| 基于神经网络的静态台标识别系统设计与实现 |
| |
| 引用本文： | 张博洋,曾向荣,刘振中.基于神经网络的静态台标识别系统设计与实现[J].计算机仿真,2009,26(1). |
| |
| 作者姓名： | 张博洋 曾向荣 刘振中 |
| |
| 作者单位： | 国防科技大学信息系统与管理学院,湖南,长沙,410073 |
| |
| 摘 要： | 台标是电视台的重要标志,是对电视节目来源、类型等属性的描述,因此台标识别是实现电视视频自动收录、检索的重要技术基础.针对静态台标的特点和识别中存在的问题,在台标提取和特征识别的基础上,提出了一种基于BP神经网络的台标识别方法,并设计实现了一个静态台标识别系统,对系统的神经网络参数经过反复试验调整,最后得到令人满意的结果.实验结果表明,通过训练和识别分开,对包括半透明台标在内的电视视频,系统具有识别效率高、结果准确等优点.
|
| 关 键 词： | 台标识别 神经网络 图形标识 |
A Static Station Logo Recognition System Based on Neural Network |
| |
| ZHANG Bo-yang,ZENG Xiang-rong,LIN Zhen-zhong.A Static Station Logo Recognition System Based on Neural Network[J].Computer Simulation,2009,26(1). |
| |
| Authors: | ZHANG Bo-yang ZENG Xiang-rong LIN Zhen-zhong |
| |
| Affiliation: | College of Information System and Management;National University of Defense Technology;Changsha Hunan 410073;China |
| |
| Abstract: | Logo can be used to describe the attributes of the TV video including the origin and types,and is an important sign of the TV station.Station logo recognition is the most important foundation for automatic record and retrieval of TV video.In view of the station logo characteristic and existing problems,this paper brings forward a recognition algorithm based on BP neural networks and a static station logo recognition system.After adjusting the parameters of the neural networks,a satisfactory result is also o... |
| |
| Keywords: | Station logo recognition Neural network Graphics logo |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
