公开(公告)号：EP2697738A4

公开(公告)日：2015-06-24

申请号：EP12770637

申请日：2012-04-15

Applicant: IBM

Inventor： HAAS NORMAN ,  LI YING ,  OTTO CHARLES A ,  PANKANTI SHARATHCHANDRA

IPC: G06K9/00 ,  B61K9/08 ,  B61L23/04

CPC classification number: G06K9/00 ,  B61L23/047 ,  B61L23/048

公开(公告)号：JP2010262653A

公开(公告)日：2010-11-18

申请号：JP2010102964

申请日：2010-04-28

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： SHARATHCHANDRA UMAPATHIRAO PANKANTI ,  CONNELL JONATHAN HUDSON II ,  HAAS NORMAN ,  HAMPAPUR ARUN ,  PATNAIK YASHODHARA M ,  FLICKNER MAYRON DALE

IPC: G06Q50/00

CPC classification number: G07G1/12 ,  G07G1/0018 ,  G07G3/00

Abstract: PROBLEM TO BE SOLVED: To provide visual security for POS terminals. SOLUTION: Items 12 to be purchased is scanned by a store assistant using a barcode reader 16 attached to or positioned near the checkout station. When the items are scanned, they are identified based on the barcodes 14, and added to an item list. Item verification can then be performed at checkout using imaging technology. Specifically, when the items are scanned, an item verification unit 18 captures an appearance thereof. Item verification software 22 within the item verification unit accesses a database that associates items with their images/appearances. The appearance is compared for consistency to the identity as determined based on the scan. The item verification unit is a separate unit from a cash register, but functions in cooperation therewith. COPYRIGHT: (C)2011,JPO&INPIT

Abstract translation: 要解决的问题：为POS终端提供视觉安全。

解决方案：要购买的商品12由商店助理使用连接到或位于结帐台附近的条形码阅读器16进行扫描。 当物品被扫描时，它们基于条形码14被识别，并被添加到项目列表中。 然后可以使用成像技术在结帐时执行项目验证。 具体来说，当物品被扫描时，物品验证单元18捕获其外观。 项目验证单元内的项目验证软件22访问将项目与其图像/外观相关联的数据库。 将外观与基于扫描确定的身份的一致性进行比较。 物品验证单元是与收银机分开的单元，但与其配合起作用。 版权所有（C）2011，JPO＆INPIT

公开(公告)号：AU1503495A

公开(公告)日：1995-11-09

申请号：AU1503495

申请日：1995-03-23

Applicant: IBM

Inventor： BOLLE RUDOLF MAARTEN ,  CONNELL JONATHAN HUDSON ,  HAAS NORMAN ,  MOHAN RAKESH ,  TAUBIN GABRIEL

IPC: G06T1/00 ,  G06K9/46 ,  G06T7/00 ,  G07G1/00 ,  G06T7/60

Abstract: The present system and apparatus uses image processing to recognize objects within a scene. The system includes an illumination source for illuminating the scene. By controlling the illumination source, an image processing system can take a first digitize image of the scene with the object illuminated a higher level and a second digitized image with the object illuminated at a lower level. Using an algorithm, the object(s) image is segmented from a background image of the scene by a comparison of the two digitized images taken. A processed image (that can be used to characterize features) of the object(s) is then compared to stored reference images. The object is recognized when a match occurs. The system can recognize objects independent of size and number and can be trained to recognize objects that it was not originally programmed to recognize.

