skip to main content
Ngôn ngữ:
Giới hạn tìm kiếm: Giới hạn tìm kiếm: Dạng tài nguyên Hiển thị kết quả với: Hiển thị kết quả với: Chỉ mục

种基于关键点检测的衣服种类和属性分类方法
Clothes type and attribute classification method based on key point detection

Chen Jikai ; Pan Yan ; Lai Hanjiang ; Yin Jian ; GAO Jing

Truy cập trực tuyến

Trích dẫn Trích dẫn bởi
  • 种基于关键点检测的衣服种类和属性分类方法

  • Nhan đề:
    Clothes type and attribute classification method based on key point detection
  • Tác giả: Chen Jikai ; Pan Yan ; Lai Hanjiang ; Yin Jian ; GAO Jing
  • Chủ đề: Physics ; Computing ; Calculating ; Counting ; Recognition Of Data ; Presentation Of Data ; Record Carriers ; Handling Record Carriers ; Computer Systems Based On Specific Computational Models ; Medicine ; Sciences ; Chemistry ; Physics
  • Mô tả: The invention provides a clothes type and attribute classification method based on key point detection. According to the method, data of a training sample is collected; a configuration clothes key point detection deep model is established, and data of the training sample is input to the deep model to train the deep model; the trained deep model is used to analyze a clothes image to predict the position of each key point in the clothes image; and according to key point predicting results, related local information is extracted and fused with global picture information, and the deep model is used to train and predict the type and attribute of the clothes. The method can be used to fuse local with global characteristics of the clothes in a better way. 本发明提供种基于关键点检测的衣服种类和属性分类方法,该方法先采集训练样本的数据;然后构建可配置的检测衣服关键点的深度模型,并将训练样本的数据输入深度模型,以对深度模型进行训练;接着利用训练后的检测关键点的深度模型对衣服图像进行分析,预测衣服图像中每个关键点的位置;最后根据S3中预测关键点的结果,以此提取相关局部信息,再融合全局的图片信息,再通过深度模型对衣服种类和属性进行训练、预测。该方法实现了能够更好融合衣服局部和全局特征。
  • Năm xuất bản: 17 April 2018
  • Ngôn ngữ: Chinese;English

Đang tìm Cơ sở dữ liệu bên ngoài...