遥感影像中属于某类别的特征向量服从正态分布，基于此理论，根据统计学原理，提出一种新的基于类别分布的分类精度检验方法，该方法与常规基于混淆矩阵的分类精度检验方法完全不同，不需检验数据，仅需要一定的样本数据来估计总体的分布，可直接利用监督分类的训练区进行，因此对监督分类而言工作量极小。该方法能够进行的关键是类别总体的分布能通过某一分布的假设检验，在这种情况下可方便地计算出该类别的生产者精度，同时根据类别均值向量对应的像元数目和均值向量在类别总体中出现的概率计算出类别总体的数目后，可计算出各类别的用户精度，然后根据各类别的用户精度和分类后各类别分布面积比例计算出分类总精度。最后以郑州市高密度建设用地分类的生产者精度数据的获取为例进行了实证研究。研究表明：对于总体分布与正态分布最接近的两个波段的分类结果，本方法的计算结果与常规方法的计算结果在统计意义上可以认为一致。

Accuracy assessment is an indispensable step in the process of classification of remotely sensed data.The common method is carried out through confusion matrix established on reference data,which has three deficiencies: the heavy workload,inability to guarantee the complete correctness of reference data,the cost of reduction error resulting in the increase of workload.In remotely sensed imagery,the feature vector belonging to one category obeys the normal distribution.Based on this hypothesis and statistic theory,a new method is proposed established on category distribution.The reference data is unnecessary for proposed method.For the supervised classification,the workload is extremely little.The key to the proposed method is that the category population can pass the hypothesis test of a certain distribution,in this case,producer's accuracy can be figured out easily.Given the number of the category population,the user's accuracy can be figured out too,and then the overall accuracy can be estimated by user's accuracy and area proportions of all categories after classification.Finally,the proposed method in this paper was applied to image classification for Zhengzhou city as an example.The result shows: if the distribution of category population can be given,producer's accuracy obtained by common method and proposed method completely conforms in the perspective of statistics.