Abstract: A pipeline architecture for analyzing multiple streams of video is embodied, in part, in a layer of application program interfaces (APIs) to each stage of processing. Buffer queuing is used between some stages, which helps moderate the load on the CPU(s). Through the layer of APIs, innumerable video analysis applications can access and analyze video data flowing through the pipeline, and can annotate portions of the video data (e.g., frames and groups of frames), based on the analyses performed, with information that describes the frame or group. These annotated frames and groups flow through the pipeline to subsequent stages of processing, at which increasingly complex analyses can be performed. At each stage, portions of the video data that are of little or no interest are removed from the video data. Ultimately, “events” are constructed and stored in a database, from which cross-event and historical analyses may be performed and associations with, and among, events may be made.

Abstract: A pipeline architecture for analyzing multiple streams of video is embodied, in part, in a layer of application program interfaces (APIs) to each stage of processing. Buffer queuing is used between some stages, which helps moderate the load on the CPU(s). Through the layer of APIs, innumerable video analysis applications can access and analyze video data flowing through the pipeline, and can annotate portions of the video data (e.g., frames and groups of frames), based on the analysis performed, with information that describes the frame or group. These annotated frames and groups flow through the pipeline to subsequent stages of processing, at which increasingly complex analysis can be performed. At each stage, portions of the video data that are of little or no interest are removed from the video data. Ultimately, “events” are constructed and stored in a database, from which cross-event and historical analysis may be performed and associations with, and among, events may be made.

Abstract: A pipeline architecture for analyzing multiple streams of video is embodied, in part, in a layer of application program interfaces (APIs) to each stage of processing. Buffer queuing is used between some stages, which helps moderate the load on the CPU(s). Through the layer of APIs, innumerable video analysis applications can access and analyze video data flowing through the pipeline, and can annotate portions of the video data (e.g., frames and groups of frames), based on the analyses performed, with information that describes the frame or group. These annotated frames and groups flow through the pipeline to subsequent stages of processing, at which increasingly complex analyses can be performed. At each stage, portions of the video data that are of little or no interest are removed from the video data. Ultimately, “events” are constructed and stored in a database, from which cross-event and historical analyses may be performed and associations with, and among, events may be made.

Abstract: A system for authenticating products and/or packages, comprising a unit for acquiring primary configurations which represent meaningful images and for generating secondary configurations for the authentication marking of products and/or packages; a unit for applying the generated secondary configurations to a product and/or package; and a unit for recognizing the secondary configurations applied to the product and/or package. All the units are provided with means for mutual connection in an active configuration for transmitting digital data. A method for authenticating products and/or packages comprises the acquisition of primary configurations which represent meaningful images; the generation of secondary configurations for marking; the application of the generated secondary configurations to a product and/or package; and the recognition of the authenticity of the product and/or package.

Abstract: A technique is disclosed for determining a group in which to add a new image set. The new image set is captured by one or more cameras in a video surveillance system. Similarity scores are generated between the new image set and one or more image sets of a plurality of groups, wherein each group includes one or more image sets of at least one object. The new image set is added to a group based on one or more factors. Also, a technique is disclosed for determining when to close a group, wherein a closed group is one to which an image set may not be added.

Abstract: A technique includes obtaining data indicative of images of a marine seismic source event, which are acquired by underwater cameras and processing the data to determine an attribute (a seismic bubble volume or motion, as non-limiting examples) that is associated with the seismic source event.

Abstract: A system is provided for determining an informational property of wayside equipment adjacent to a route. The system includes a camera to collect visible spectral data of the wayside equipment. The camera is attached to a powered system traveling along the route. The system includes at least one filter to filter a known portion of the visible spectral data based upon known filter properties. The system further includes a controller coupled to the camera, to compare unfiltered visible spectral data with the filtered visible spectral data, in conjunction with the known properties of the filter, to determine the informational property of the wayside equipment. The unfiltered visible spectral data includes the data collected by the camera prior to the at least one filter being applied to the camera. Additionally, a method and computer readable medium are provided for determining an informational property of wayside equipment adjacent to a route.

