PubMed Health⌕ Search

Biomedical subjects

K W Bowyer

Publications and source records attributed to K W Bowyer.

6 recordsLinked to original sources
PubMed2005

An evaluation of multimodal 2D+3D face biometrics.

We report on the largest experimental study to date in multimodal 2D+3D face recognition, involving 198 persons in the gallery and either 198 or 670 time-lapse probe images. PCA-based methods are used separately for each modality and match scores in the separate face spaces are combined for multimodal recognition. Major conclusions are: 1) 2D and 3D have similar recognition performance when considered individually, 2) combining 2D and 3D results using a simple weighting scheme outperforms either 2D or 3D alone, 3) combining results from two or more 2D images using a similar weighting scheme also outperforms a single 2D image, and 4) combined 2D+3D outperforms the multiimage 2D result. This is the first (so far, only) work to present such an experimental control to substantiate multimodal performance improvement.

Algorithms↗
PubMed1999

Registration and difference analysis of corresponding mammogram images.

An automated technique is proposed for identifying differences between corresponding mammogram images. The technique recovers an approximate deformation between a pair of mammograms based on identifying corresponding features across the two images. The registration process is completed using an unwarping technique for transforming one image into the coordinate system of the other. A difference image is generated using intensity-weighted subtraction in order to identify regions of large difference. Evaluation of the technique is performed using 124 bilateral image pairs which contain a total of 77 abnormalities of different types. The purpose of this paper is to measure the extent to which the mammogram registration technique is able to provide useful information for identifying abnormalities in mammograms.

Algorithms↗
PubMed1997

Generating ROC curves for artificial neural networks.

Receiver operating characteristic (ROC) analysis is an established method of measuring diagnostic performance in medical imaging studies. Traditionally, artificial neural networks (ANN's) have been applied as a classifier to find one "best" detection rate. Recently researchers have begun to report ROC curve results for ANN classifiers. The current standard method of generating ROC curves for an ANN is to vary the output node threshold for classification. In this work, we propose a different technique for generating ROC curves for a two-class ANN classifier. We show that this new technique generates better ROC curves in the sense of having greater area under the ROC curve (AUC), and in the sense of being composed of a better distribution of operating points.

Diagnostic Imaging↗
PubMed1984

Effects of age on radionuclide angiographic detection and quantitation of left-to-right shunts.

The usefulness of quantitative radionuclide angiography (RNA) in detecting left-to-right shunts and estimating shunt size in young children was assessed. The total population of 88 patients was divided into 2 groups: 23 patients 2 years of age and younger (mean 0.8 +/- 0.6 [+/- standard deviation] ) and 65 patients older than 2 years (mean 15 +/- 15 years). The accuracy of 2 different RNA shunt estimation techniques, the gamma variate and the Stewart-Hamilton approach, were compared with the estimations obtained at cardiac catheterization using Fick (88 patients) and indocyanine green dye-dilution techniques (20 patients). Automated data processing algorithms were used to determine the RNA estimations, thereby avoiding the effects of operator judgment and subjectivity on shunt estimation. Of the 88 patients, 16 had no shunt by Fick data (that is, estimation less than 20%) but had a left-to-right shunt demonstrated by cardiac catheterization cineangiocardiography. Nine of these patients had no shunt by RNA (that is, estimation less than 20%). For patients 2 years of age and younger, linear regression analysis of the Fick and gamma variate data provided a slope of 0.63 and a correlation coefficient of 0.82; analysis of the Fick and Stewart-Hamilton data provided a slope of 0.59 and a correlation coefficient of 0.79. For patients older than 2 years, analysis of the Fick and gamma variate data provided a slope of 0.63 and a correlation coefficient of 0.79; analysis of the Fick and Stewart-Hamilton data provided a slope of 0.64 and a correlation coefficient of 0.76.(ABSTRACT TRUNCATED AT 250 WORDS)

Adolescent↗