一种新型的基于神经网络的图像检索算法  

A New Image Retrieval Algorithm Based on Neural Network

作　　者：吴岸雄[1] WU Anxiong

机构地区：[1]肇庆学院计算机科学与软件学院,广东肇庆526061

出　　处：《科技创新与应用》2020年第34期22-23,共2页Technology Innovation and Application

摘　　要：提出了一种改进的基于神经网络的图像检索算法。这种算法不止是考虑到了图像颜色和形状特征的提取,更是把特征权值的调整转化为优化问题。利用神经网络算法得到权值的最优解,从此到最佳检索效果。通过实验结果表明,此算法能更加高效地找到图像,并且有较强的稳定性和图像检索功能。An improved image retrieval algorithm based on neural network is proposed.This algorithm not only considers the extraction of image color and shape features,but also turns the adjustment of feature weights into an optimization problem.The optimal solution of weights is obtained by neural network algorithm to achieve the best retrieval effect.Experimental results show that this algorithm can find the image more efficiently and has strong stability and capability of image retrieval.

关 键 词：图像检索 神经网络 特征提取 特征权重 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]