PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Computer vision”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,315 records · Page 73Linked to original sources
PubMed1991

A statistical analysis of natural images matches psychophysically derived orientation tuning curves.

A neural net method is used to extract principal components from real-world images. The initial components are a Gaussian followed by horizontal and vertical operators, starting with the first derivative and moving to successively higher orders. Two of the components are 'bar-detectors'. Their measured orientation selectivity is similar to that suggested by Foster & Ward (Proc. R. Soc. Lond. B 243, 75 (1991] to account for brief-exposure psychophysical data. In tests with noise images, the ratio of sensitivity between the two components is controlled by the degree of anisotropy in the image.

Humans↗
PubMed2001

Specified-resolution wavelet analysis of activation patterns from BOLD contrast fMRI.

Functional magnetic resonance (MR) MR imaging (fMRI) with blood-oxygenation-level-dependent (BOLD) contrast localizes neuronal processing of cognitive paradigms. As magnetic resonance signal responses are small, functional mapping requires statistical analysis of temporally averaged image data. Although voxels activating at the paradigm frequency can be identified from the Fourier power spectrum, such analyses collapse the temporal information that is useful to establish consistency of responses during the paradigm. The design of a set of nonorthogonal wavelets of specified frequency resolution within the power spectrum was investigated for extracting desired frequency responses from the noisy signal intensity of individual voxels. These wavelets separate the low-frequency cognitive response to the paradigm from the respiratory and cardiac responses at higher frequencies. The retention of the temporal information, possible by wavelet analysis, allows the MR signal changes to be compared to changes in behavioral responses over the duration of an entire paradigm. The amplitude and time delay of the wavelet specified by the paradigm identify quantitatively the size of the MR signal change and the temporal delay of the hemodynamic BOLD response, respectively. This specified-resolution wavelet analysis was demonstrated for individual voxels and maps through the frontal eye fields using a visually guided saccade paradigm.

Adult↗
PubMed1998

A microfabricated electrostatic haptic display for persons with visual impairments.

An electrostatic haptic display with three 7 x 7 electrode arrays of three different sizes was fabricated on a 4-in wafer using lithographic microfabrication techniques. The display utilizes electrostatic stimulation to generate a tactile sensation of texture on a scanning finger. The tactile sensation appeared to be a result of increased friction and vibration due to the electrostatic forces between the finger skin and the electrodes. Various spatial tactile patterns (lines, circles, squares, and triangles, etc.) can be presented on the display. Experiments of threshold, line separation, and pattern recognition were performed on subjects with visual impairments to study the spatial resolution and information transmission on arrays of variant electrode size and spacing. Two columns with two-column spacing can be resolved with 80% accuracy on the small array, for a spatial resolution of 5.8 mm in terms of edge-to-edge electrode distance. The overall percentages of correct recognition for the patterns were 68.3, 72.1, and 71.3% on the small, medium, and large arrays, respectively. While subject is an important factor for both threshold and pattern recognition, electrode size was statistically significant for threshold only. Frequency and duty cycle of the stimulation waveform did not show statistical significance.

Adult↗
PubMed2005

Linear demosaicing inspired by the human visual system.

There is an analogy between single-chip color cameras and the human visual system in that these two systems acquire only one limited wavelength sensitivity band per spatial location. We have exploited this analogy, defining a model that characterizes a one-color per spatial position image as a coding into luminance and chrominance of the corresponding three colors per spatial position image. Luminance is defined with full spatial resolution while chrominance contains subsampled opponent colors. Moreover, luminance and chrominance follow a particular arrangement in the Fourier domain, allowing for demosaicing by spatial frequency filtering. This model shows that visual artifacts after demosaicing are due to aliasing between luminance and chrominance and could be solved using a preprocessing filter. This approach also gives new insights for the representation of single-color per spatial location images and enables formal and controllable procedures to design demosaicing algorithms that perform well compared to concurrent approaches, as demonstrated by experiments.

Algorithms↗
PubMed2004

A new postural balance control system for rehabilitation training based on virtual cycling.

