Abstract Improved inspection of crushed rock aggregates will reduce the production of unsaleable material, enhance site quality control and boost sales revenue through premium quality aggregate mixtures. A low cost optomechatronic system is described which aims to provide a rapid breakdown of particle size distribution, along with descriptions of constituent product shape. A material sampling system directs aggregate into a novel optical inspection chamber, where particle geometry is digitised in real time by a dual beam laser scanning system. Classical image processing algorithms obtain dimensional triaxial information from the digitised data, and allow fractal or fourier features to be extracted if required. Soft computing techniques implement a neurofuzzy pattern classifier which assigns linguistic shape descriptors - rounded, irregular, flaky etc. to the particle data. These methods combine to allow a detailed and meaningful interpretation of the sampled crusher product.