System and method for biometric authentication in connection with camera equipped devices

Abstract

The present invention relates generally to the use of biometric technology for authentication and identification, and more particularly to non-contact based solutions for authenticating and identifying users, via computers, such as mobile devices, to selectively permit or deny access to various resources. In the present invention authentication and/or identification is performed using an image or a set of images of an individual's palm through a process involving the following key steps: (1) detecting the palm area using local classifiers; (2) extracting features from the region(s) of interest; and (3) computing the matching score against user models stored in a database, which can be augmented dynamically through a learning process.

1 . A system for providing selective access to resources available in connection with a device comprising software executed on suitable computer hardware, said system comprising:
 (a) at least one camera associated with said device, said camera being capable of taking at least one photograph of a human palm print;   (b) a detector module using local classifiers to locate and segment the region of interest of the palm without physical contact;   (c) a conversion processor which converts raw pixel data associated with said region of interest of a human palm print into a unique signature associated with said palm print; and   (d) an authentication and identification engine, said authentication and identification engine determining whether access to one or more of said resources should be granted based upon said unique signature and at least one database containing a plurality of user models.   
     
     
         2 . The system of  claim 1 , further comprising a learning processor that improves the user models with new data, wherein the learning processor selectively includes said palm print image to augment said database and said authentication and identification engine. 
     
     
         3 . The system of  claim 1 , wherein said device is a mobile device, a desktop device, or a stationary embedded device. 
     
     
         4 . The system of  claim 1 , wherein said device includes a flash component that selectively activates at the time of image capture to provide minimum sufficient light for region of interest detection, feature extraction, and signature processing of the human's palm image. 
     
     
         5 . The system of  claim 1 , wherein the conversion processor uses descriptors extracted from patches over the region of interest. 
     
     
         6 . The system of  claim 1 , wherein the descriptors are encoded into high dimensional sparse vectors and wherein the sparse vectors are pooled into at least one group. 
     
     
         7 . The system of  claim 1 , wherein the signature is computed from a Bag of Features or multiple Bags of Features representations. 
     
     
         8 . The system of  claim 1 , wherein the detector module uses Haar Wavelets and AdaBoost algorithms. 
     
     
         9 . The system of  claim 1 , wherein the detector module uses support vector machines, a convolutional neural network, or both. 
     
     
         10 . The system of  claim 1 , wherein the user model is a statistical model computed from a collection of a human's palm images. 
     
     
         11 . The system of  claim 1 , wherein the user model is a Gaussian density model or a mixture of Gaussians density model. 
     
     
         12 . The system of  claim 1 , wherein at least one of the resources is remote from the device or resident on the device. 
     
     
         13 . The system of  claim 1 , wherein said at least one of the resources is an application or a database. 
     
     
         14 . The system of  claim 1 , wherein the individual signatures of each of both palm print images of a human, if available, are utilized together for authentication or identification of the human. 
     
     
         15 . The system of  claim 1 , wherein palm print authentication or identification is combined with other modalities. 
     
     
         16 . The system of  claim 15 , wherein the other modalities include one or more of the following: passcodes, security questions, fingerprint recognition, facial recognition, iris recognition, written signature recognition, and other biometric and non-biometric modalities. 
     
     
         17 . The system of  claim 1 , wherein an application selectively permits one or more users to conduct one or more transactions. 
     
     
         18 . The system of  claim 1 , wherein a sequence of flash and non-flash images of the human's palm are utilized as part of an anti-spoofing mechanism to determine whether the presented hand is a 3-D object or a 2-D representation of a hand. 
     
     
         19 . The system of  claim 1 , wherein image data captured during movement of the human's palm are utilized as part of an anti-spoofing mechanism to determine whether the presented hand is a 3-D object or a 2-D representation of a hand. 
     
     
         20 . The system of  claim 1 , wherein the sequence of flash and non-flash images of the human's palm as well as the time interval(s) between successive images are utilized as part of an anti-spoofing mechanism to determine whether an adversary is attempting to utilize a previously-recorded sequence of images for authentication or identification. 
     
     
         21 . The system of  claim 1 , wherein all of a human's previously used images are stored for comparison against new images as part of an anti-spoofing mechanism to determine whether an adversary is attempting to utilize previously-recorded images for authentication or identification. 
     
     
         22 . The system of  claim 1 , wherein transaction information or other data is embedded within the timing of a sequence of images and/or flash patterns as part of an anti-spoofing mechanism to determine whether the image sequence provided for authentication or identification matches the information from the transaction itself.