基于curvelet变换的新生儿疼痛表情识别分析-analysis of neonatal pain expression recognition based on curve let transformation.docxVIP

AbstractNeonates undergo repeated pain stimulation will produce a series of physical and psychological impact, in the worst case, will cause severe and permanent central nervous system damage and developmental delay. The traditional method, used to assess neonatal pain is conducted by health professionals, has many limitations. For example, using this artificial method, plenty of time and energy are spent to cultivate many health professionals; the results of the assessment are vulnerable to the subjective factors; sometimes, health professionals cannot assess the neonatal pain immediately. So, it is significant to develop an auto and efficient system to recognize neonatal pain.Feature extraction is the key technology in the procedure of neonatal pain recognition and it determines the recognition rate.This paper uses Curvelet transform to extract the feature of neonatal pain expression, then uses FDA method to reduce the dimensions of feature,and finally uses sparse representation as a classifier. Experiments show that the proposed algorithm has a satisfied performance, the average correct rate can achieve to 91.75%.The main contributions are as follows:The paper discusses the impact of direction parameter of Curvelet transform on recognition results.In order to analysis the relation between recognition rate and dimension, the FDA method is adopted to reduce the dimensions of feature.Several methods are used to decompose the test images, such as Newton-precondition conjugate gradient method, homotopy and orthogonal matching pursuit method.Then the recognition performance under different number of training samples and different feature dimension is discussed after experiments.The cross validation method is adopted to calculate the average recognition rate, and the correct identification rate and false rate of each class in each test are analyzed at last.Key words: Neonatal pain, Expression recognition, Curvelet transform, Compressive sensing, Sparse representation目