Differences between revisions 2 and 3
Revision 2 as of 2011-11-16 14:08:59
Size: 8726
Editor: WebMaster
Revision 3 as of 2011-11-17 13:09:28
Size: 8726
Editor: WebMaster
Deletions are marked like this. Additions are marked like this.
Line 1: Line 1:
<<Include(MVG/HeaderMVGResearch)>> <<Include(CMV/HeaderCMVResearch)>>

Research at the Center for Machine Vision Research

Our research areas range from generic computer vision methodologies to machine vision applications and vision systems engineering.

The main areas of our research are:

  • Computer vision methods
  • Human-centered vision systems
  • Vision systems engineering

Local Binary Patterns
The LBP methodology has led to significant progress in texture analysis. Due to its discriminative power and computational simplicity, the method has been highly successful in many such computer vision problems which were not earlier even regarded as texture problems, such as face analysis and motion analysis. More...

New Texture Descriptors
In our research we have investigated different approaches for characterizing local properties of image textures. Besides LBP we have also proposed other operators such as the blur insensitive local phase quantization (LPQ) and the Weber's law descriptor (WLD). More...

Computational Imaging

In computational imaging the objective is to create images that cannot be produced by conventional cameras. This is achieved by integrating a computer to a camera, which enables more enhanced features to be used in acquisition and processing of the images. More...

Object Detection and Recognition
Object recognition and detection refer to the tasks of classifying and localizing a given object from an image or video sequence. For example, one can search for bounding boxes of persons or face in the given image. Our research in this topic focuses particularly on detecting humans and generic object classes. More...

Geometric Computer Vision
Geometry is an important aspect of computer vision. The laws of geometry and optics describe how the three-dimensional world is imaged on the camera sensor and, hence, an understanding of imaging geometry is important for the development of automatic image analysis methods. More...

Face Recognition and Biometrics
MVG have a long experience and renowned expertise in investigating face related problems since 1997. For instance, our LBP-based face description has been widely adopted by many research groups around the world. More...

Recognition of Facial Expressions and Emotions
A goal of this research is to determine the emotional state from facial expressions using dynamic information analysis. Other modalities will also be used to supplement facial expressions for reliable emotion recognition. More...

Action and Gesture Recognition
Texture based methods are investigated for describing actions and gestures. Static texture operators with temporal template and dynamic texture operators are utilized to represent motion. More...

Image and Video Synthesis
Research on image and video synthesis has a wide variety of potential applications, for example in implementing an avatar (i.e. talking head) for affective human-computer interaction. More...

Tracking and Recognition in Camera Networks
Detect and track moving objects in each view of a camera network and maintain their identities while moving across the views. More...

Camera-Based Interfaces for Mobile Devices
Multiple built-in cameras and the small size of hand-held devices are under-exploited assets for creating novel user interfaces and applications. Studies into alternatives to mobile user interaction have, therefore, become a very active research area in recent years. More...

Affective Human-Robot Interaction
A robot should provide personalized services to different human users and even recognize emotion of the user to allow affective interaction. More...

Visual Inspection
The goal of our work is to find and identify approaches, architectures, and algorithms that enable building useful machine vision systems for industrial applications. More...

Energy Efficient Architectures and Signal Processing
Our research on energy efficiency considers both the software and hardware aspects of signal processing systems, while paying attention to the interface between as well. A long term goal is to develop a complete toolchain that enables designers to instantiate energy-efficient signal processing systems out of high-level specifications. More...

CMV/Research (last edited 2011-11-19 14:09:14 by WebMaster)