Abstract: A system and method for classifying facial images from a partial view of a facial image, the method comprising the steps of: training a classifier device for recognizing facial images, the classifier device being trained with input data associated with a facial image of a subject; detecting a partial view of a subject's facial image; warping the partial view of the subject's facial image onto a frontal image to obtain a warped image of the subject; and, classifying the warped image according to a classification method performed by the trained classifier device.

Abstract: A system and method for classifying facial image data, the method comprising the steps of: training a classifier device for recognizing facial images and obtaining learned models of the facial images used for training; inputting a vector of a facial image to be recognized into the classifier, the vector comprising data content associated with one-half of a full facial image; and, classifying the one-half face image according to a classification method. Preferably, the classifier device is trained with data corresponding to one-half facial images, the classifying step including matching the input vector of one-half image data against corresponding data associated with each resulting learned model.

Abstract: A ball-throwing machine includes a camera connected to a computer vision unit and a microphone connected to a speech-processing unit. The computer vision unit processes images from the camera to determine a user's position, and to detect user gestures from a predetermined repertoire of gestures. The speech-processing unit recognizes user vocal commands from a predetermined repertoire of commands. A computer receives information from a control panel, from the computer vision unit, from the speech-processing unit, and from a file describing the ballistic properties of the ball to be thrown. The computer accordingly determines a ball trajectory according to the user's position and parameters indicated by a combination of control-panel settings, user gestures, and user vocal commands. The computer then adjusts the direction, elevation, ball speed, and ball spin to conform to the determined trajectory, and initiates throwing of a ball accordingly.

Abstract: A method and apparatus are disclosed for classifying objects using a hierarchical object classification scheme. The hierarchical object classification scheme provides candidate classes with an increasing degree of specificity as the hierarchy is traversed from the root node to the leaf nodes. Each node in the hierarchy has an associated classifier, such as a Radial Basis Function classifier, that determines a probability that an object is a member of the class associated with the node. The nodes of the hierarchical tree are individually trained by any learning technique, such as the exemplary Radial Basis Function Network, that uses appearance-based information of the objects under consideration to classify objects. A disclosed recognition scheme uses a decision criterion based upon recognition error to classify objects.

Abstract: A system and apparatus are disclosed for modeling patterns of behavior of humans or other animate objects and detecting a violation of a repetitive pattern of behavior. The behavior of one or more persons is observed over time and features of the behavior are recorded in a multi-dimensional space. Over time, the multi-dimensional data provides an indication of patterns of human behavior. Activities that are repetitive in terms of time, location and activity, such as sleeping and eating, would appear as a Gaussian distribution or cluster in the multi-dimensional data. Probability distribution functions can be analyzed using known Gaussian or clustering techniques to identify repetitive patterns of behavior and characteristics thereof, such as a mean and variance. Deviations from repetitive patterns of behavior can be detected and an alarm can be triggered, if appropriate.

Abstract: A method and apparatus are disclosed for automatically learning and identifying events in image data using hierarchical HMMs to define and detect one or more events. The hierarchical HMMs include multiple paths that encompass variations of the same event. Hierarchical HMMs provide a framework for defining events that may be exhibited in various ways. Each event is modeled in the hierarchical HMM with a set of sequential states that describe the paths in a high-dimensional feature space. These models can then be used to analyze video sequences to segment and recognize each individual event to be recognized. The hierarchical HMM is generated during a training phase, by processing a number of images of the event of interest in various ways, typically observed from multiple viewpoints.

Abstract: A method for monitoring a person of interest in a scene, the method comprising: capturing image data of the scene; detecting and tracking the person of interest in the image data; analyzing features of the person of interest; and detecting at least one of an event and behavior associated with the detected person of interest based on the features; and informing a third party of the at least one detected events and behavior.

Abstract: A method and system for the automatic detection of a sleeping person and for adjusting electrical power supplied to a number of electronic devices; it includes a unit for observing the behavior of a person in a predetermined area under surveillance and a unit for analyzing output data from the observing unit to determine whether the observed behavior is associated with predefined sleeping behaviors. Upon recognition that the observed behavior indicates the sleeping state of a person, the electrical power supplied to the plurality of electronic devices is selectively adjusted according to predetermined criteria.

Abstract: System and method for adjusting the position of a displayed image of a person. The system comprises a control unit that receives a sequence of images and processes the received images to determine whether the person is positioned at the border of the received images to be displayed. If so positioned, the control unit generates control signals to control the position of an optical device providing the sequence of images so that the person is positioned entirely within the image.