A new rehabilitation training system was developed to improve postural balance control by combining virtual reality technology with an unfixed bicycle. Twenty healthy subjects participated in the present study by riding the virtual cycling system under two different conditions: with or without visual feedback. Data were collected on the following parameters: path deviation, cycling velocity, etc. As a result of conducting the repeated training, results showed improvement not only in the ability to control balance and weight shift but also in the overall cycling ability including the degree of path deviation and the cycling speed. It was concluded that the system was effective as a training device and, in addition, the technology might have a wider applicability to the rehabilitation field.

Adult↗
PubMed2002

Full-screen magnification for windows using DirectX Overlays.

This paper presents the basic features of software-based magnifiers used by some visually impaired people to read information from a computer screen. The paper briefly presents two major approaches to full-screen magnification for modern multiple window systems (the paper focuses on Microsoft Windows). This paper describes in detail the architecture and operation of a full-screen magnifier that uses Microsoft DirectX Overlays. This approach leads to a robust magnifier that has a low computational overhead. The magnifier has problems with video cards that use a YUV color model but these problems may be addressed by RGB to YUV translation software--an issue that is still to be investigated. The magnifier also has problems when the generic device driver, rather than the manufacturer's device driver, is installed on the system. The paper presents two further strategies for full screen magnification, namely, using multimonitor support and true type fonts for text enlargement.

Algorithms↗
PubMed2003

Sonification of range information for 3-D space perception.

We present a device that allows three-dimensional (3-D) space perception by sonification of range information obtained via a point laser range sensor. The laser range sensor is worn by a blindfolded user, who scans space by pointing the laser beam in different directions. The resulting stream of range measurements is then converted to an auditory signal whose frequency or amplitude varies with the range. Our device differs from existing navigation aids for the visually impaired. Such devices use sonar ranging whose primary purpose is to detect obstacles for navigation, a task to which sonar is well suited due to its wide beam width. In contrast, the purpose of our device is to allow users to perceive the details of 3-D space that surrounds them, a task to which sonar is ill suited, due to artifacts generated by multiple reflections and due to its limited range. Preliminary trials demonstrate that the user is able to easily and accurately detect corners and depth discontinuities and to perceive the size of the surrounding space.

Acoustics↗
PubMed2004

Design and implementation of haptic virtual environments for the training of the visually impaired.

This paper presents a haptic virtual reality (VR) tool developed for the training of the visually impaired. The proposed approach focuses on the development of a highly interactive and extensible haptic VR training system (the ENORASI VR training system) that allows visually impaired, to study and interact with various virtual objects in specially designed virtual environments, while allowing designers to produce and customize these configurations. Based on the system prototype and the use of the CyberGrasp haptic device, a number of custom applications have been developed. An efficient collision detection algorithm is also introduced, by extending the proximity query package (PQP) algorithm to handle five points of contact (a case studied with the use of CyberGrasp). Two test categories were identified and corresponding tests were developed for each category. The training scenarios include: object recognition and manipulation and cane simulation, used for performing realistic navigation tasks. Twenty-six blind persons conducted the tests and the evaluation results have shown the degree of acceptance of the technology and the feasibility of the proposed approach.

Adult↗
PubMed2004

Producing preferred format material from Microsoft Word.

This paper presents a set of tools that are integrated with a word processor to produce documents in a visually impaired person's "preferred format." The paper considers the motivation for producing such tools and describes tools to perform spoken transcription (to cassette tape) and intelligent large print production.

Communication Devices for People with Disabilities↗
PubMed2006

Clearspeech: a display reader for the visually handicapped.

Many domestic appliances and much office equipment is controlled using a keypad and a small digital display. Programming such devices is problematical for the blind and visually handicapped. In this paper, we describe a device that may be used to read the displays on these devices. The device is designed to accept a description of the display being read, which specifies the types and locations of elements of the display. Images are captured using a handheld webcam. Images are processed to remove the distortions due to the camera orientation. The elements of the screen are interpreted and a suitable audio output is generated. In suitably illuminated scenes, the display data is interpreted correctly in approximately 90% of the cases investigated.

Communication Devices for People with Disabilities↗