Abstract Sign language is the most important means of communication for deaf people. Given the lack of familiarity of non-deaf people with the language of deaf people, designing a translator system which facilitates the communication of deaf people with the surrounding environment seems to be necessary. The system of translating the sign language into spoken languages should be able to identify the gestures in sign language videos. Consequently, this study provides a system based on machine vision to recognize the signs in continuous Persian sign language video. This system generally consists of two main phases of sign words extraction and their classification. Several stages, including tracking and separating the sign words, are conducted in the sign word extraction phase. The most challenging part of this process is separation of sign words from video sequences. To do this, a new algorithm is presented which is capable of detecting accurate boundaries of words in the Persian sign language video. This algorithm decomposes sign language video into the sign words using motion and hand shape features, leading to more favorable results compared to the other methods presented in the literature. In the classification phase, separated words are classified and recognized using hidden Markov model and hybrid KNN-DTW algorithm, respectively. Due to the lack of proper database on Persian sign language, the authors prepared a database including several sentences and words performed by three signers. Simulation of proposed words boundary detection and classification algorithms on the above database led to the promising results. The results indicated an average rate of 93.73 % for accurate words boundary detection algorithm and the average rate of 92.4 and 92.3 % for words recognition using hands motion and shape features, respectively.