A blood cell classification system for locating and classifying white blood cells in a peripheral blood smear is disclosed. The system utilizes a rapid scanning system which quickly enables detecting the location of white blood cells and defining a field about the blood cell which is scanned for classification of the type of white cell located within the field. The masking and filtering process for detecting white cells avoids the necessity of examining other than white cells in time consuming detail.

Scanning system for location and classification of patterns

Video-rate digital image analysis equipment

Methods and apparatus are described by which detected signal pulses arising from features in a field can be associated to thereby generate so-called agglomerates of features, in dependence on the relative spacing of the features in the field. In this way it is possible to link up the detected signal pulse information relating to small features arranged approximately in straight lines. The invention generates capture zones from each feature one extending in the line scan direction and the other generally perpendicular thereto. The invention envisages the combination therewith of an associated parameter computer whereby information may be obtained relative to a parameter of each detected feature. The information from features within an agglomerate may be suppressed or collated and released as a single information signal relating to the agglomerate. Thus where a count pulse is generated for each feature these may be inhibited from all features within an agglomerate and the latter counted as a single feature. Alternatively where a signal proportional to the area of each feature is generated by the associated parameter computer, these may be combined for features within an agglomerate and a total area signal released for the agglomerate proportional to the total of the individual areas of the features within the agglomerate.

Gibbons J

Papers

Feature association in image analysis