Handwritten character retrieval apparatus and method

US9424477B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9424477-B2
Application numberUS-201313841767-A
CountryUS
Kind codeB2
Filing dateMar 15, 2013
Priority dateMay 28, 2012
Publication dateAug 23, 2016
Grant dateAug 23, 2016

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

According to one embodiment, a handwritten character retrieval apparatus is provided with an acquisition unit, a feature extraction unit, an segmentation unit, a attribute append unit and a retrieval unit. The acquisition unit acquires a handwritten character string in units of a stroke. The feature extraction unit extracts a first feature value unique to each of the strokes from the handwritten character string. The segmentation unit segments the strokes into a plurality of sets. The attribute append unit appends a second feature value based on the sets to each of the strokes. The retrieval unit executes retrieval based on the first feature value and the second feature value.

First claim

Opening claim text (preview).

What is claimed is: 1. A handwritten character retrieval apparatus comprising: a processor; and storage comprising instructions to cause the processor to execute: acquisition of a handwritten character string in units of each of strokes; feature extraction of a first feature value which is unique to each of the strokes from the handwritten character string; segmentation of the strokes into a plurality of sets; append of a second feature value based on the sets, to each of the strokes; and retrieval of an item including the handwriting character based on the first feature value and the second feature value; wherein the segmentation comprises segmentation of the handwritten character string into at least one part or all of a character area, a word block, a character block and a radical block, and classification of the handwritten character string into at least the character area and an area other than the character area, the second feature value is a feature value vector indicative of a total number of strokes included in each of one or a plurality of sets to which each of the strokes belongs, and the second feature value appended for each of the strokes includes at least a third feature value and a fourth feature value, the third feature value being associated with the sets to which the strokes belong if the strokes belong to the character area, the fourth feature value being associated with the sets to which the strokes belong if the strokes belong to the area other than the character area. 2. The handwritten character retrieval apparatus of claim 1 , wherein the acquisition comprises acquisition of the handwritten character string in units of a stroke by online recognition. 3. The handwritten character retrieval apparatus of claim 1 , wherein the acquisition comprises acquisition of one of pre-stored handwritten character strings, which is designated by a user. 4. The handwritten character retrieval apparatus of claim 1 , wherein the acquisition comprises acquisition of a handwritten character string which is formed by using templates of stroke strings, which are prepared in advance in accordance with the sets. 5. The handwritten character retrieval apparatus of claim 1 , further comprising a display configured to display a retrieval result by the retrieval unit. 6. The handwritten character retrieval apparatus of claim 1 , wherein the retrieval comprises retrieval of a handwritten document including a stroke string which is similar to the acquired handwritten character string. 7. The handwritten character retrieval apparatus of claim 6 , wherein when a retrieval result is displayed, the handwritten document including the stroke string is displayed, and the stroke string is displayed and the stroke string is highlighted. 8. A handwritten character retrieval apparatus comprising: a processor; and storage comprising instructions to cause the processor to execute: acquisition of a handwritten character string in units of each of strokes; feature extraction of a first feature value which is unique to each of the strokes from the handwritten character string; segmentation of the strokes into a plurality of sets; append of a second feature value based on the sets, to each of the strokes; and retrieval of an item including the handwriting character based on the first feature value and the second feature value; wherein the segmentation comprises segmentation of the handwritten character string into at least one part or all of a character area, a word block, a character block and a radical block, and classification of the handwritten character string into at least the character area and an area other than the character area, wherein the second feature value is a feature value vector indicative of a feature value that is obtained by applying a method, which is identical to a method of calculating the first feature value, to all strokes included in each of one or a plurality of sets to which each of the strokes belongs, and the second feature value appended for each of the strokes includes at least a third feature value and a fourth feature value, the third feature value being associated with the sets to which the strokes belong if the strokes belong to the character area, the fourth feature value being associated with the sets to which the strokes belong if the strokes belong to the area other than the character area. 9. The handwritten character retrieval apparatus of claim 8 , wherein the acquisition comprises acquisition of the handwritten character string in units of a stroke by online recognition. 10. The handwritten character retrieval apparatus of claim 8 , wherein the acquisition comprises acquisition of one of pre-stored handwritten character strings, which is designated by a user. 11. The handwritten character retrieval apparatus of claim 8 , wherein the acquisition comprises acquisition of a handwritten character string which is formed by using templates of stroke strings, which are prepared in advance in accordance with the sets. 12. The handwritten character retrieval apparatus of claim 8 , further comprising a display configured to display a retrieval result by the retrieval unit. 13. The handwritten character retrieval apparatus of claim 8 , wherein the retrieval comprises retrieval of a handwritten document including a stroke string which is similar to the acquired handwritten character string. 14. The handwritten character retrieval apparatus of claim 13 , wherein when a retrieval result is displayed, the handwritten document including the stroke string is displayed, and the stroke string is displayed and the stroke string is highlighted.

Assignees

Inventors

Classifications

  • Physics · mapped topic

  • Physics · mapped topic

  • using stroke segmentation · CPC title

  • G06V30/416Primary

    Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9424477B2 cover?
According to one embodiment, a handwritten character retrieval apparatus is provided with an acquisition unit, a feature extraction unit, an segmentation unit, a attribute append unit and a retrieval unit. The acquisition unit acquires a handwritten character string in units of a stroke. The feature extraction unit extracts a first feature value unique to each of the strokes from the handwritte…
Who is the assignee on this patent?
Toshiba Kk
What technology area does this patent fall under?
Primary CPC classification G06K9/00865. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Aug 23 2016 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).