Characterization of aluminum hydroxide particles from the Bayer process using neural network and Bayesian classifiers

An automatic process of isolating and characterizing individual aluminum hydroxide particles from the Bayer process in scanning electron microscope gray-scale images of samples is described. It uses image processing algorithms, neural nets and Bayesian classifiers. As the particles are amorphous and different greatly, there were complex nonlinear decisions and anomalies. The process is in two stages; isolation of particles, and classification of each particle. The isolation process correctly identifies 96.9% of the objects as complete and single particles after a 15.5% rejection of questionable objects. The sample set had a possible 2455 particles taken from 384 256/spl times/256-pixel images. Of the 15.5%, 14.2% were correctly rejected. With no rejection the accuracy drops to 91.8% which represents the accuracy of the isolation process alone. The isolated particles are classified by shape, single crystal protrusions, texture, crystal size, and agglomeration. The particle samples were preclassified by a human expert and the data were used to train the five classifiers to embody the expert knowledge. The system was designed to be used as a research tool to determine and study relationships between particle properties and plant parameters in the production of smelting grade alumina by the Bayer process.