This paper presents an approach for gesture recognition based on curvature scale space (CSS). First, for each gesture sequence, hands are segmented from gesture images into binary silhouette images, and then the binary hand contours are computed. Next, CSS features of hand contours and four-directional chain codes between two successive hand contours are extracted to characterize hand shapes and trajectories of gestures, respectively. In particular, a feature-preserving algorithm is proposed to allocate the extracted CSS features to a one-dimensional feature vector with a fixed size for the input of hidden Markov models (HMMs). Finally, the HMM is applied to determine hand-shape and trajectory transitions in different gestures for gesture identification. Results show that the proposed approach performs well in recognizing the gestures and is more accurate than the previous methods that were based on conventional features.