Abstract: A method for determining a video file such as a television program file is provided. The method comprises receiving information identifying an input image; comparing the input image with a plurality of video files to determine a video file that includes information that is considered to match the input image; and providing access to that video file or otherwise performing an action in response to the determination.

Abstract: A subject judgment program is capable of reducing the calculation load on a computer functioning as a device for judging the subject in a subject image. In a controller of a digital still camera, when a CPU running the subject judgment program (stored in a flash memory) obtains image data from an A/D converter via a first interface circuit, the CPU generates two-dimensional distribution data of product-moment correlation coefficients for each of model image data stored in the flash memory by successively calculating the product-moment correlation coefficient between the model image data and each part of the obtained image data, identifies a piece of model image data corresponding to two-dimensional distribution data having the highest maximum value, and thereby identifies subject information which has been associated with the identified model image data.

Abstract: An apparatus for verifying subjects includes: a camera for photographing a plurality of subjects; a subject detector for detecting subject images of each of the subjects from the pieces of image information photographed by the camera; a subject tracking unit for tracking each of the subjects based on the movement of the subject images corresponding to each of the subjects and for forming tracking information of each of the subjects; a tracking information storage for storing the tracking information of each of the subjects; a subject selector for selecting a subject to be verified from the plurality of subjects based on the tracking information; a verification unit for verifying the selected subject; and a notification unit for notifying the verified result.

Abstract: A system for identifying a user by deriving a digital representation of an analogue form entered by the user, the analogue form being distinctive of the user; and by grading the digital representation against a plurality of grades. The grades are defined dependent upon possible variation in the analogue form. The grades ensure the same grading of the analogue form notwithstanding the variation. The graded digital representation constitutes an identification of the user.

Abstract: An optimized time and attendance system and methods. In some embodiments, a networked time and attendance system includes a network services server with a global database and a client device terminal with a local database. The device terminal is configured to create new time keeping records on the local database using information stored in the local database. The device terminal is further configured to initiate a connection to the host server and synchronize the local database with the global database. In some embodiments, the client terminal is configured to continue creating additional new time keeping records in the local database even when a connection to the host server is unavailable. In some embodiments, the client terminal includes a user interface, a local database, a first processor configured to control all system functions except for biometric data processing, and a second processor configured to capture and process biometric data.

Abstract: In order to eliminate an unauthorized action trying to find out authentication information, a mobile phone 1ncludes a processing execution portion (65) which executes processing corresponding to an operation when the operation is accepted via operation keys, an identification information requesting portion (51) which requests an input of identification information for identification of the operator, an authentication portion (53) which performs authentication of the input identification information, a camera arranged in a position where the operator is included in its image pickup range and outputting image data obtained by picking up an image, an image data acquiring portion (55) which activates the camera to acquire image data when the identification information requesting portion (51) requests an input of identification information, an area extracting portion (57) which extracts an area including an image recognized as a person from the image data, and a mode switching portion (61) which enables execution

Abstract: A security monitoring system for reducing the number of false alarms through verification comprises a remote system at a first location remote from a second location and a local system located at the second location. The remote system comprises a remote database. The local system is electronically linked with the remote system to provide indication of alarm events to the remote system and comprises at least one camera operable to capture at least one image of a local object in view of the camera, a local database operable to electronically store at least one template corresponding to an authorized object, and an image processing system operable to perform a visual verification. The visual verification comprises comparing the at least one image of the local object with the at least one template corresponding to the authorized object and, if a matching result occurs from the visual verification, suppressing indication of an alarm event to the remote system.

