面向手机平台的快速笑脸识别方法

近年来,随着手机平台处理能力的增强,手机内置笑脸识别功能变得可行。传统基于Gabor的笑脸识别方法应用于手机平台遇到的主要难点是运算量大、实时性差。提出了一种改进笑脸特征提取算法,该算法基于Gabor变换和Adaboost算法,训练时采用Gabor变换提取全部特征,然后利用AdaBoost算法从降采样特征中挑选关键特征;检测时先计算关键特征点和相关特征卷积模板,然后计算特征值,最后进行匹配。实验表明改进算法不仅比原算法识别速度快,而且特征点分布规律表明识别性能还具有改善的可能。

Fast Smile Recognition Method for Mobile Platform

Due to the increases in computing power and storage capacity of mobile devices over the years,an incorporation of realtime smile recognition to mobile devices such as mobile phone and PDA is no longer unattainable.The major obstacles to be overcome are the relatively low processor speed,low storage memory and low image quality in mobile devices.In order to solve the challenging problems,a novel and efficient feature extraction algorithm for smile detection was proposed.The proposed algorithm is based on Gabor filters and Adaboost algorithm.The global face features using gabor filters were extracted,and then through a training process using the AdaBoost algorithm,the system could efficiently search for key features in a large set of features.According to these features,the key points in the original image and the corresponding convolution masks could be calculated.The effectiveness of the proposed algorithm and the feasibility of its application in mobile devices were demonstrated through empirical experiments.The results show that the proposed algorithm significantly outperforms several popular smile recognition methods with a dramatic reduction in computational speed.