Estimation of nucleation and crystal growth rates from microscopic information is of critical importance. This can be an especially challenging task if needle growth of crystals is observed. To address this challenge, an image analytical method for counting of needle-shaped crystals and estimating their length is presented. Since the current algorithm has a number of parameters that need to be optimized, a combination of simulation of needle crystal growth and Design of Experiments was applied to identify the optimal parameter settings for the algorithm. The algorithm was validated for its accuracy in different scenarios of simulated needle crystallization, and subsequently, the algorithm was applied to study the influence of additive on antisolvent crystallization. The developed algorithm is robust for quantifying heavily intersecting needle crystals in optical microscopy images, and has the potential for being applied for real-time crystallization monitoring and control.