Abstract: Systems and methods for high fidelity multi-modal out-of-band biometric authentication are disclosed. According to one embodiment, a method for multi-mode biometric authentication may include (1) receiving, at a computer application executed by an electronic device, a first input from a first input device on the electronic device; (2) receiving, at the computer application, a second data from a second input device on the electronic device; (3) receiving, at the computer application, a third input from a third input device on the electronic device; and (4) communicating, by the computer application and to a server, the first input, the second input, and the third input. The first input, second input and third input may be received within a predetermined time period, such as five seconds.
Abstract: An authentication method in a system having a display and a storage device is provided. The authentication method includes the steps of registering an object selected for each user from among a plurality of visually distinguishable objects prepared in advance as a key object in the storage device; and presenting the plurality of objects to the display, accepting selection of an object by a user to be authenticated, and performing authentication based on matching/mismatching of the selected object with the key object registered in association with the user. The step of registering includes a step of determining a degree of freedom of selection of the object at the time of registration of the key object according to a degree of overlapping of the key object already registered in the storage device.
Abstract: A method and apparatus for enabling multimodal tags in a communication device is disclosed. The method comprises receiving a first training signal and receiving a second training signal in conjunction with the first training signal. A multimodal tag is created to represent a combination of the first training signal and the second training signal and a function is associated with the created multimodal tag.
Abstract: A method of accessing an Extensible Hypertext Markup Language Plus Voice Web page can include the step of receiving a request for an Extensible Hypertext Markup Language Plus Voice Web page from a source that lacks the ability to directly render the Web page. The Web page can be segmented into a multitude of fragments, where each fragment can consist of a single interface category, such as a graphical user interface category or a voice category. These fragments can be used to provide the requesting source with information from the Web page.
Type:
Grant
Filed:
December 10, 2003
Date of Patent:
October 7, 2008
Assignee:
International Business Machines Corporation
Inventors:
Chang Yan Chi, James J. Sliwa, Hui Su, Leslie R. Wilson, Shi Wan Zhao