cvBoostNextWeakClassifier（翻译）

标签：cvboostnextweakclass   opencv源码分析   

原文如下：

/*
 * cvBoostNextWeakClassifier
 *
 * The cvBoostNextWeakClassifier function performs next training
 * iteration and caluclates response values and weights for the next weak
 * classifier training.
 *
 * Parameters
 *   weakEvalVals
 *     Vector of values obtained by evaluation of each sample with
 *     the last trained weak classifier (iteration i). Must be of CV_32FC1 type.
 *   trainClasses
 *     Vector of classes of training samples. Each element must be 0 or 1,
 *     and of type CV_32FC1.
 *   weakTrainVals
 *     Vector of response values for the next weak classifier training
 *     (iteration i+1). Must be of type CV_32FC1.
 *   weights
 *     Weight vector of training samples for the next weak classifier training
 *     (iteration i+1). Must be of type CV_32FC1.
 *   trainer
 *     A pointer to internal trainer returned by the cvBoostStartTraining
 *     function call.
 *
 * Return Values
 *   The return value is the coefficient for the last trained weak classifier.
 *
 * Remarks
 *   weakTrainVals and weights must be exactly the same vectors as used in
 *   the cvBoostStartTraining function call and should not be modified.
 *   The function calculates response values and weights for the next weak
 *   classifier training and stores them into weakTrainVals and weights
 *   respectively.
 *   Note, the training of the weak classifier of iteration i+1 using
 *   weakTrainVals, weight, trainingData is outside of this function.
 */
CV_BOOST_API
float cvBoostNextWeakClassifier( CvMat* weakEvalVals,
                                 CvMat* trainClasses,
                                 CvMat* weakTrainVals,
                                 CvMat* weights,
                                 CvBoostTrainer* trainer );

/*
 * cvBoostNextWeakClassifier
 *这个函数的作用是为了训练下一个弱分类器，进行下一个迭代训练，计算响应值和权重
 *
 * 参数含义：
 *   weakEvalVals
 *     用上一个迭代训练的弱分类器（第i次迭代）来计算每一个样本的响应值的向量， 必须是 CV_32FC1 的类型
 *   trainClasses
 *     训练样本类的向量  0 or 1,类型必须为 CV_32FC1.
 *   weakTrainVals
 *     下一个弱分类器（第i+1次迭代）所需要的的响应值向量，类型也必须为CV_32FC1.
 *   weights
 *     下一个弱分类器（第i+1次迭代）所需要的的权重向量，类型也必须为CV_32FC1.
 *   trainer
 *     内部trainer的指针，它由cvBoostStartTraining函数回调
 *
 * 返回值
 *   返回值是上一个训练的弱分类器的系数
 *
 * 注：
 *   weakTrainVals and weights 必须与在cvBoostStartTraining函数回调 的向量严格一致，而且不能修改 ；
 *   这个函数计算响应值和权重，并分别存储在 weakTrainVals and weights里，下一个弱分类器的训练需要这两个参数。
 *   注意,第i+1次迭代过程的弱分类器的训练所使用的  weakTrainVals, weight, trainingData 在这个函数之外。
 */
CV_BOOST_API
float cvBoostNextWeakClassifier( CvMat* weakEvalVals,
                                 CvMat* trainClasses,
                                 CvMat* weakTrainVals,
                                 CvMat* weights,
                                 CvBoostTrainer* trainer );

cvBoostNextWeakClassifier（翻译）

标签：cvboostnextweakclass   opencv源码分析   

原文地址：http://blog.csdn.net/ding977921830/article/details/46775441