基于BP神经网络的风景图像分类  

Classification of Natural Images Based on BP Neural Network

作　　者：谢文兰[1] 

机构地区：[1]广东培正学院计算机科学与工程系,广州510830

出　　处：《湖南工程学院学报（自然科学版）》2012年第2期45-47,共3页Journal of Hunan Institute of Engineering(Natural Science Edition)

摘　　要：通过建立一个多输出的BP神经网络,提取图像的底层特征作为网络的输入,用语义期望值作为网络的输出.训练完成后,该网络能够对风景图像进行多种语义分类检索,从而建立起了从底层特征到语义特征之间的映射.提出的一种颜色提取方法不仅降低了颜色特征向量的维数,减少了计算量,节省了时间,而且在描述风景图像的颜色内容上更加准确.如何选取图像的语义阈值是一个重点也是一个难点,通过实验发现,当阈值的选取范围在[0.55,0.65]时,检索的查全率和准确率能达到一个比较好的平衡效果.实验证明,此方法在风景图像的分类上取得了较好的检索查全率和准确率.This paper establishes a multioutput BP neural network. This method extracts lowlevel fea tures vector as the network input and the exceptions as its output. The System trains the network with BP arithmetic. When the training is over, this network can classify natural images. So it has established the mapping between the lowlevel features and highlevel semantic features. This paper proposes a new Color method which not only reduces the color characteristic vector dimension and the amount of computation＇, saves the time, but also describes the content of image more accurately. How to select the semantic image threshold is important and difficult. Through the experiment, it is found that when the selected threshold ranges of[0.55, 0.65], the retrieval of the recall rate and the accurate rate can achieve a better balance effect. The experiment proves that it has obtained the high accuracy.

关 键 词：颜色提取方法 BP神经网络 阈值 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]