公开(公告)号：WO0169529A2

公开(公告)日：2001-09-20

申请号：PCT/US0105757

申请日：2001-02-23

Applicant: INTEL CORP

Inventor： LIENHART RAINER W ,  WERNICKE AXEL

IPC: G06K9/32 ,  G06T5/00

CPC classification number: G06K9/325 ,  G06K2209/01 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/20008 ,  G06T2207/30176

Abstract: In some embodiments, the invention includes a method for locating text in digital images. The method includes scaling a digital image into images of multiple resolutions and classifying whether pixels in the multiple resolutions are part of a text region. The method also includes integrating scales to create a scale integration saliency map and using the saliency map to create initial text bounding boxes through expanding the boxes from rectangles of pixels including at least one pixel to include groups of at least one pixel adjacent to the rectangles, wherein the groups have a particular relationship to a first threshold. The initial text bounding boxes are consolidated. In other embodiments, a method includes classifying whether pixels are part of text region, creating initial text bounding boxes, and consolidating the initial text bounding boxes, wherein the consolidating includes creating horizontal projection profiles having adaptive thresholds and vertical projection profiles having adaptive thresholds.

Abstract translation: 在一些实施例中，本发明包括用于定位数字图像中的文本的方法。 该方法包括将数字图像缩放成多个分辨率的图像，并分类多个分辨率中的像素是否是文本区域的一部分。 该方法还包括集成比例以创建比例积分显着图并使用显着图通过从包括至少一个像素的像素矩形扩展框来创建初始文本边界框，以包括与矩形相邻的至少一个像素的组， 其中所述组与第一阈值具有特定关系。 初始文本边界框被合并。 在其他实施例中，一种方法包括对像素是文本区域的一部分，创建初始文本边界框以及合并初始文本边界框进行分类，其中合并包括创建具有自适应阈值的水平投影轮廓和具有自适应阈值的垂直投影轮廓。

公开(公告)号：WO0169530A3

公开(公告)日：2002-12-27

申请号：PCT/US0105776

申请日：2001-02-23

Applicant: INTEL CORP

Inventor： LIENHART RAINER W ,  WERNICKE AXEL

IPC: G06K9/32 ,  G06T5/00

CPC classification number: G06K9/325 ,  G06K2209/01 ,  G06K2209/015 ,  G06T7/11 ,  G06T7/194 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/30176

Abstract: In some embodiments, the invention includes receiving a digital image including text and background. The method includes vector quantizing the digital image such that the digital image is divided into certain colors, and creating a text color histogram from a portion of the text and a first portion of the background. The method also includes creating at least one background color histogram from a second portion of the background, and creating a difference color histogram from a difference between the text color histogram and the at least one background color histogram, and wherein an estimated color of the text is derived from the difference color histogram. In other embodiments, the invention includes receiving a text object including bounding boxes of multiple frames of a video signal. The method further includes estimating a color of text of the bounding boxes and aligning blocks representing the bounding boxes through a best displacement search in which only pixels having a color within a threshold of an estimated color are considered. Some embodiments of the invention also include receiving digital images in text bounding boxes and in preparation for a segmentation process, adjusting sizes of the digital images to a fixed height.

Abstract translation: 在一些实施例中，本发明包括接收包括文本和背景的数字图像。 该方法包括量化数字图像的矢量，使得数字图像被划分成某些颜色，并且从文本的一部分和背景的第一部分创建文本颜色直方图。 该方法还包括从背景的第二部分创建至少一个背景颜色直方图，以及从文本颜色直方图和至少一个背景颜色直方图之间的差异创建差异颜色直方图，并且其中文本的估计颜色 是从差异色彩直方图得出的。 在其他实施例中，本发明包括接收包括视频信号的多个帧的边界框的文本对象。 该方法还包括通过最佳位移搜索来估计边界框的文本的颜色和对齐表示边界框的块，其中仅考虑具有估计颜色的阈值内的颜色的像素。 本发明的一些实施例还包括在文本边界框中接收数字图像，并准备分割过程，将数字图像的大小调整到固定的高度。