Neonatal pain assessment has gained more and more attention from clinical care, and pain scales are usually adopted as the main assistants for neonatal pain rankings. Due to the large time and manpower consumption of pain scales, automatic pain assessment for neonates during painful clinical procedures is of great requirements. A video database of neonatal facial expression, containing pain intensity labels obtained from two different pain scales, is constructed in this paper as a pre-work for automatic pain score evaluation. Uniform and rotation invariant local binary patterns (LBP) are implemented as feature descriptors and the effectiveness of the extracted features is validated. As a result, a feature set of 144 dimensionalities is established and with the implementation of dimension reduction, new feature sets ranging from 40 to 60 dimensionalities, accounting for more than 90% of original data, are preserved as the input data for future pain classification.