184 Result(s)
-
Chapter and Conference Paper
The Synthesis of Realistic Human Face
In this paper, we present new techniques for creating a realistic specific human face based on a general 3D face model and several photos of a human. The morphing technique allows interactive alignment of feat...
-
Chapter and Conference Paper
Detecting Facial Features on Images with Multiple Faces
This paper presents an approach to detect facial features of multiple faces on complex background and with variable poses, illumination conditions, expressions, ages, image sizes, etc. First, the skin parts of...
-
Chapter and Conference Paper
ROI and FOI Algorithms for Wavelet-Based Video Compression
Many techniques make great contributions to video compression with removal of spatial and temporal redundancy in and between frames. However, compressed video is still rather large for applications such as sur...
-
Chapter and Conference Paper
A Hybrid Motion Compensated 3-D Video Coding System for Blocking Artifacts Reduction
We compare, both objectively and subjectively, the performance of various advanced motion compensation methods, including overlapped block motion compensation (OBMC) and control grid interpolation (CGI), in a ...
-
Chapter and Conference Paper
A Hybrid Swipe Fingerprint Mosaicing Scheme
Due to their very small contact areas and low cost, swipe fingerprint sensors provide the very convenient and reliable fingerprint security solutions and are being increasingly used for mobile phones, PDAs, po...
-
Chapter and Conference Paper
PanoWalk: A Remote Image-Based Rendering System for Mobile Devices
Real-time rendering of complex 3D scene on mobile devices is a challenging task. The main reason is that mobile devices have limited computational capabilities and are lack of powerful 3D graphics hardware sup...
-
Chapter and Conference Paper
Semi-supervised Cast Indexing for Feature-Length Films
Cast indexing is a very important application for content-based video browsing and retrieval, since the characters in feature-length films and TV series are always the major focus of interest to the audience. ...
-
Chapter and Conference Paper
Unifying Keywords and Visual Features Within One-Step Search for Web Image Retrieval
The multi-modal characteristics of Web image make it possible to unify keywords and visual features for image retrieval in Web context. Most of the existing methods about the integration of these two features ...
-
Chapter and Conference Paper
A Three-Level Scheme for Real-Time Ball Tracking
A three-level method is proposed to achieve robust and real-time ball tracking in soccer videos. It includes object-, intra-trajectory-, and inter-trajectory-level processing. Due to much noise and frequent oc...
-
Chapter and Conference Paper
Robust Speaking Face Identification for Video Analysis
We investigate the problem of automatically identifying speaking faces for video analysis using only the visual information. Intuitively, mouth should be first accurately located in each face, but this is extr...
-
Chapter and Conference Paper
Multimedia Evidence Fusion for Video Concept Detection via OWA Operator
We present a novel multi-modal evidence fusion method for highlevel feature (HLF) detection in videos. The uni-modal features, such as color histogram, transcript texts, etc, tend to capture different aspects ...
-
Chapter and Conference Paper
Graph-Based Pairwise Learning to Rank for Video Search
Learning-based ranking is a promising approach to a variety of search tasks, which is aimed at automatically creating the ranking model based on training samples and machine learning techniques. However, the p...
-
Chapter and Conference Paper
3D Digitization and Its Applications in Cultural Heritage
3D digitizing technology has a variety of applications including reverse engineering, quality control, virtual reality and digital heritage. Recently, great development in 3D digitizing technology facilitates ...
-
Chapter and Conference Paper
Topological Design of Weakly-Coupled 3-Translation Parallel Robots Based on Hybrid-Chain Limbs
This paper presented a novel and systematic design method for topological structure of weakly-coupled parallel robots with three pure translations by using hybrid chains. First, the general design steps for hy...
-
Chapter and Conference Paper
Five-Axis Milling Simulation Based on B-rep Model
Formulating the swept volume by a cutter along its path plays an important role in volumetric simulation of five-axis machining. In some cases, the swept volume may experience self-intersection, which is a cru...
-
Chapter and Conference Paper
Experimental Studies of Visual Models in Automatic Image Annotation
Semantic image annotation can be viewed as a map** procedure from image features to semantic labels, by the steps of image feature extraction and image-semantic map**. The features can be low-level visual ...
-
Chapter and Conference Paper
Segmentation Based Tone-Map** for High Dynamic Range Images
In this paper, we present a novel segmentation based method for displaying high dynamic range image. We segment images into regions and then carry out adaptive contrast and brightness adjustment using global t...
-
Chapter and Conference Paper
Blind Detection of Copy-Move Forgery Based on Multi-Scale Autoconvolution Invariants
With regard to the Copy-Move forgery of image region, this paper proposes one blind detection algorithm based on Multi-Scale Autoconvolution. The eigenvectors of image are generated by extracting the MSA invar...
-
Chapter and Conference Paper
Exploring the Role of Perceived Interactivity in Establishing Behavioral Intention in Micro-blog Environments
The growing prevalence of the Web2.0 is promoting micro-blog as one of the most promising innovations in the past few years. This study develops a model aims at investigating the effects of perceived interacti...
-
Chapter and Conference Paper
Kernel L1 Graph for Image Analysis
Graph costructing plays an essential role in graph based learning algorithms. Recently, a new kind of graph called L1 graph which was motivated by that each datum can be represented as a sparse combination of ...