Autonomous Text Capturing Robot Using Improved DCT Feature and Text Tracking
Autonomous Text Capturing Robot Using Improved DCT Feature and Text Tracking
复制标题
DOI：
10.1109/icdar.2007.71
复制
发表时间：
2007-09
期刊：
影响因子：
--
通讯作者：
Makoto Tanaka;Hideaki Goto
中科院分区：
文献类型：
--
作者：
Makoto Tanaka;Hideaki Goto
当一个自主机器人试图使用机载摄像机在周围的场景中寻找文本时，一些重复的文本图像会出现在视频帧中。为了避免多次识别相同的文本，需要减少文本候选区域的数量。本文提出了一种利用活动摄像头观察周围环境的文本捕捉机器人。使用改进的DCT特征从图像中提取文本候选区域。在视频序列中跟踪文本区域，以便减少要识别的文本图像的数量。在实验中，我们测试了460张走廊的图片，上面有15块带有文字的广告牌。使用我们的文本跟踪方法，文本候选区域的数量减少了90.1%。
When an autonomous robot tries to find text in the surrounding scene using an onboard video camera, some duplicate text images appear in the video frames. To avoid recognizing the same text many times, it is necessary to decrease the number of text candidate regions for recognition. This paper presents a text capturing robot that can look around the environment using an active camera. The text candidate regions are extracted from the images using an improved DCT feature. The text regions are tracked in the video sequence so that the number of text images to be recognized is reduced. In the experiment, we tested 460 images of a corridor with fifteen signboards including text. The number of text candidate regions is reduced by 90.1% using our text tracking method.