M. E. Jernigan

Learn More
Texture feature extraction and discrimination in an additive noise environment is wnsidered. A new set of 28 texture features derived in the spatial frequency domain is presented. A successive addition and deletion feature selection scheme based on the Wilks criterion is used to obtain a subset of features which effectively discriminate among a set of(More)
In this correspondence the implementations of fast Haar transforms are examined. Previous algorithms are described and compared to a new implementation called the in place algorithm. By performing the transform in place and limiting the amount of data movement, the algorithm attains greater memory efficiency and speed than other known algorithms. Index(More)
An approach which uses regional entropy measures in the spatial frequency domain for texture discrimination is presented. The measures provide texture discriminating information independent of that contained in the usual summed energy within based frequency domain features. Performance of the entropy features as measured by a between-to-within-class scatter(More)
A compensation scheme for the correction of both horizontal and vertical eye position measurements is developed. Based on the assumption that the distortion process can be modeled as piecewise linear, a new sample point structure is introduced. This structure permits both fixation-based and tracking-based sampling strategies. It also provides a convenient(More)
A method of automatically estimating the location of the bladder wall in ultrasound images is proposed. Obtaining this estimate is intended to be the first stage in the development of an automatic bladder volume calculation system. The first step in the bladder wall estimation scheme involves globally processing the images using standard image processing(More)