• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Asia-Pacific Signal and Information Processing Association Annual Summit and Conference >Image Recognition Based on Convolutional Neural Networks Using Features Generated from Separable Lattice Hidden Markov Models
【24h】

Image Recognition Based on Convolutional Neural Networks Using Features Generated from Separable Lattice Hidden Markov Models

机译：基于可分离格子隐马尔可夫模型生成特征的基于卷积神经网络的图像识别

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

An image recognition method based on convolutional neural networks (CNNs) using features generated from separable lattice hidden Markov models (SLHMMs) is proposed. A major problem in image recognition is that the recognition performance is degraded by geometric variations in the size and position of the object to be recognized. To solve this problem, SLHMMs have been proposed as an extension of HMMs with size and locational invariances based on state transitions. Although SLHMMs are generative models that can represent the generation processes of observations well, there is a possibility that they are not specialized for discrimination compared to discriminative models. Our method integrates SLHMMs that extract features invariant to geometric variations with CNNs that build an accurate classifier based on discriminative models with the extracted features. Face recognition experiments showed that the proposed method improves recognition performance.
机译：提出了一种基于卷积神经网络（CNN）的图像识别方法，该方法利用可分离的格子隐马尔可夫模型（SLHMM）生成的特征。图像识别中的主要问题是，由于要识别的对象的尺寸和位置的几何变化而导致识别性能下降。为了解决这个问题，已经提出SLHMM作为HMM的扩展，其具有基于状态转变的尺寸和位置不变性。尽管SLHMM是生成模型，可以很好地表示观测结果的生成过程，但与判别模型相比，它们可能不专门用于区分。我们的方法将提取几何变化不变特征的SLHMM与CNN集成在一起，CNN基于具有提取特征的判别模型构建准确的分类器。人脸识别实验表明，该方法提高了识别性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号