公开(公告)号：ES2151000T3

公开(公告)日：2000-12-16

申请号：ES95102666

申请日：1995-02-24

Applicant: IBM

Inventor： BOLLE RUDOLF MAARTEN ,  CONNELL JONATHAN HUDSON ,  HAAS NORMAN ,  MOHAN RAKESH ,  TAUBIN GABRIEL

IPC: G06T1/00 ,  G06K9/46 ,  G06T7/00 ,  G07G1/00 ,  G06K9/00 ,  B07C5/10

Abstract: The present system and apparatus uses image processing to recognize objects within a scene. The system includes an illumination source for illuminating the scene. By controlling the illumination source, an image processing system can take a first digitize image of the scene with the object illuminated a higher level and a second digitized image with the object illuminated at a lower level. Using an algorithm, the object(s) image is segmented from a background image of the scene by a comparison of the two digitized images taken. A processed image (that can be used to characterize features) of the object(s) is then compared to stored reference images. The object is recognized when a match occurs. The system can recognize objects independent of size and number and can be trained to recognize objects that it was not originally programmed to recognize.

公开(公告)号：DE102013216892B4

公开(公告)日：2020-08-13

申请号：DE102013216892

申请日：2013-08-26

Applicant: IBM

Inventor： HAAS NORMAN ,  LI YING ,  OTTO CHARLES A ,  PANKANTI SHARATHCHANDRA ,  FUJIJI YUICHI ,  TRINH HOANG

IPC: B61L23/04

Abstract: Verfahren zum Bestimmen einer globalen Position eines observierten Objektes, wobei es sich bei dem observierten Objekt um wenigstens eine fehlende Eisenbahnschienenkomponente oder eine beschädigte Eisenbahnschienenkomponente handelt, wobei das Verfahren aufweist:Beziehen einer ersten globalen Position des observierten Objektes mit wenigstens einer Positionsbestimmungseinheit;Ermitteln, ob ein Satz an gespeicherten visuellen Eigenschaftsdaten wenigstens eines Wegepunktes mit einem Satz an visuellen Eigenschaftsdaten übereinstimmt, der anhand von wenigstens einem aufgenommen Bild bezogen wurde, das eine zu dem observierten Objekt gehörende Szene aufweist;Ermitteln, ob dieses wenigstens eine Bild irgendwelche fehlenden oder beschädigten Eisenbahnschienenkomponenten aufweist, undErmitteln, in Reaktion darauf, dass der Satz an gespeicherten visuellen Eigenschaftsdaten mit dem bezogenen Satz an visuellen Eigenschaftsdaten übereinstimmt, einer zweiten globalen Position des observierten Objektes auf der Grundlage von gespeicherten Standortdaten, die zu dem wenigstens einen Wegepunkt und der ersten globalen Position gehören, wobei die zweite globale Position des Weiteren auf der Grundlage von wenigstens einer Zählung von Eisenbahnschwellen und einer ab einem Bezugspunkt zurückgelegten Entfernung ermittelt wird.

公开(公告)号：DE69518947T2

公开(公告)日：2001-03-22

申请号：DE69518947

申请日：1995-02-24

Applicant: IBM

Inventor： BOLLE RUDOLF MAARTEN ,  CONNELL JONATHAN HUDSON ,  HAAS NORMAN ,  MOHAN RAKESH ,  TAUBIN GABRIEL

IPC: G06T1/00 ,  G06K9/46 ,  G06T7/00 ,  G07G1/00 ,  G06K9/00 ,  B07C5/10

Abstract: The present system and apparatus uses image processing to recognize objects within a scene. The system includes an illumination source for illuminating the scene. By controlling the illumination source, an image processing system can take a first digitize image of the scene with the object illuminated a higher level and a second digitized image with the object illuminated at a lower level. Using an algorithm, the object(s) image is segmented from a background image of the scene by a comparison of the two digitized images taken. A processed image (that can be used to characterize features) of the object(s) is then compared to stored reference images. The object is recognized when a match occurs. The system can recognize objects independent of size and number and can be trained to recognize objects that it was not originally programmed to recognize.

