公开(公告)号：EP2593920A2

公开(公告)日：2013-05-22

申请号：EP11807382.4

申请日：2011-07-12

申请人： Google Inc.

发明人： WU, Bo ,  BISSACCO, Alessandro ,  SMITH, Raymond, W. ,  CHEUNG, Kong, Man ,  FROME, Andrea, Lynn ,  URBACH, Shlomo

IPC分类号： G06Q50/00

CPC分类号： G06K9/3258 ,  G06K9/00 ,  G06K9/18 ,  G06K2209/01 ,  G06Q50/10

摘要： A system and method is provided for automatically recognizing building numbers (530) in street level images (320). In one aspect, a processor (210) selects a street level image (320) that is likely to be near an address (530) of interest. The processor (210) identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values (410) of the characters displayed in such portions. If an extracted value (720) corresponds with the building number of the address of interest (750) such as being substantially equal to the address of interest, the extracted value (820) and the image portion (850) are displayed to a human operator. The human operator confirms, by looking at the image portion (850), whether the image portion (850) appears to be a building number that matches the extracted value (820). If so, the processor (210) stores a value that associates that building number with the street level image (320).

公开(公告)号：EP2583201A2

公开(公告)日：2013-04-24

申请号：EP11796149.0

申请日：2011-05-31

申请人： Google Inc.

发明人： YADID, Tal ,  NETZER, Yuval ,  URBACH, Shlomo ,  FROME, Andrea ,  BEN-HAIM, Noam

IPC分类号： G06F17/30 ,  G06F17/27 ,  G06F9/44

CPC分类号： G06K9/723 ,  G06F17/241 ,  G06F17/2705 ,  G06F17/30241 ,  G06K9/00664 ,  G06K2209/01

摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.