Abstract: An image processor for producing clusters of related objects in a multi-level digital representation of an image includes a part for identifying predetermined objects in the image and for supplying data defining their locations. It also includes a part for deriving segmentation data directly from the multi-level digital representation. A segmentation device receives both sets of data and clusters the predetermined objects into groups for each segmented region before providing clustering data for subsequent analysis.

Abstract: An image processing system produces clusters of related objects for subsequent analysis. It receives a multi-level digital representation of the image and predetermined objects are identified by extraction units (4). A segmentation unit (6) drives boundary data from the multi-level digital representation, the boundary data representing boundaries between different regions of the image. A clustering unit (8) clusters the predetermined objects into groups in dependence on their proximity to each other and in dependence on the boundary data and supplies this cluster data for subsequent analysis.

Abstract: An apparatus for processing images comprise means (2) to scan in an image. The image data is stored and a variance calculator (6) calculates a variance for the scanned image. An image categoriser (16) determines what further processing of the image is appropriate in dependence on the variance.