计算机工程与应用2019，Vol.55Issue(24)：141-146,177,7.DOI:10.3778/j.issn.1002-8331.1810-0010
基于多特征融合的深层网络图像语义识别方法
Multi-Feature Fusion Based Deep Network for Image Semantic Recognition
摘要
Abstract
Images are powerful tools with which to convey human emotions, with different images stimulating diverse emotions. In this paper, a data augmentation method based on small data sets is adopted. The advanced features(object category and deep emotion feature)are used, which are automatically extracted by the deep network combined with low-level features(color and texture features)to recognize emotion of the image. A high-level semantic descriptive phrase including compound emotions and object is output. The results show that the proposed method is superior to other tradi-tional manual extraction methods or existing deep learning models and achieves 66.54% accuracy on emotion recognition on IAPS and GAPED data sets.关键词
图像情感/迁移学习/卷积神经网络Key words
image semantics/transfer learning/Convolutional Neural Network(CNN)分类
信息技术与安全科学引用本文复制引用
王哲,杨鹏飞,杨雅茹,姚蓉,杨雄,李海芳..基于多特征融合的深层网络图像语义识别方法[J].计算机工程与应用,2019,55(24):141-146,177,7.基金项目
国家自然科学基金(No.61472270). （No.61472270）
