This work is about the extraction of the motion of fingers, in their three articulations, of a keyboard player from a video sequence. The relevance of the problem involves several aspects, in fact, the extraction of the movements of the fingers may be used to compute the keystroke efficiency and individual joint contributions, as showed by Werner Goebl and Caroline Palmer in the paper 'Temporal Control and Hand Movement Efficiency in Skilled Music Performance'. Those measures are directly related to the precision in timing and force measures. A very good approach to the hand gesture recognition problem has been presented in the paper ' Real-Time Hand Gesture Recognition Using Finger Segmentation'. Detecting the keys pressed on a keyboard is a task that can be complex because of the shadows that can degrade the quality of the result and possibly cause the detection of not pressed keys. Among the several approaches that already exist, a great amount of them is based on the subtraction of frames in order to detect the movements of the keys caused by their pressure. Detecting the keys that are pressed could be useful to automatically evaluate the performance of a pianist or to automatically write sheet music of the melody that is being played.