Multi-Modal Identity Verification Based on Improved BP Neural Network

Back propagation neural network, as a method of data fusion technology, has been used in many common fields widely. In this paper, back propagation neural network based on binary full codes has been presented. Traditional back propagation method may classify the data as a good result, but it does not recognize the untrained data exactly. Back propagation neural network based on binary full codes method can solve this problem with mapping the float data into binary space using multi-modal on feature level fusion. The result of experiment proves that this algorithm obtains a good verification effect.