【24h】

Research of license plate recognition based on HSV Space

机译:基于HSV空间的车牌识别研究

获取原文

摘要

In order to solve the problem of license plate recognition in a complex environment, put forward a combined with the feature of license plate color, gray features, geometric shape, a general method of license plate recognition, first of all according to the color feature of license plate of China, this paper proposes a method based on HSV color space color recognition of license plate, solves the basic problem of license plate recognition accuracy is not high; Then with the improved Sobel operator edge detection method to obtain a rectangular area where the background plate; Finally could license plate area unified dimension, and verification, the last segment the license plate area. Adopt natural complex images taken to validate the new method in the environment of experiments show that compared with other methods, the new method can be adaptive within limits the type of license plate number, size, and direction, and the car position in the image and image background of fewer restrictions, applicability is a strong way.
机译:为了解决牌照识别的问题在复杂的环境中,提出了一种与车牌颜色,灰色特性,几何形状,车牌识别的一般方法中,首先的特征相结合根据的颜色特征中国的车牌,本文提出了一种基于HSV颜色空间的颜色识别车牌的方法,解决了车牌识别精度的基本问题不高;然后用改进的Sobel算子的边缘检测方法来获得的矩形区域,其中背景板;最后可以车牌区域统一的尺寸,和验证,最后一段车牌区域。采用验证新方法中的实验环境采取自然复杂的图像显示,与其他方法相比,新方法可以是限制的车牌号码,大小和方向的类型,并且在图像中的汽车的位置和内自适应的限制较少图像背景,适用性是一种强的方式。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号