This paper focuses on sign language recognition with respect to the hand movement trajectories at a sentence level. This is achieved by applying two proposed methods namely Chunk-based and Cluster-based feature representation techniques in order to extract the desired keyframes. The features are extracted based on hands and head local centroid characteristics such as velocity, magnitude and orientation. A set of experiments are conducted on a large self-curated sign language sentence data set (UOM-SL2020) in order to evaluate the performance of the proposed methods. The results clearly show the high recognition rate of 75.51% in terms of F-measure which is achieved by combining the proposed method with symbolic interval-based representation and validation of feature sets.

This paper proposes a gesture recognition approach in which morphological and trajectories are analysed. A video input containing the gesture demonstration is given to the algorithm as an input and the analysis are carried out frame by frame in 3 stages. During the Primary processing stage, the location and shape of the face and hands are identified. Secondary processing is concerned with extracting information on the change in these parameters throughout the video sample. At the decision-making stage, a two-step algorithm is used based on comparison of the motion trajectories and key object shapes between the test gesture and the reference gestures. The experiments were performed on a set of selected classes from UOM-SL2020 sign language data set and a high recognition F1-score of 0.8 was achieved.