White specks are undyed spots on dyed fabric, and are commonly caused by neps. The manual counting of white specks on a fabric is not only a time-consuming process but also inconsistent and prone to error because it is very subjective. In this study, a white speck counter was designed using image analysis techniques to count and size white specks on dyed fabric. It can minimize the variations from light fluctuations, and automatically perform threshold determination and calibration. The performance of the white speck counter was compared with that of the traditional manual counting of white specks on the sample fabrics in terms of accuracy, repeatability and sensitivity to different operators. The white speck counter identified white specks faster and more efficiently than the manual counting method. The white speck counter also performed more consistently and objectively than the manual counting method.