公开(公告)号：US06728391B1

公开(公告)日：2004-04-27

申请号：US09454090

申请日：1999-12-03

Applicant: Jianxin Wu ,  Gregory P. Skinger ,  Jason Wang ,  James Recktenwalt

Inventor： Jianxin Wu ,  Gregory P. Skinger ,  Jason Wang ,  James Recktenwalt

IPC: G06K900

CPC classification number: G06K9/4647 ,  B07C1/00 ,  G06K9/3233 ,  G06K9/6857 ,  G06K2209/01 ,  Y10S209/90

Abstract: A multi-resolution label locator system divides an input image into a plurality of multi-pixel cells. The multi-resolution label locator system then creates a decimated image or low resolution image corresponding to the input image. The decimated image includes a common-characteristic value that corresponds to a multi-pixel cell of the input image. The multi-resolution label locator system identifies one or more areas within the decimated image that have characteristics corresponding to the characteristics of interest. While generating the decimated image, the multi-resolution label locator system simultaneously creates an edge-occurrence image that corresponds to the input image. The edge-occurrence image includes an edge value that corresponds to each cell of the input image. Each edge value represents the number of occurrences of an edge within the pixels of a corresponding cell of the input image. The multi-resolution label locator system identifies one or more candidate areas within the input image that have decimated-image characteristics and edge-occurrence image characteristics corresponding to the characteristics of interest. The multi-resolution label locator system then classifies the candidate areas according to the likelihood of the input image containing indicia having the characteristics of interest. Lastly, the multi-resolution label locator system compiles a list of one or more candidate areas that most likely contain indicia having the characteristics of interest.

Abstract translation: 多分辨率标签定位器系统将输入图像划分成多个多像素单元。 然后，多分辨率标签定位器系统创建对应于输入图像的抽取图像或低分辨率图像。 抽取的图像包括对应于输入图像的多像素单元的公共特征值。 多分辨率标签定位器系统识别抽取图像中具有与感兴趣特征相对应的特征的一个或多个区域。 在生成抽取图像的同时，多分辨率标签定位器系统同时创建对应于输入图像的边缘发生图像。 边缘出现图像包括对应于输入图像的每个单元的边缘值。 每个边缘值表示输入图像的相应单元的像素内的边缘的出现次数。 多分辨率标签定位器系统识别输入图像内具有对应于感兴趣特征的抽取图像特性和边缘出现图像特性的一个或多个候选区域。 多分辨率标签定位器系统然后根据包含具有感兴趣特征的标记的输入图像的可能性对候选区域进行分类。 最后，多分辨率标签定位器系统编译最可能包含具有感兴趣特征的标记的一个或多个候选区域的列表。