Abstract: In the present invention, there is provided a data processing device, including: a first memory configured to store identification information for identification of video data in association with a feature included in the video data; a second memory configured to store the feature included in the video data in association with the identification information for identification of the video data; a first reader configured to read out the identification information stored in the first memory based on a feature included in input video data; a second reader configured to read out the feature stored in the second memory based on the identification information read out by the first reader; and a checker configured to compare the feature included in the input video data with the feature read out by the second reader to determine whether or not the input video data matches video data whose feature is stored in the second memory.

Abstract: An image information management system includes: a reading device which reads unique information from a storage medium in which the unique information is stored; an imaging device which automatically starts shooting a video at a time of detecting a change of a picture image in an image area; and a processing device which includes a database which receives the unique information read by the reading device and the image information shot by the imaging device and associates the unique information and the image information to store the unique information and the image information.

Abstract: A digital still camera records a photographer's biological information on a photographic image reliably and protects the copyright of photographic images without affecting processing, and in a manner transparent to operation, at the time of photographing a subject. Biological information (iris information) that is registered beforehand by the photographer is recorded as personal data on an ID card. If an image is taken in a state in which the ID card bearing the recorded personal data has been inserted into the apparatus, iris information that has been sensed by an iris sensor is checked when a power supply is turned on. If the two compared items of iris information match, the personal data is added onto the image of the photographed subject.

Abstract: Methods and systems for monitoring a brush holder assembly and/or detecting wear of a brush in a brush holder assembly are disclosed. One method includes sending data from a plurality of remote monitoring locations to a central control unit, where the data may be evaluated in order to monitor states of brushes at a plurality of remote electrical facilities. For example, multiple images of a marker tracking longitudinal movement of the brush may be acquired. A comparison of the images, for example, a comparative imaging technique, such as pixel-by-pixel comparison, may then be performed in order to evaluate a condition of the brush, such as the wear rate, wear state, or life expectancy of the brush.

Abstract: A method for reading a license plate disposed on a vehicle includes determining whether a license plate image is required, automatically processing the license plate image in response to determining that the license plate image is required, providing at least one verified image, and determining whether to manually read the license plate image by matching the license plate image with the at least one verified image.

Abstract: A programmable digital camera requiring a programming password to be entered to access the camera's programmability. The camera further includes programming so as to allow the camera to be operated only for a specified time interval, after which the camera becomes inoperable until the programming password is again entered and the camera is programmed to operate for another interval of time. An alternate embodiment of the invention includes a programmable digital camera as above described wherein the camera is programmed to only capture a set number of images, at which point the programming password must again be entered and the camera reset for another quantity of images. A further alternate embodiment includes a camera system with a separate transmitter for radiating a signal designed to cover a designated area, the signal being modulated with a camera operational code. The camera is equipped with a corresponding receiver and demodulator to receive the operational code.

Abstract: A video surveillance system includes clients coupled to servers using a network. The clients generate data, video, and optionally audio. Using the network, clients communicate in real-time the data, video, and optionally audio to the servers for monitoring, analyzing, and reporting on the financial transactions occurring at the clients. The video surveillance system also supports receiving stored data upon connection between the clients and the servers.

Abstract: An information processing apparatus detects the sampling rate of a coordinate input device, and standardizes the writing data which is input from the coordinate input device based on the detected sampling rate. The standardized writing data is further used for signature verification or for handwritten character recognition. The information processing apparatus provides precise signature verification or handwritten character recognition even if signatures or handwritten characters for handwritten character recognition are input using digitizers having different processing rates.

Abstract: When a signature is registered, a signature in Japanese characters, for example, ‘’ (‘Fujitsu’), or a signature in English characters, for example, ‘Fujitsu’ is input n times through an input device of an input equipment of a signature authentication system, and each element of the shape of handwriting, writing speed, writing acceleration, and writing pressure is computed. A combination of nC2 is set for each element of the data input n times, the reciprocal of each similarity is obtained, an average value of the similarity is computed for each element, a weight is determined for each similarity from the average value, a weighted average value of the four elements is computed and defined as the total similarity of the registered signature. In an authenticating process, signature data to be compared is input/output m times. In the same method, the total similarity of a signature to be compared is obtained.

