On the basis of SVM( Support Vector Machine) multiclass classification，an improved DAGSVM ( Directed Acyclic Graph
Support Vector Machine) hand gesture recognition approach is put forward． Firstly，depth information of the scene is collected by using
Kinect sensor and hand region is obtained． Then feature vectors are extracted，which are used to train multiple binary SVM classifiers．
DAGSVM classifier is constructed using DAG topological structure with trained binary SVM classifiers and its structure sequence is improved．
Finally，the experimental results proved that the improved DAGSVM could reach higher recognition rate and can be used in the
control of intelligent wheelchair successfully．

To the speciality of mixed noise constituted by pulse noise and Gauss noise，we present a comprehensive algorithm in this
text，which is based on the simplified PCNN model，utilizing several technique specialities of the model，selecting parameters properly，
and combining with mathematical morphology method，median filtering and wiener filtering． This method performs better than average
filters and median filters on hybrid noise reduction while retaining edges and detail information of the image． Experiments show that the
effect of eliminating grey image mixed noise which applying the simplified PCNN eliminating algorithm proposed in this paper is good．
This algorithm can show a big advantage when in the comparison with other algorithms． This algorithm not only can effectively filter hybrid
noise but also can excel in real-time tasks because of its reduced computation complexity． With the increase of the image populated
by blends noise，the advantage is obvious．