查询结果:   闫河,王鹏,董莺艳,罗成,李焕.基于深度CNN和极限学习机相结合的实时文档分类[J].计算机应用与软件,2019,36(3):174 - 179.
中文标题
基于深度CNN和极限学习机相结合的实时文档分类
发表栏目
人工智能与识别
摘要点击数
753
英文标题
REAL-TIME DOCUMENT CLASSIFICATION BASED ON DEEP CNN AND EXTREME LEARNING MACHINE
作 者
闫河 王鹏 董莺艳 罗成 李焕 Yan He Wang Peng Dong Yingyan Luo Cheng Li Huan
作者单位
重庆理工大学计算机科学与工程学院 重庆 401320 重庆理工大学两江人工智能学院 重庆 401147    
英文单位
College of Computer Science, Chongqing University of Teachnology, Chongqing 401320, China Artificial Intelligence College, Chongqing University of Teachnology, Chongqing 401147, China    
关键词
文档图像分类 CNN 迁移学习
Keywords
Document image classification CNN Migration learning
基金项目
国家自然科学基金面上项目(61173184);重庆市自然科学基金项目(cstc2018jcyjAX0694)
作者资料
闫河,教授,主研领域:深度学习,图像识别。王鹏,硕士生。董莺艳,硕士生。罗成,硕士生。李焕,硕士生。 。
文章摘要
提出一种文档图像实时分类训练和测试的方法。在实际应用中,数据训练的精确性和高效性在文档图像识别中起着关键的作用。现有的深度学习方法不能满足此要求,因为需要大量的时间用于训练和微调深层次的网络架构。针对此问题,提出一种基于计算机视觉的新方法:第一阶段训练深度网络,作为特征提取器;第二阶段用极限学习机(ELM)用于分类。该方法的性能优于目前最先进的基于深度学习的相关方法,在Tobacco-3482数据集上的最终准确率为83.45%。与之前基于卷积神经网络(CNN)的方法相比,相对误差降低了26%。ELM的训练时间仅为1.156秒,对2 482张图像的整体预测时间是3.083秒。因此,该文档分类方法适合于大规模实时应用。
Abstract
This paper presented a real-time training and testing method for document image classification. In practical applications, the accuracy and efficiency of data training play a key role in document image recognition. The existing deep learning methods cannot meet this requirement, because they need a lot of time to train and fine-tune the deep network architecture. To solve this problem, we proposed a new method based on computer vision. The method was divided into two steps: the depth network was trained as a feature extractor; we used the extreme learning machine(ELM) for classification. The performance of this method is superior to the advanced methods based on deep learning. The final accuracy of this method on Tobacco-3482 dataset is 83.45%. Compared with the method based on convolution neural network, the relative error is reduced by 26%. The training time of ELM is only 1.156 s, and the overall prediction time of 2 482 images is 3.083 s. Therefore, the method is suitable for large-scale real-time applications.
下载PDF全文