Abstract: A method in image processing for detection of a change in the scene in an area. The method comprises the steps of recording a digital image of the area using a sensor and transforming the recorded image by an operator. The operator is based on a previous modeling of changes in the lighting in the area and on a modeling of how the sensor depicts the area in grayscale values in the recorded image. The method further comprises the step of comparing the transformed image with a reference image of the area in order to detect a difference that indicates a change in the scene.

Abstract: An apparatus and method for performing first and second imaging processes contemporaneously, in particular where one of the processes is detecting fires based on images of the flames. The apparatus includes an image sensor for producing a video image, a frame grabber for capturing first frames and second frames, a processor for processing the data within the frames, and an output device. The apparatus may also include an adjustment mechanism for adjusting the image settings of the image sensor between settings suitable for flame imaging and non-flame imaging, and a control mechanism for controlling the image settings of the image sensor. In the method at least two first frames are obtained, and a plurality of second frames are obtained. The first and second frames are used for first and second processes. The first and second processes are contemporaneous, so that they are carried out within the same time period without interfering with one another.

Abstract: An image data analysis security camera having internal logic circuits and remote user controls. The image data analysis security camera samples an initial image and compares subsequent images thereto, if a deviation between the two images is detected the image data analysis camera will initiate a remote alarm. The image data analysis security camera may also be provided with wireless communication capabilities and an internal battery thereby enabling the user to move the camera to another location quickly and easily.

Abstract: A video surveillance system (10) includes clients (12) coupled to servers (20) using a network (24). The clients (12) generate digital files (14) that may include data (82), video (72), and audio (74). Using the network (24), the clients (12) communicate the digital files (14) to the servers (20) for monitoring, analyzing, and reporting on the financial transactions occurring at the clients (12). The video surveillance system (10) also supports one-way or two-way audio/video conferencing between the clients (12) and the servers (20) using the network (24).

Abstract: When using a digital still camera to sense and capture an image of a medium with a bar code being recorded thereon for indication of information to be input to the digital still camera (such as information indicative of photographing conditions and/or information representing processing conditions of image processing), judgment is done to determine whether a region equivalent to the bar code is present within an image, and then a region equivalent to the bar code is extracted for analyzation of coded information as indicated by such bar code; if no contradiction is found in the coded information then let it be stored in a storage or “memory” region pursuant to the kind of such coded information. And the information thus stored will be used to perform setting of image pickup conditions and/or setup of image processing condition.

Abstract: In an image collection apparatus an image acquisition unit acquires an image, an event detection unit detects an event, an event data creation unit creates event data indicative of at least a generation time and contents of the event detected by the event detection unit, a macro event definition unit defines a macro event including a related event group and having a time width by using the generation time and contents of the event, a macro event data creation unit creates macro event data by structurizing a plurality of event data based on definition contents of the macro event, an image recording unit records an image of a macro event corresponding to the macro event data, a retrieval unit retrieves a desirable macro event based on the macro event data, and a display unit displays the image of the macro event.

Abstract: A method of authenticating a signature including the steps of sampling a signature and storing data representative of the signature, converting the data to high dimensions vectors, feeding the high dimension vectors to an unsupervised neural network, performing a high order principal component extraction process on the high dimensions vectors to thereby identifying clusters of high dimension points, and analyzing the clusters of high dimension points to determine, based on previously stored information, the authenticity of the signature.

Abstract: An information processing apparatus detects the sampling rate of a coordinate input device, and standardizes the writing data which is input from the coordinate input device based on the detected sampling rate. The standardized writing data is further used for signature verification or for handwritten character recognition. The information processing apparatus provides precise signature verification or handwritten character recognition even if signatures or handwritten characters for handwritten character recognition are input using digitizers having different processing rates.

