for studying the kinematic properties of a 3DOF manipulative robot using computer graphics methods and tools is described. Graphical M-images of functions describing the kinematic properties of a manipulative robot were used to visualize local geometric characteristics. The software module RANOK 2D was used as a means of computer graphics, which allows creating M-images of functions of two variables. The graphical M-images of the functional dependence, which is an analog of the function obtained to calculate the velocity of a point selected at the final link of the kinematic structure of the studied manipulation system, are presented.