PatMax Patterns

When you train PatMax you specify a region of interest in an image or shape description that includes the features you want to train. When you train using an image, PatMax constructs an internal geometric representation of the features (a pattern) it finds in the training image. These features are made up of continuous boundaries between regions of dissimilar pixels in the image. When you train using a shape description PatMax transforms the model into this same internal geometric description. Once trained, PatMax execution is the same regardless of whether PatMax was trained with an image or with a shape description.