Advanced control of crystal shape, size distribution, and polymorphic form (internal lattice structure) in suspension crystallization processes has been hindered by the limitations of available on-line sensors. High-speed, in-situ video microscopy is a promising technology for measuring these critical solid-phase properties. However, automatically extracting the desired information from in-situ images in a robust and efficient manner remains challenging, especially for highly non-spherical shapes. Needle-like crystals are particularly challenging, typically exhibiting a high degree of overlap. We have developed a novel image analysis algorithm that automatically extracts particle size information for needle-like crystals in in-situ images.¹ We have validated its performance experimentally by comparing its results with the results obtained by manually sizing crystals imaged over the duration of a pharmaceutical crystallization experiment. The algorithm's results agree well with the results obtained by manual sizing, and the speed with which it analyzes the images appears suitable for real-time PSD monitoring and control. We have also developed a method for identifying crystals of arbitrary shape provided that the shape can be represented by a parameterized three-dimensional model. We have demonstrated the method's ability to extract particle size and shape information using noisy, in-situ images of a pharmaceutical system in which the different polymorphic forms exhibit different crystal shapes. ¹ P.A. Larsen, J.B. Rawlings, and N.J. Ferrier, "An algorithm for analyzing noisy, in situ images of high-aspect-ratio crystals to monitor particle size distribution", submitted to Chemical Engineering Science.