Search

The results of an automated classification of the peripheral blood leukocytes into eight categories are presented. The classification was achieved by means of digital image processing. The categories were: small lymphocytes, medium lymphocytes, large lymphocytes, band neutrophils, segmented neutrophils, eosinophils, basophils, and monocytes. An eight-dimensional multivariate Gaussian classifier was used. The features were extracted from a 50 × 50 point digital image. These features were measures of such visual concepts as nuclear size, nuclear shape, nuclear and cytoplasmic texture, cytoplasm color, and cytoplasm colored texture. The data set consisted of 1041 blood cell images and were divided into a training set of 523 cells and an independent testing set of 518 cells. These cells were digitized directly from the blood smear, which was stained with Wright's stain. Twenty different blood smears were used and were collected over a three-year period from 20 people. The "true" classification of the data set was obtained from four experienced hematology technicians. Their performance was compared to the automated classifier both in terms of an absolute classification of cells and in terms of estimating the percentage composition of the population (or the blood cell differential count). The measure of performance used was the percentage error for each class. The mean percentage error for the eight classes in terms of an absolute classification was 8 and 29 percent for the human observers and the automated classiffier, respectively.

A brief argument is presented for the need for automatic speech segmentation both to facilitate automatic speech recognition and for its theoretical linguistic importance. The problem of speech segmentation in the acoustic domain using a digital computer is examined in detail, that is, of determining an acoustic partition in time which has linguistic relevance. This problem is viewed, in more general terms, as that of detecting transitions, in a globally non-stationary process, from one local stationary state to another. Non-stationary analyses are approximated by considering short fixed length time series sections as seen through a window which moves by a fixed increment. Various non-stationary signal representations are explored in order to establish a feature space suitable for applications to segmentation. Spectral representations are generated only as a reference space for comparison of an automatic segmentation procedure with the linguistically determined segmentation of any given speech sample. Temporal representations of the zero crossings of speech signals are explored in detail. In particular the central sample moments of the reciprocal zero crossings as a function of time are used as input to a simple segmentation algorithm. The results of a demonstration of this algorithm show that speech segmentation as defined is possible by non-human means.

Increased use of computer output for decision-making has led to the need for effective computer-generated displays of symbols and lines in various formats. Two key functions involved in display generation are digital-to-image conversion, and image storage for projection. Symbol generation can be performed by use of logical and electron beam devices to create dot patterns, intensity modulated scans, mixtures of waveforms or shaped electron beams. Lines are generated as dots, line segments, or vectors. Large, bright displays are obtained by optically projecting images using CRT, photographic, electrostatic, oil film, or thermoplastic techniques. Many new developments show promise for application in computer-generated displays.

Deflection linearity and adjustment in a TV system are accomplished by a test pattern usually generated by a scanning process which may itself be subject to error. This paper describes a method and equipment for generating a circular test pattern derived from an electronic memory. The readout is accomplished by an accurate time base synchronous with scanning standards. By this means an extremely accurate circular (or other) pattern can be generated for adjustment of display devices.

In this paper we develop methods of segmenting a large system into smaller subsystems so that the letter can be diagnosed in parallel. Two basic techniques called serial segmentation and parallel segmentation are introduced. Furthermore, an algorithm is developed for the purpose of reducing the complexity and the size of the large subsystem.

The artificial color definition of gray-scale levels has progressed through a number of evolutionary steps which started with early efforts to "color-label" the high-, medium- and low-intensity tone levels of infra red films. The three-layer color-composite, when registered and projected on a viewing screen, provided some coarse but readily recognizable bench marks for the gray-scale values of an image. While a three-point index spread over a wide range of image intensity was a rather crude and inflexible form of scaling indication, it was, neverthe-less, the first step in the right direction. Multispectral photographs provide distinctive information about ground terrain, from aerial views and when the individual spectral responses are encoded by projection through colored filters, the composite result may be registered and viewed on a common viewing screen.

It is well known that the first-order properties of an optical system are sufficiently specified by the tracing of two meridional paraxial rays through the system, namely the marginal ray, which originates at the center of the object plane and passes through the edge of the stop, and the chief ray, which originates at the edge of the object and passes through the center of the stop. Wherever the marginal ray crosses the axis an image plane is located and wherever the chief ray crosses the axis a pupil plane is located. Moreover, the height of the chief ray at an image plane gives the size of the image and the height of the marginal ray at a pupil plane gives the size of the pupil.

We propose an algorithm for articulated human motion segmentation that estimates parametric motions of body parts and segments images into moving regions accordingly. Our approach combines robust optical flow estimation, RANSAC, and region segmentation using color and Gaussian shape priors. This combination results in an algorithm that can robustly estimate and segment multiple motions, even for moving regions with small support and in low-resolution images. Based on the raw motion segmentation, consistent body motions are detected over time to characterize human activity. The effectiveness of this approach is demonstrated in a real scenario: characterizing dining activities of patients at a nursing home.

This paper examines algorithms and techniques for use in a complete FLIR target cuer/recognizer. The application is the Air Force Theater Missile Defense Eagle Smart Sensor and Automatic Target Cuer/Recognizer (TESSA) program. The data used for this research are 1st generation FLIR images collected from an F-15E. The database contains thousands of images with various target arrangements. The specific target of interest is a mobile missile launcher, which will be defined as the primary target. The goal is to locate all vehicles (secondary targets) within a scene and identify the missile launchers. The system designed includes an image segmenter, region cluster algorithm, and classifier. Conventional algorithms in conjunction with neural network techniques are used to form a complete ATR system. Some of the conventional techniques include hit/miss filtering, difference of Gaussian filtering, and region clustering. A neural network (multilayer perceptron) is used for classification. These various algorithms are tested and combined into a functional ATR system. Overall target detection rate (cuer) is 84% with a 69% accurate primary target identification (recognizer) rate. Furthermore, the false alarm rate (a non-target cued as a target) is only 2.3 per scene. The research will be completed with a 10 flight test profile using an F-15E and will collect 3/sup rd/ generation FLIR images for use with these algorithms.

R. C. Johnson, author of "Design of Linear Double Tapers in Rectangular Waveguides," which appeared on pp. 374-378 of the July 1959 issue of these Transactions has brought the following corrections to the attention of the Editor.