The stereoscopic image quality assessment has become one of the popular topics in the field of three-dimensional imaging.Due to the slow training speed,easily falling into local minimum and the low generalization in traditional neural network,the extreme learning machine (ELM) algorithm is presented for objective stereoscopic image quality assessment in this paper.ELM works for generalized single-hidden layer feedforward neural networks (SLFNs),which randomly chooses the input weights and analyticall y determines the output weights of SLFNs.Compared with traditional neural network algorithms,EL M not only is easier to select the parameters,but also keeps the advantage of extremely fast l earning speed and achieves better generalization performance,and is widely applied in the fie ld of function approximations and pattern recognition.Experimental results show that the corre ct classification rate of 241different levels of test samples with sigmoid activation function is 93.85%.At the same time,the paper not only studies the effects of different hidden layer node s for ELM in different activation functions,but also performs an analysis and comparison of the performance among ELM,traditional back propagation (BP) and support vector machine (SVM) in st ereoscopic image quality assessment.