Abstract: A system employing an automated collaborative filtering process for recommending an item to a viewer based upon feedback data, implicit data, and/or explicit data corresponding to a primary viewer as well as secondary viewers is disclosed. A first act of the automated collaborative filtering process is to match data indicative of a viewing of a first group of items by the primary viewer to data indicative of a viewing of a second group of items by the secondary viewers. A second act of the automated collaborative filtering process is to generate a recommendation of the item by the primary viewer as a function of data indicative of one or more attributes of the item as compared to the data matching accomplished in the first act.

Abstract: A method for aiding a customer in the purchase of clothes on-line. The method including: accessing an Internet web site for the purchase of clothes, the Internet web site having a three-dimensional model of at least one style and size of clothes displayed thereon; providing a three-dimensional model of the customer; selecting the at least one style and size of clothes displayed at the Internet web site; generating a virtual three-dimensional model of the customer wearing the at least one style and size of clothes selected; and displaying the virtual three-dimensional model to the customer.

Abstract: A method for presenting information from telephone messages to a user. The method including the steps of: receiving incoming telephone messages; recognizing speech in the incoming telephone messages by searching the incoming telephone messages for at least one predetermined category of information; and if the at least one predetermined category of information is found in the recognized speech, presenting the at least one predetermined category of information to the user.

Abstract: When a call is placed to an organization seeking information from a representative of that organization, the call is frequently placed on hold for an extended period of time. After the call is made and the called party's telephone is placed on hold, the caller enters a code signal to place the call on hold. At this instant, both telephones are on hold. At some time after this “Hold On Hold” connection is established when a representative of the organization called answers the telephone and speaks to identify himself, the network identifies the signals as being generated by a live person, and a ring signal is sent to the caller's telephone to alert the caller that the call is no longer on hold.

Abstract: A method for automatically assessing interest in a displayed product is provided. The method including: capturing image data within a predetermined proximity of the displayed product; identifying people in the captured image data; and assessing the interest in the displayed product based upon the identified people. In a first embodiment, the identifying step identifies the number of people in the captured image data and the assessing step assesses the interest in the displayed product based upon the number of people identified. In a second embodiment, the identifying step recognizes the behavior of the people in the captured image data and the assessing step assesses the interest in the displayed product based upon the recognized behavior of the people. The method can also include the step of recognizing at least one characteristic of the people identified, which can be performed with or without the assessing step.

Abstract: A method for bidding for the products of a provider. The method including the step of: contacting one or more providers of a product within a predetermined area through a first wireless transmission from a user; initiating a bid for the product with the one or more providers through a second wireless transmission; bidding on the product by the one or more providers; and accepting a lowest bid on the product from one of the one or more providers through a third wireless transmission.

Abstract: A method and apparatus are disclosed for monitoring a retail location using vision-based technologies to recognize predefined fraudulent events. Captured images are processed to identify one or more predefined fraudulent events and to initiate an appropriate response, such as sending notice to an employee for further investigation or recording the event for evidentiary purposes. A number of rules define various fraudulent events. For example, rules can be devised to detect when a patron is wearing stolen clothing out of the changing room, or when a patron is fraudulently attempting to return merchandise without a receipt. Each rule contains one or more conditions that must be satisfied and a corresponding action-item that should be performed when the rule is satisfied. At least one of the conditions for each rule identifies a feature that must be detected in an image using vision-based techniques.

Abstract: Briefly, an alarm system monitors the entry and exit of a fitting room. Various devices, including cameras for imaging, are used to scan customers as they enter and leave. Using image analysis, analysis of the audio signature of footfalls, and other criteria, the system attempts to match the images of customers leaving with stored images of customers entering. If no match can be found, an alarm signal is generated.

Abstract: A video content analysis system extends content analysis capability of one system to multiple channels by providing for the spatial multiplexing of the multiple channels and appropriately analyzing the spatially multiplexed video signal. The resulting system may be lower in cost that present systems and permit the system to work with ancillary equipment such as video recorders. The system also preserves the real-time information inherent in the multiple source signals.

Abstract: A collaborative speed measurement device detection system provides early warning and increased reliability by sharing the responses of multiple detectors through a broadcast radio network. A vehicle with one detector (e.g., radar, laser detector) broadcasts a detection event to any other detectors in its vicinity. The receiving detectors generate a warning signal in response to the broadcast. The receivers can combine the results of multiple detections to generate a reliability estimate. The location of the detection events may be broadcast and used in generating alarms in the receiver as well.

Abstract: Disclosed is a method and system for switching a commercial for a user. Accordingly, the present invention obtains a user's profile or monitors a user's viewing history of various commercials to determine the type of commercials that are not watched or not liked by the user. Thereafter, commercials between television programs are detected during a commercial break and compared with the user's profile or the user's past viewing information to determine whether the detected commercial is liked by the user.