摘要
学习表情数据库中学习表情图像的数量与质量将直接决定深度学习模型的效率和泛化能力,但既有表情数据库存在样本数量少、分辨率低、表情类型有限等问题,而且其建设初衷也并非出于教育教学研究的需要,这无疑限制了学习表情的识别与应用。文章从现实需求出发,建成了拥有168000幅图像的学习表情数据库,并采用主观评价法对该数据库进行了评价,以确保该数据库的实用性和有效性。评价结果显示,学习表情数据库具有较高质量,能够满足实际需要。学习表情数据库的建设,对于提高学习表情识别的效率、准确率和鲁棒性具有重要意义,并有助于实现学习者与学习环境之间的深层情感交互。
The quantity and quality of learning expression images in the learning expression database can directly determine the efficiency and generalization ability of the deep learning model.However,the existing learning expression databases had problems of small sample size,low resolution and limited expression types,and their original intention of construction were not out of the needs of education,which undoubtedly limited the recognition and application of learning expressions.Starting from the actual needs,this paper constructed a learning expression database which contained 168,000 images.In order to ensure the reliability and effectiveness of the constructed database,this paper evaluated it using a subjective evaluation method.The results showed that the learning expression database was of high quality and could meet the actual needs.This paper was of great significance for improving the efficiency,accuracy and robustness of learning expression recognition,and helped achieve harmonious emotional interaction between learning environment and learners.
作者
徐振国
刘志
孔玺
党同桐
XU Zhen-guo;LIU Zhi;KONG Xi;DANG Tong-tong(School of Communication,Qufu Normal University,Rizhao,Shandong,China 276826;National Engineering Laboratory for Educational Big Data,Central China Normal University,Wuhan,Hubei,China 430079)
出处
《现代教育技术》
CSSCI
2021年第8期112-118,共7页
Modern Educational Technology
基金
国家自然科学基金青年科学基金项目“学习画面情感对学习者情感的影响机制及其自适应调整方法研究”(项目编号:62007020)
教育部人文社会科学研究青年基金项目“智慧学习环境下学习画面情感对学习者情感的影响及其作用机制研究”(项目编号:20YJCZH194)
山东省社会科学规划研究青年项目“智慧学习环境下深度学习影响因素模型构建研究”(项目编号:20DJYJ05)的阶段性研究成果。
关键词
深度学习
学习表情
表情识别
学习情感
表情数据库
deep learning
learning expression
expression recognition
learning emotion
expression database
