Abstract | ||
---|---|---|
In this paper, an algorithm of gesture recognition based on simulated annealing BP neural network is presented. Firstly, this new algorithm extracts the edge outline by skin color division and recognition feature of the distance between center and edge of binary gesture image. Secondly, it combines simulated annealing with BP neural network, which has both the learning ability and robustness of the neural network and the global optimization of simulated annealing, avoids the slow convergence and prevents it from falling into local minimum. The results of experiments show that the algorithm can greatly improve efficiency and accuracy of gesture recognition. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/EMEIT.2011.6022891 | EMEIT |
Keywords | Field | DocType |
bp neural network,global optimization,backpropagation,binary gesture image,skin recognition feature,learning ability,edge detection,simulated annealing bp neural network,edge outline extraction,skin color division,gesture recognition,simulated annealing,neural nets,image colour analysis,hidden markov model,input device,neural network,interactive media,time series,weed control,human computer interaction,template matching,back propagation | Simulated annealing,Computer vision,Pattern recognition,Computer science,Edge detection,Gesture recognition,Adaptive simulated annealing,Robustness (computer science),Time delay neural network,Artificial intelligence,Artificial neural network,Backpropagation | Conference |
Volume | Issue | ISBN |
1 | null | 978-1-61284-087-1 |
Citations | PageRank | References |
3 | 0.43 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hui Zhang | 1 | 5 | 2.14 |
Yongqi Wang | 2 | 3 | 0.43 |
Chen Deng | 3 | 5 | 1.14 |