基于定向成对混合的摄影档案图像数据增广研究  

Research on Image Data Augmentation of Photographic Archives Based on Directional Pairwise Mixing

作　　者：刘清[1] LIU Qing(Xi'an Polytechnic University,Xi'an 710048 China)

机构地区：[1]西安工程大学,陕西西安710048

出　　处：《自动化技术与应用》2023年第7期8-10,38,共4页Techniques of Automation and Applications

摘　　要：为了实现针对数字档案图像的高效分类与高精度识别,提出一套基于定向成对混合的摄影档案图像数据增广方案,运用OPairIM算法对细粒度图像类别加以划分,并通过成对生成方式提取数字图像混合的样本序列和标签序列,并通过各种不同类型的图像数据集对该算法的有效性加以验证,取得了较为理想的图像识别效果。In order to realize the efficient classification and high-precision recognition of digital archives images,this study proposes a set of photographic archives image data expansion scheme based on directional pairwise mixing,divides the fine-grained image categories by using opairim algorithm,and extracts the mixed sample sequence and label sequence of digital images through pairwise generation method.The effectiveness of the algorithm is verified by various types of image data sets,and an ideal image recognition effect is achieved.

关 键 词：摄影档案图像 定向成对混合 数据增广 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]