Neuronal signal consists of short voltage pulses called action potentials or spikes. The sequence of action potentials contains the information that is conveyed from one neuron to others. In biological nervous systems, the transmitted information is usually encoded in the frequency of spiking and/or in the timing of the spikes. A spiking neuron transmits information by the timing of the spikes. Spiking neural networks are networks of spiking neuro that their inputs and outputs are spike firing times. At first, the pulse neural networks were introduced and modeled on a single layer in which neurons did not need to be trained. In these models, neurons are sensitive to intensity level of pixles of an image as input and produce pulses based on the amount of stimulation at different times. These networks were used in image processing effectively. In this thesis, as an application we make use of simultaneous feature of activating neurons with the same stimulation intensity. The pulse neural network is used for binarization of image of documents. The purpose of this study is to compare pulse neural network performance with other document binarization techniques. In last few years, by providing appropriate training methods , spiking neurons are also trained. It is shown, developing an effective learning method is a challenge in the study of spiking neural networks. One of the most widely used learning methods in this field is gradient descent based learning method. However, in these methods, due to complexity of computations related to the hidden layer, the network requires a lot of learning epochs. In this thesis, by modification of the network error function and according to the input coding, the number of required layers of the network is reduced to two. Accordingly, by removing the hidden layer, the convergence speed is improved Keywords: 1. Spiking neural networks, 2. Multi-spike learning, 3. Single-spike learning, 4. Document image binarization.