公开(公告)号：AT196695T

公开(公告)日：2000-10-15

申请号：AT95102666

申请日：1995-02-24

Applicant: IBM

Inventor： BOLLE RUDOLF MAARTEN ,  CONNELL JONATHAN HUDSON ,  HAAS NORMAN ,  MOHAN RAKESH ,  TAUBIN GABRIEL

IPC: G06T1/00 ,  G06K9/46 ,  G06T7/00 ,  G07G1/00 ,  G06K9/00 ,  B07C5/10

Abstract: The present system and apparatus uses image processing to recognize objects within a scene. The system includes an illumination source for illuminating the scene. By controlling the illumination source, an image processing system can take a first digitize image of the scene with the object illuminated a higher level and a second digitized image with the object illuminated at a lower level. Using an algorithm, the object(s) image is segmented from a background image of the scene by a comparison of the two digitized images taken. A processed image (that can be used to characterize features) of the object(s) is then compared to stored reference images. The object is recognized when a match occurs. The system can recognize objects independent of size and number and can be trained to recognize objects that it was not originally programmed to recognize.

公开(公告)号：GB2496009B

公开(公告)日：2015-03-04

申请号：GB201213099

申请日：2012-07-24

Applicant: IBM

Inventor： LI YING ,  PALURI BALAMANOHAR ,  OTTO CHARLES ,  PANKANTI SHARATHCHANDRA UMAPATHIRAO ,  FUJIKI YUICHI ,  HAAS NORMAN

IPC: G06K9/62 ,  G06T7/00

Abstract: A system, method, and computer program product for detecting anomalies in an image. In an example embodiment the method includes partitioning each image of a set of images into a plurality of image local units. The method further includes clustering all local units in the image set into clusters, and consequently assigning a class label to each local unit based on the clustering results. The local units with identical class labels having at least one substantially related image feature. Further, the method includes assigning a weight to each of the local units based on a variation of the class labels across all images in a set of images. The method further includes performing a clustering over all images in the set by using a distance metric that takes the learned weight of each local unit into account, then determining the images that belong to minorities of the clusters as anomalies.

公开(公告)号：AU2003268328A1

公开(公告)日：2005-02-14

申请号：AU2003268328

申请日：2003-08-29

Applicant: IBM

Inventor： POTAMIANOS GERASIMOS ,  CONNELL JONATHAN H ,  HAAS NORMAN ,  MARCHERET ETIENNE ,  NETI CHALAPATHY VENKATA

IPC: G10L15/24

Abstract: Techniques for performing audio-visual speech recognition, with improved recognition performance, in a degraded visual environment. For example, in one aspect of the invention, a technique for use in accordance with an audio-visual speech recognition system for improving a recognition performance thereof includes the steps/operations of: (i) selecting between an acoustic-only data model and an acoustic-visual data model based on a condition associated with a visual environment; and (ii) decoding at least a portion of an input spoken utterance using the selected data model. Advantageously, during periods of degraded visual conditions, the audio-visual speech recognition system is able to decode (recognize) input speech data using audio-only data, thus avoiding recognition inaccuracies that may result from performing speech recognition based on acoustic-visual data models and degraded visual data.

公开(公告)号：AU685904B2

公开(公告)日：1998-01-29

申请号：AU1503495

申请日：1995-03-23

Applicant: IBM

Inventor： BOLLE RUDOLF MAARTEN ,  CONNELL JONATHAN HUDSON ,  HAAS NORMAN ,  MOHAN RAKESH ,  TAUBIN GABRIEL

IPC: G06T1/00 ,  G06K9/46 ,  G06T7/00 ,  G07G1/00 ,  G06T7/60

Abstract: The present system and apparatus uses image processing to recognize objects within a scene. The system includes an illumination source for illuminating the scene. By controlling the illumination source, an image processing system can take a first digitize image of the scene with the object illuminated a higher level and a second digitized image with the object illuminated at a lower level. Using an algorithm, the object(s) image is segmented from a background image of the scene by a comparison of the two digitized images taken. A processed image (that can be used to characterize features) of the object(s) is then compared to stored reference images. The object is recognized when a match occurs. The system can recognize objects independent of size and number and can be trained to recognize objects that it was not originally programmed to recognize.