| 1. | Automatic caption location and extraction in digital video frame based on svm and ica
的视频帧字幕自动定位与提取 |
| 2. | Video frame store
视频框储存器 |
| 3. | Video frame size
视讯帧大小 |
| 4. | Video object segmentation usually divides the contents of a video frame into semantic regions that can be dealt as objects
对视频对象的分割通常是将视频的内容分割成具有语义的区域，并进一步作为对象来处理。 |
| 5. | In addition to throwing away the spatial and color similarities of individual images , the temporal redundancies between adjacent video frames are eliminated
另外，为了丢弃在每幅图像之间空间和色彩的相似部分，要除去相邻视频画面之间的时间冗余。 |
| 6. | A method for overcoming the incompatibility of film and video frame rates when converting or transferring film ( shot at 24 frames per second ) to video ( shot at 30 frames per second )
在将电影（每秒24帧）转换或传输为电视（每秒30帧）时，一种克服电影和电视帧速率不兼容的方法。 |
| 7. | In order to improve the algorithm , a algorithm integrating with optic flow is presented by introducing the theory of estimating motion between video frames by optic flow
为了提高匹配速度，引入了光流法估计视频图像帧间运动的思想，提出了综合光流法和基于归一化积相关和高斯塔形分解的配准算法的匹配定位方法。 |
| 8. | Caption detection and enhancement choosing reasonable features according to the particularity of caption , and combining the redundant information of multiple video frame to detect and enhance caption
基于视频的字幕检测和增强根据字幕的特殊性选择合理的特征，并利用视频中多帧间的冗余信息实现字幕的检测和增强。 |
| 9. | Audio - video object - based coding and description are the distinct features of mpeg - 4 standard . in the mpeg - 4 standard , video frame was composed of a series of independent semantic video object , which was encoded independently
在mpeg - 4标准中，视频帧被认为是由一系列相互独立的运动对象组成，视频帧的编码也直接针对一个个视频对象。 |
| 10. | Chapter three give a method of detecting the movement on video through analyzing the video frames . the direction and speed of the moving object on video can also be detected by means of the method
第三章研究实现了一种数字图象序列的运动检测和运动报警算法，不仅能够实现简单运动检测，而且还能够分析出运动物体的运动方向和运动速度。 |
