This paper describes the architecture of an integrated multi-modal sensory (vision and touch) computational system. We propose to use an approach based on robotics control theory that is motivated by biology and devel...
详细信息
This paper describes the architecture of an integrated multi-modal sensory (vision and touch) computational system. We propose to use an approach based on robotics control theory that is motivated by biology and developmental psychology, in order to integrate the haptic and visual information processing. We show some results carried out in simulation and discuss the implementation of this system using a platform consisting on an articulated stereo-head and an arm, which is currently under development.
The paper presents the foundations of IBAL, a general specification for scene animation. IBAL regulates interactions among graphical elements, such as geometric models and behavioral algorithms, to describe animated s...
详细信息
The paper presents the foundations of IBAL, a general specification for scene animation. IBAL regulates interactions among graphical elements, such as geometric models and behavioral algorithms, to describe animated scenes. Interactions among graphical elements are managed by primitives which are arranged into three graphs. The three graphs logically partition an animation into "who", "what", and "when". IBAL's unique design permits applications to represent, save, and restore a wide variety of complex scenes. A short summary of existing formats for scene modeling and scene animation is presented to distinguish and to assess the utility of IBAL's design.
Boron carbide microscopic images may present grains crossed by twins (or macles) viewed as straight lines in the inner part of each grain. The twins preclude the segmentation because they are very similar to the grain...
详细信息
Boron carbide microscopic images may present grains crossed by twins (or macles) viewed as straight lines in the inner part of each grain. The twins preclude the segmentation because they are very similar to the grain borders. To eliminate the twins a preprocessing step, which relies on mathematical morphology tools, is applied to the image. The main operation used is a directional opening, using structuring elements with several sizes and directions. After this step the image is ready to be segmented.
This paper addresses the problem of automatic synthesis of visual detectors. We present a method using genetic techniques to learn visual features and a program which combines and integrates the features in non-linear...
详细信息
This paper addresses the problem of automatic synthesis of visual detectors. We present a method using genetic techniques to learn visual features and a program which combines and integrates the features in non-linear ways. The method is integrated in a face tracking system to generate a variety of new visual perceptual processes.
We describe an interactive video-on-demand (VoD) service, which supports VCR-like functions. It consists of two parts. The first part is a database, which contains the information concerning the videos. This informati...
详细信息
We describe an interactive video-on-demand (VoD) service, which supports VCR-like functions. It consists of two parts. The first part is a database, which contains the information concerning the videos. This information is published on an Intranet Web. The second part is the actual video distribution using the client server model. The architecture combines network manipulation of high level and a modular system of pluggable components which provides adjustability to the needs of the user.
This paper presents a system for automatic extraction of the user-entered data from brazilian bankchecks. We have assumed that the layout structure of bankchecks is standardized, that any bankcheck can be identified t...
详细信息
This paper presents a system for automatic extraction of the user-entered data from brazilian bankchecks. We have assumed that the layout structure of bankchecks is standardized, that any bankcheck can be identified through the MICR line and that a sample of the background pattern is available for every bankcheck. Based on these assumptions, a template is designed for extracting the user-entered items of any bankcheck, no matter which financial institution has issued it. First, the bankcheck is digitized through a scanner and its skew angle is computed by an algorithm based on the Hough transform. Next a template is generated and used for extracting the user-entered data. The extracted data still shows the presence of the background pattern, character strings, and vertical and horizontal lines. The background pattern is eliminated by a morphological subtraction operation while the baselines are erased using an algorithm based on the projection profiles. The printed character strings are eliminated through a morphological subtraction between the image covered by the signature area and a sample of the character strings generated by the system. Finally, a post-processing algorithm is used for recovering some erased pixels. Experimental results show that this approach is robust and efficient for automatic extracting the user-entered items from brazilian bankchecks achieving a moderate processing time, very good image quality and excellent accuracy rates.
This paper describes a technique developed to analyze and recognize paper based electronic circuit diagram images. One of the key aspects of this recognition system relies on the identification of feature points used ...
详细信息
This paper describes a technique developed to analyze and recognize paper based electronic circuit diagram images. One of the key aspects of this recognition system relies on the identification of feature points used to guide a new line vectorization method developed for circuit diagram images. The feature paints are also used as a discriminate element in the symbol classification process. Once the lines are vectorized, the open symbols are first identified by a syntax-based classifier, followed by the identification of the loop-based symbols using a supervised parametric statistical classifier. We have demonstrated the proposed system by implementing and testing it on various real images of circuit diagrams.
This paper investigates computer vision techniques for three-dimensional reconstruction having as source of information non-professional images captured from cameras of arbitrary position and orientation. The main pur...
详细信息
This paper investigates computer vision techniques for three-dimensional reconstruction having as source of information non-professional images captured from cameras of arbitrary position and orientation. The main purpose is to compose a methodology for 3D reconstruction, aiming specially at its use in the documentation of historic buildings and monuments through their three-dimensional modeling. For being particularly suitable, the technique of shape from stereo is then more closely analysed. Laboratory experiments, with controlled environment and objects are carried out in order to study the influence of some elements in the quality of reconstruction. A practical application with actual photographs of old buildings is presented, and final conclusions are drawn.
Geometric accuracy of a close-range photogrammetric system is assessed in this paper considering surface reconstruction with structured light as its main purpose. The system is based on an off-the-shelf digital camera...
详细信息
Geometric accuracy of a close-range photogrammetric system is assessed in this paper considering surface reconstruction with structured light as its main purpose. The system is based on an off-the-shelf digital camera and a pattern projector. The mathematical model for reconstruction is based on the parametric equation of the projected straight line combined with collinearity equations. A sequential approach for system calibration was developed and is presented. Results obtained from real data are also presented and discussed. Experiments with real data using a prototype have indicated 0.5 mm of accuracy in height determination and 0.2 mm in the XY plane considering an application where the object was 1630 mm distant from the camera.
Computational visualization systems and techniques have improved information gathering activities and changed the ways in which science is studied. However, the complexity of the data handled by such systems has sugge...
详细信息
Computational visualization systems and techniques have improved information gathering activities and changed the ways in which science is studied. However, the complexity of the data handled by such systems has suggested the need for alternative representation and display techniques. Auditory display has been considered to be a real possibility in this area, in a field known as sonification. The paper describes the approach, implementation and results of a prototype for a sonification system to support graphical techniques in visualization applications. Results have shown that there are many possibilities for the inclusion of sound tools in visualization systems, in ways that may ease data interpretation and improve performance in analysis tasks.
暂无评论