Retrieving electronic documents by converting them to synthetic text

• US 8,176,054 B2
• Filed: 07/12/2007
• Issued: 05/08/2012
• Est. Priority Date: 07/12/2007
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Moraleda, Jorge
• Primary Examiner(s): Vo, Tim T
• Assistant Examiner(s): TRAN, ANHTAI V
• Application Number:
  US11/777,142
• Publication Number:
  US 20090018990A1
• Time in Patent Office: 1,762 Days
• Field of Search: None
• US Class Current: 707/743
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/18171 Syntactic representation, e.g. using a grammatical approach
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

The present invention relies on the two-dimensional information in documents and encodes two-dimensional structures into a one-dimensional synthetic language such that two-dimensional documents can be searched at text search speed. The system comprises: an indexing module, a retrieval module, an encoder, a quantization module, a retrieval engine and a control module coupled by a bus. A number of electronic documents are first indexed by the indexing module and stored as a synthetic text library. The retrieval module then converts and input image to synthetic text and searches for matches to the synthetic text in the synthetic text library. The matches can be in turn used to retrieve the corresponding electronic documents. It should be noted that a plurality of matches and corresponding electronic documents may be retrieves ranked by order according the similarity of the synthetic text. In one or more embodiments, the present invention includes a method for indexing documents by converting them to synthetic text, and a method for retrieving documents by converting an image to synthetic text and comparing the synthetic text to documents that have been converted to synthetic text for a match.

Claims

1. A computer system for generating synthetic words for parts of documents, the computer system comprising:

an indexing module for receiving an electronic document comprising a first part and a second part, identifying a first bounding box for the first part, identifying a second bounding box for the second part, generating a synthetic word of the first bounding box, the synthetic word including a location of the first bounding box, a first quantized angle measured between a line originating from the first bounding box and a path joining a center of the first bounding box to a center of the second bounding box and a second quantized angle defining a width of the second bounding box, and producing an association between the electronic document and the synthetic word; and

a data storage for storing the electronic document, the synthetic word and the association between the electronic document and the synthetic word,

wherein the first part and the second part are at least one of text, a character and an image.

2. The computer system of claim 1 wherein the synthetic word includes at least one of text and scripts.

3. The computer system of claim 1 wherein the indexing module provides a full true mapping of the electronic document to plain text.

4. The computer system of claim 1 wherein the synthetic word alone is sufficient to perform retrieval of a corresponding electronic document.

5. The computer system of claim 1 wherein the synthetic word does not represent any natural language content of the electronic document.

6. The computer system of claim 1 wherein the synthetic word is in a one dimensional synthetic language encoded from a two-dimensional structure of a part of the electronic document.

7. The computer system of claim 1 wherein the indexing module also associates a document identification, a document page and a location within the document page to the synthetic word.

8. The computer system of claim 1 further comprising a retrieval module for retrieving one or more original electronic documents corresponding to a string of synthetic text, the retrieval module adapted for communication with the data storage and the indexing module.

9. The computer system of claim 1, comprising a graph encoder for converting the electronic document to synthetic text by converting a script in the electronic document to a sequence of quantized feature vectors.

10. The computer system of claim 1, further comprising a quantization module to adjust and optimize the generation of the synthetic word by modifying a quantization parameter used in the generation.

11. The computer system of claim 1 wherein the first part and the second part are each a word of synthetic text.

12. The computer system of claim 8 wherein the retrieval module receives an image patch and generates a string of synthetic text from the image patch.

13. The computer system of claim 8 further comprising a retrieval engine for searching for the string of synthetic text in the data storage, the retrieval engine being a conventional search engine.

14. The computer system of claim 8, wherein the retrieval module retrieves and presents an ordered list of electronic documents most likely to match the input image.

15. A method for generating synthetic words for parts of documents, the method comprising:

using a computer to perform steps comprising;

receiving an electronic document comprising a first part and a second part;

identifying a first bounding box for the first part;

identifying a second bounding box for the second part;

generating a synthetic word of the first bounding box, the synthetic word including a location of the first bounding box, a first quantized angle measured between a line originating from the first bounding box and a path joining a center of the first bounding box to a center of the second bounding box and a second quantized angle defining a width of the second bounding box; and

producing an association between the electronic document and the synthetic word, wherein the first part and the second part are at least one of text, a character and an image.

16. The method of claim 15, comprising storing the electronic document and an association between the synthetic word and the electronic document in a database.

17. The method of claim 15, wherein the steps of generating the synthetic word and producing the association are performed for every bounding box in the electronic document.

18. The method of claim 15, comprising receiving a second electronic document and performing the steps of generating a second synthetic word and producing a second association for the second electronic document.

19. The method of claim 16, wherein the association includes a document identification, a document page and a location within the document page.