The rapid development in imageprocessing technology allows to tackle applications of increasing complexity. For efficient design of application specific systems, design automationtechniques are required. This paper ...
The rapid development in imageprocessing technology allows to tackle applications of increasing complexity. For efficient design of application specific systems, design automationtechniques are required. This paper reports on activities for automated texture classification system design employingnon-linear oriented kernels (NLOK) configured by evolutionary optimization techniques and swarm optimization (PSO). First and second order statistical features of the dominating kernels in automatically adapted regions of interests serve as features for the texture classification. Our approach was tested with benchmark and application data from leather inspection and was found to be viable and competitive in both cases. The optimized feature set was tested versus features computed from gray value co-occurrence matrices (COOC) with non-optimized parameters. The classification rates for NLOK were significantly higher than for COOC (> 75% vs. < 65%) for benchmark data and slightly higher for application data (> 90% vs. < 90%). Regarding the two optimization approaches, PSO outperformed genetic algorithms (GA) in optimization time and in accuracy for the benchmark data and in accuracy for application data. Additionally, the COOC parameters were adapted as well and yielded higher classification rates than without adaptation.
Rapid programming of applications with down-times near zero is a key to automation of small lotsize production. This paper proposes an approach to program by gestures. It combines the visual observation and interpreta...
详细信息
ISBN:
(纸本)0780395050
Rapid programming of applications with down-times near zero is a key to automation of small lotsize production. This paper proposes an approach to program by gestures. It combines the visual observation and interpretation of human activities and gestures, mapping to technical tasks and autonomous execution. Automated planning/generation of the robot motion combined with automated correction of pose deviations (induced from the visual observation) allows an execution which is independent of the observation accuracy. The industrial application: Bores and internal threads play a critical role as integral parts of connections, bearings, engines, hydraulic and pneumatic systems. The increased industrial requirement for high quality components demands 100% surface inspection of bores (here with diameters from 4 to 50 mm) at small lotsizes. Since state-of-the-art automation is limited to high volumes, the main target is to develop a semi-autonomous system for rapid and flexible inspection featuring new programming. The main focus is on rapid and intuitive programming of robotic systems. The paper will describe the implementation and techniques in case of a bore inspection system.
Intelligent imageprocessing blurs the distinction between Guidance Vision for Robots (GVR) and Automated Visual inspection (AVI) applications. The paper presents AI techniques for interactive learning of scene-object...
详细信息
This paper aims at investigating a novel solution to the problem of defect detection from textile images using the Discrete Wavelet Transform (DWT) Analysis, involving multiple wavelet bases, and the Support Vector Ma...
详细信息
Intelligent imageprocessing blurs the distinction between Guidance Vision for Robots (GVR) and Automated Visual inspection (AVI) applications. The paper presents AI techniques for interactive learning of scene-object...
详细信息
Intelligent imageprocessing blurs the distinction between Guidance Vision for Robots (GVR) and Automated Visual inspection (AVI) applications. The paper presents AI techniques for interactive learning of scene-object models by feature descriptions of part flows. Robot grippers are modelled by fingerprints for ***collision-free part access. The parameters of the vision models are remotely created by a Server application which accepts simultaneous connections over LAN/Internet with multiple Clients – executing on IBM PC robot terminals integrated in flexible, networked manufacturing structures. Experimental results are reported for cluster and pattern construction for part recognition.
The proceedings contain 51 papers from the Conference on Metrology, inspection, and Process Control for Microlithography XIX. The topics discussed include: development of voltage contrast defect inspection technique f...
详细信息
The proceedings contain 51 papers from the Conference on Metrology, inspection, and Process Control for Microlithography XIX. The topics discussed include: development of voltage contrast defect inspection technique for the line monitoring 300mm ULSI hp90 logic contact layer;optical digital profilometry (ODP) feasibility studies for CD control in lithography applications;repair simulation with imageprocessing and artificial intelligence;camera correlation focus: an image-based focussing techniques;advances in hardware, software, and automation for 193nm aerial image measurement systems;and effective control of photomask surface chemical residuals through thermal treatment.
This paper describes a convolution-based approach to the analysis of images containing few texture classes. Segmentation of foreground and background textures, or detection of boundaries between similarly textured obj...
详细信息
This paper describes a convolution-based approach to the analysis of images containing few texture classes. Segmentation of foreground and background textures, or detection of boundaries between similarly textured objects, is demonstrated. The application to industrial inspectionapplications is demonstrated. Near frame-rate performance on low-cost hardware is possible, since only convolution with small kernels is used. A new algorithm to optimize convolution kernels for the required texture analysis task is presented. A key feature of the paper is the industrial readiness of the techniques described.
Smart man machine interfaces turn out to be a By technology for service robots, for automationapplications in industrial environments as well as in future scenarios for applications in space. For either field, the us...
详细信息
ISBN:
(纸本)0819429848
Smart man machine interfaces turn out to be a By technology for service robots, for automationapplications in industrial environments as well as in future scenarios for applications in space. For either field, the use of virtual reality (VR) techniques showed a great potential. At the IRF a virtual reality system was developed and implemented which allows the intuitive control of a multi-robot system and different automation systems under one unified VR framework. As the developed multi-robot system is also employed for space application, the intuitive commanding of inspection and teleoperation sequences is of great interest. In order to facilitate teleoperation and inspection, we make use of several metaphors and a vision system as an intelligent sensor". One major metaphor to be presented in the paper is the,;TV-view into reality", where a TV-set is displayed in the virtual world with images of the real world being mapped onto the screen as textures. The user can move the TV-set in the virtual world and, as the image generating camera is carried by a robot, the camera-viewpoint changes accordingly. Thus the user can explore the physical world "behind" the virtual world, which is ideal for inspection and teleoperation tasks. By means of real world images and with different measurement-services provided by the underlying 3D vision system, the user can thus interactively build up or refine the virtual world according to the physical world he is watching through the TV set.
暂无评论