Image classification and information retrieval over wireless digital networks and the internet
A method and system for matching an unknown facial image of an individual with an image of a celebrity using facial recognition techniques and human perception is disclosed herein. The invention provides a internet hosted system to find, compare, contrast and identify similar characteristics among two or more individuals using a digital camera, cellular telephone camera, wireless device for the purpose of returning information regarding similar faces to the user. The system features classification of unknown facial images from a variety of internet accessible sources, including mobile phones, wireless camera-enabled devices, images obtained from digital cameras or scanners that are uploaded from PCs, third-party applications and databases. Once classified, the matching person's name, image and associated meta-data is sent back to the user. The method and system uses human perception techniques to weight the feature vectors.
1. A method for matching an unknown image with a known image, the method comprising:
receiving, at a server that includes a neural network, an unknown facial image from a video camera within a video surveillance system;
processing the unknown facial image at the server to create a first set of variables that represent the unknown facial image;
comparing the first set of variables to a plurality of additional variables stored in a database, the plurality of additional variables including a second set of variables representing a known facial image;
determining a match value based at least in part on match prediction carried out by algorithmically employing the first set of variables and the second set of variables within the neural network; and
selectively and concurrently displaying the unknown facial image and the known facial image on a wireless communication device when a match exists based at least in part on an indication provided by the match value.
2. The method of claim 1 wherein the neural network is a high-dimensional neural network.
3. The method of claim 1 wherein the wireless communication device is a wireless mobile telephone.