发明申请
US20120243787A1 SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR DOCUMENT IMAGE ANALYSIS USING FEATURE EXTRACTION FUNCTIONS
有权
使用特征提取函数的文档图像分析的系统,方法和计算机程序产品
- 专利标题: SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR DOCUMENT IMAGE ANALYSIS USING FEATURE EXTRACTION FUNCTIONS
- 专利标题(中): 使用特征提取函数的文档图像分析的系统,方法和计算机程序产品
-
申请号: US13071999申请日: 2011-03-25
-
公开(公告)号: US20120243787A1公开(公告)日: 2012-09-27
- 发明人: Yuh-Lin E. Chang , Stewart N. Taylor , Michael F. Fallon
- 申请人: Yuh-Lin E. Chang , Stewart N. Taylor , Michael F. Fallon
- 主分类号: G06K9/34
- IPC分类号: G06K9/34
摘要:
Methods, systems and computer program products to improve the efficiency and computational speed of an image enhancement process. In an embodiment, information that is generated as interim results during feature extraction may be used in a segmentation and classification process and in a content adaptive enhancement process. In particular, a cleaner image that is generated during a noise removal phase of feature extraction may be used in a content adaptive enhancement process. This saves the content adaptive enhancement process from having to generate a cleaner image on its own. In addition, low-level segmentation information that is generated during a neighborhood analysis and cleanup phase of feature extraction may be used in a segmentation and classification process. This saves the segmentation and classification process from having to generate low-level segmentation information on its own.
公开/授权文献
信息查询