摘要
针对场景识别中低级特征与高级概念之间的语义鸿沟问题,提出了一种基于稀疏自动编码机的场景识别方法。采用了稀疏自动编码机和空间金字塔池化相结合的特征编码技术。首先对场景图像提取局部的HOG特征,然后利用改进的稀疏自动编码机对HOG特征进行编码,得到稀疏特征,通过空间金字塔池化和局部归一化得到整张场景图像的表示,最后利用线性SVM实现分类。在标准的场景图像数据集Scene-15上进行的实验表明,该算法可以将识别的准确率提升至81. 97%。
To narrow the gap between low-level features and high-level concepts in scene recognition,a new algorithm based on the sparse autoencoder was proposed.This algorithm adopted the feature encoding technique that combined the sparse autoencoder and spatial pyramid pooling.First of all,the local HOG descriptors were extracted from scene images,then they were encoded into sparse features by the modified sparse autoencoder.After spatial pyramid pooling and local normalization on these sparse features,the image representation can be obtained.Finally,linear SVM was utilized to implement scene recognition.The experimental results on Scene-15dataset indicated that the recognition accuracy of this algorithm can be increased up to81.97%.
作者
谢林
李菲菲
陈虬
XIE Lin;LI Feifei;CHEN Qiu(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science andTechnology,Shanghai 200093,China)
出处
《电子科技》
2019年第1期38-41,51,共5页
Electronic Science and Technology
基金
上海市高校特聘教授(东方学者)岗位计划(ES2012XX
ES2014XX)~~
