In order to develop applications for visual interpretation of medical images, the early detection and evaluation of microcalcifications in digital mammograms is very important since their presence is often associated ...
详细信息
In order to develop applications for visual interpretation of medical images, the early detection and evaluation of microcalcifications in digital mammograms is very important since their presence is often associated with a high incidence of breast cancers. Accurate classification into benign and malignant groups would help improve diagnostic sensitivity as well as reduce the number of unnecessary biopsies. The challenge here is the selection of the useful features to distinguish benign from malignant micro calcifications. Our purpose in this work is to analyse a microcalcification evaluation method based on a set of shape-based features extracted from the digitised mammography. The segmentation of the microcalcifications is performed using a fixed-tolerance region growing method to extract boundaries of calcifications with manually selected seed pixels. Taking into account that shapes and sizes of clustered microcalcifications have been associated with a high risk of carcinoma based on different subjective measures, such as whether or not the calcifications are irregular, linear, vermiform, branched, rounded or ring like, our efforts were addressed to obtain a feature set related to the shape. The identification of the parameters concerning the malignant character of the microcalcifications was performed on a set of 146 mammograms with their real diagnosis known in advance from biopsies. This allowed identifying the following shape-based parameters as the relevant ones: Number of clusters, Number of holes, Area, Feret elongation, Roughness, and Elongation. Further experiments on a set of 70 new mammograms showed that the performance of the classification scheme is close to the mean performance of three expert radiologists, which allows to consider the proposed method for assisting the diagnosis and encourages to continue the investigation in the sense of adding new features not only related to the shape.
The proceedings contains 12 papers from the ieecolloquium on Underwater Applications of Image Processing. Topics discussed include: sidescan sonar survey data analysis;underwater robotics navigation using multisensor...
详细信息
The proceedings contains 12 papers from the ieecolloquium on Underwater Applications of Image Processing. Topics discussed include: sidescan sonar survey data analysis;underwater robotics navigation using multisensor fusion;behaviors implemented using a vision system based on coded light projection;broadband underwater acoustic communications systems;wide-band high-resolution sonar techniques;autonomous underwater vehicles as imaging platforms;automated acoustic data collection experiments using a directional projector system;uncalibrated computervision techniques in the underwater environment;and underwater measurement of salmon biomass.
Minimally Invasive Surgery is a relative term. Anything that can reduce the trauma of entry and access to the site of the procedure will be of great benefit. Robots have a considerable part to play in this. Because th...
详细信息
Minimally Invasive Surgery is a relative term. Anything that can reduce the trauma of entry and access to the site of the procedure will be of great benefit. Robots have a considerable part to play in this. Because they can carry out precise motions along predetermined trajectories to achieve very accurate positions, the entry wound can be made minimal. Robots can also accurately carry out repetitive motions and do not require good vision to avoid getting 'lost' inside a cavity. All these aspects give robots a considerable potential in minimally invasive surgery. The term robot in this regard is generally used loosely to include not only externally powered reprogrammable manipulating devices but also computer assisted devices. The latter may be passive arms, held by the surgeon, which are used to point at targets displayed on a computer screen. They may also include sensors attached to tools to keep track of the tool relative to a target.
This paper summarizes the use of 3 types of optical system which measure 3D robot movement and position. The principal objective has been the calibration of industrial robots as part of an ESPRIT research project, CAR...
详细信息
This paper summarizes the use of 3 types of optical system which measure 3D robot movement and position. The principal objective has been the calibration of industrial robots as part of an ESPRIT research project, CAR 5220. This project aims at improving the absolute static positional capability of industrial robots from greater than l0 millimetres (approx.) to better than 1 millimetre, which is the typical level of repeatability.< >
robotics is the most powerful tool available to ensure the success of modern manufacturing industry in Europe. The requirement for education and training in the area of robotics led to the choice of name for a new cou...
详细信息
robotics is the most powerful tool available to ensure the success of modern manufacturing industry in Europe. The requirement for education and training in the area of robotics led to the choice of name for a new course at Portsmouth Polytechnic; Automation and robotics. The course consists of both practical and theoretical work. The practical work is in three parts, beginning with basic control techniques. The other two parts are an investigation into the use of sensors and transducers in a flexible manufacturing environment (especially vision systems) and path and trajectory planning and the control of industrial robots.< >
Presents a new paradigm in the field of Multi-Agents Worlds. The coordination patterns (the PACO project), in which the concepts of autonomous agents, multi agent systems, emergent functionality and complex dynamics m...
详细信息
Presents a new paradigm in the field of Multi-Agents Worlds. The coordination patterns (the PACO project), in which the concepts of autonomous agents, multi agent systems, emergent functionality and complex dynamics meet. The originality of the approach is mainly due to the definition and the control of a perception scope and of a communication scope that guide the interaction between agent themselves and between the agents and the environment. The second originality of the approach is the explicitation of a decision filter that experimentally enables the entire system to faster stabilize into an equilibrium. This research has been initialized at LIFIA and then enhanced at VUB/AI-Lab, both through image analysis studies. From the beginning, however, several applications in different fields were envisioned. The author is applying the coordination patterns to the path-planning and the execution control problems in robotics, when spatially taking into account the temporal constraints.< >
Tactile sensors determine various aspects of the environment through direct contact with objects within that environment. Such sensors can be used to ascertain the distribution of forces over an area, and can also be ...
详细信息
Tactile sensors determine various aspects of the environment through direct contact with objects within that environment. Such sensors can be used to ascertain the distribution of forces over an area, and can also be used to sense shape parameters, location, and orientation of objects touching the sensor. The simplest form of tactile sensor consists of a single touch probe, but effort has also been put into developing sensors that consist of an orthogonal grid, or array, of sensing elements. Each element is known as a tactel, a term derived from 'tactile element'. Such sensors produce as output a digital image that can be input to a conventional image processing system, as might be used for analysing images from a vision camera. The paper describes the operation of a very high resolution tactile sensor array; it is able to detect detailed surface variations which are beyond the capabilities of most other tactile sensors. Some aspects of tactile sensing compared to those of vision are also discussed.< >
Progress in providing the Oxford Autonomous Guided Vehicle (AGV) with computervision capabilities is described. The GEC Turtle vehicle is the basis for a sensor integration project in which vision plays the strategic...
详细信息
Progress in providing the Oxford Autonomous Guided Vehicle (AGV) with computervision capabilities is described. The GEC Turtle vehicle is the basis for a sensor integration project in which vision plays the strategic role of locating pallets in an unstructured environment. In other projects, the aim is visual servocontrol of the vehicle. Early visual processing using a Sun/Datacube architecture is sketched. Model-based recognition of palletised loads is discussed. Finally, work on the development of parallel vision algorithms is reviewed.< >
暂无评论