An approach to texture pattern analysis and recognition

A two-dimensional statistical model is proposed for the characterization of textural pattern, and a technique is introduced for textural pattern recognition by computer. The model building involves two major steps. The first step is the determination of a preliminary model from textural data. In the second step, the model is refined via parameter optimization. The refined model is used to characterize a pattern class. The measured data from an unclassified textural pattern and the estimated data from the models are used to determine similarity measures and variances which provide the key to textural pattern recognition by computer.