• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2013 International Conference on Circuits, Power and Computing Technologies >Detect and separate localization text in various complicated-colour image
【24h】

Detect and separate localization text in various complicated-colour image

机译：检测并分离各种复杂颜色图像中的本地化文本

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Text detection and localization in Multi-color images is important for content-based image analysis. This conflict is occurring due to the various backgrounds, the inhomogeneous illumination, and the variations of text font, size and line orientation. In this the image is converted into grayscale image then median filter is used to discard the unwanted noise in the gray scale image. Edge detection is mentioned by using canny edge detection and sobel edge detector. Canny edge detection is used to measure edges of the horizontal and vertical axis present around the text region in gray scale image. Sobel edge detector is used to measure edges of the overall boundaries of the horizontal and vertical axis present in the grayscale image. A mask is a dark and light image of the same dimensions as the original image (or the region of interest we are working in). Group of the pixels in the mask can have therefore a value of 0 (black) or 1 (white). When executing operations on the image the mask is used to restrict the result to the pixels that are 1 (selected, active, and white) in the mask. Morphological operations are defined by moving a structuring element over a binary image to be modified in such a way that it is centered over an image pixel at some point. The process of removing certain details in an image which is smaller than certain preference shape is called Morphological image processing and the preference shape is called structuring element. The goal of the connected component analysis is to detect the large sized connected foreground region or object. This is one of the important operations in motion detection. The pixels that are collectively connected can be clustered into changing or moving objects by analyzing their connectivity. The recognition of the text region is referred to the optical Character Recognition which compares the text with databases which consists of different types of character and extracts the text and mentioned in the text notepad docum- nt.
机译：多色图像中的文本检测和本地化对于基于内容的图像分析非常重要。由于各种背景，不均匀的照明以及文本字体，大小和行方向的变化而发生此冲突。在这种情况下，图像被转换为​​灰度图像，然后使用中值滤波器来丢弃灰度图像中不需要的噪声。通过使用canny边缘检测和sobel边缘检测器提到了边缘检测。 Canny边缘检测用于测量灰度图像中文本区域周围出现的水平轴和垂直轴的边缘。 Sobel边缘检测器用于测量灰度图像中存在的水平轴和垂直轴的整体边界的边缘。遮罩是与原始图像（或我们正在研究的感兴趣区域）尺寸相同的明暗图像。因此，遮罩中的像素组可以具有0（黑色）或1（白色）的值。在图像上执行操作时，使用遮罩将结果限制为遮罩中1（选定，活动和白色）的像素。通过将结构元素移动到要修改的二进制图像上来定义形态操作，以使其在某个点上位于图像像素上方。去除小于特定偏好形状的图像中的特定细节的过程称为形态图像处理，而偏好形状称为结构化元素。连接组件分析的目的是检测大型的连接前景区域或对象。这是运动检测中的重要操作之一。通过分析像素的连通性，可以将集体连接的像素聚类为变化或运动的对象。文本区域的识别称为“光学字符识别”，它将文本与包含不同类型字符的数据库进行比较，并提取文本并在文本记事本文档中提及。

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