Object detection and extraction from image sequences
US-9213898-B2 · Dec 15, 2015 · US
US2016180191A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016180191-A1 |
| Application number | US-201414581861-A |
| Country | US |
| Kind code | A1 |
| Filing date | Dec 23, 2014 |
| Priority date | Dec 23, 2014 |
| Publication date | Jun 23, 2016 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An image recognition apparatus includes an acquisition unit and a controller. The acquisition unit acquires an image which captures by photography a pattern indicative of an object. The controller is configured to specify a pattern area from a first image which the acquisition unit acquires, to recognize a pattern which the specified pattern area includes, to acquire a second image from the acquisition unit, to determine whether a disposition of the object of the first image and a disposition of the object of the second image coincide, and to specify a pattern area from the second image, if determining that the disposition of the object of the first image and the disposition of the object of the second image are non-coincident, and to recognize a pattern which the specified pattern area includes.
Opening claim text (preview).
1 . An image recognition apparatus, comprising: a camera interface; and a controller configured to execute a decoding process on first and second images received through the camera interface in this order by specifying a first pattern area within the first image, decoding an identification pattern of an object included in the first pattern area, determining whether or not the first image and the second image match, and when the first image and the second image are determined to not match, specifying a second pattern area within the second image, and decoding the identification pattern of an object included in the second pattern area. 2 . The image recognition apparatus of claim 1 , wherein the decoding process further includes specifying, within an area of the second image that does not match with a corresponding area of the first image, a third pattern area, and decoding at least an identification pattern included in the third pattern area. 3 . The image recognition apparatus of claim 2 , wherein the controller determines the non-matching area based on pixels of the first image and the second image within the area. 4 . The image recognition apparatus of claim 1 , wherein the controller is configured to repeatedly perform the decoding process on additional first and second images received from the camera interface in that order at predetermined intervals. 5 . The image recognition apparatus of claim 1 , wherein the specifying of the second pattern area and decoding of the identification pattern in the second pattern area are carried out after the specifying of the first pattern area or after the decoding of the identification pattern in the first pattern area. 6 . The image recognition apparatus of claim 1 , wherein the controller determines that the first image and the second image match, when the second image is a translated or rotated image of the first image. 7 . The image recognition apparatus of claim 1 , wherein the controller determines whether or not the first image and the second image match based on pixels of the first image and the second image. 8 . The image recognition apparatus of claim 1 , wherein the pattern includes any one of a bar code, a QR code, a character, a numeral, a mark, and a feature value for object recognition. 9 . A commodity information processing apparatus, comprising: a camera interface; and a controller configured to execute a settlement process based on first and second images received through the camera interface in this order by specifying a first pattern area within the first image, decoding an identification pattern of an object included in the first pattern area, determining whether or not the first image and the second image match, when the first image and the second image are determined to not match, specifying a second pattern area within the second image, and decoding an identification pattern of the object included in the second pattern area, acquiring commodity information corresponding to the decoded identification pattern in the first pattern area or the decoded identification pattern in the second pattern area, and executing a settlement process based on the acquired commodity information. 10 . An image recognition method, comprising: acquiring a first image; specifying a first pattern area within the acquired first image; decoding an identification pattern of an object included in the first pattern area; acquiring a second image after the acquisition of the first image; determining whether or not the first image and a the second image match; and when the first image and the second image are determined to not match, specifying a second pattern area within the second image and decoding an identification pattern of an object included in the second pattern area.
Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title
Physics · mapped topic
Physics · mapped topic
Physics · mapped topic
Input by product or record sensing, e.g. weighing or scanner processing · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.