Abstract: A fingerprint collating device and a fingerprint collating method which can prevent an illicit use of fingerprint. The fingerprint collating device includes fingerprint reader for reading a user's fingerprint to create read fingerprint information, and to create read history information indicating that the read fingerprint information has been created, read history storage for storing the read history information, and collator for collating the read fingerprint information with the registered fingerprint information to effect personal authentication and output a result of authentication when the read history information is stored in the read history storage.

Abstract: The present invention relates to an apparatus and a method to detect a moving target. An embodiment of the present invention includes a processor that uses an imaging sensor such as, for example, an electronic camera, and uses images and surveillance system pointing angle information to generate a dynamically changing reference image that is subtracted from the live image, with the result being a moving target.

Abstract: An efficient approach to exploit hyperspectral imagery and detect target of interest is disclosed. This approach uses proximity pixels as reference signatures to detect potential discontinuity that represents material of unknown existing on the terrain. By incorporating signature of a chosen material of interest, this approach provides an effective way for target detection and identification. An evolutionary algorithm is employed to estimate the abundance of material of interest.

Abstract: A digital camera contains biometric capability to identify a photographer, which is preferably provided by the camera's own optical sensors. The biometric feature is preferably the iris of a photographer's eye, which is recognized as unique for each individual. The camera captures an image of an iris, abstracts a set of distinguishing features, and matches this set to an on-board database. The iris image is preferably captured when the photographer brings his eye in the vicinity of the camera's viewing window, through a combination of mirrors, lenses, prisms, and the like. This capability may be used to record the identity of a photographer with the image, as an anti-theft or privacy device, or to personalize the camera settings.

Abstract: A technique of using an electronic device to change light into the facsimile of an image. Signals are generated, indicative of the image shape. An array of electro optical devices are transformed based on the image signals, and those devices are used to transform the light characteristics.

Abstract: A method for transforming three color input signals (R, G, B) corresponding to three gamut defining color primaries to four color output signals (R?, G?, B?, W) corresponding to the gamut defining color primaries and one additional color primary W for driving a display having a white point different from W includes the steps of: normalizing the color input signals (R,G,B) such that a combination of equal amounts in each signal produces a color having XYZ tristimulus values identical to those of the additional color primary to produce normalized color signals (Rn,Gn,Bn); calculating a common signal S that is a function F1 of the three normalized color signals (Rn,Gn,Bn); calculating a function F2 of the common signal S and adding it to each of the three normalized color signals (Rn,Gn,Bn) to provide three color signals (Rn?,Gn?,Bn?); normalizing the three color signals (Rn?,Gn?,Bn?) such that a combination of equal amounts in each signal produces a color having XYZ tristimulus values identical to those of the

Abstract: A camera comprising a memory for storing at least one camera setting for each of at least one user, a user identification sensor for identifying at least one of the at least one user of the camera, and a processor for controlling the camera according to the stored at least one camera setting in response to a signal from the sensor. Alternatively, a camera may comprise means for identifying at least one user of the camera, and means for automatically controlling the camera according to the identification of the user.

Abstract: A traffic sensor system for detecting and tracking vehicles is describede. A video camera is employed to obtain a video image of a section of a roadway. Motion is detected through changes in luminance and edges in frames of the video image. Predetermined sets of pixels (“tiles”) in the frames are designated to be in either an “active” state or an “inactive” state. A tile becomes active when the luminance or edge values of the pixels of the tile differ from the respective luminance or edge values of a corresponding tile in a reference frame in accordance with predetermined criteria. The tile becomes inactive when the luminance or edge values of the pixels of the tile do not differ from the corresponding reference frame tile in accordance with the is predetermined criteria. Shape and motion of groups of active tiles (“quanta”) are analyzed with software and a neural network to detect and track vehicles.

Abstract: In a vehicle time-of-entry and time-of-exit system, the passing of a vehicle through an entrance generates a “trigger-t0” signal. An entrance video camera provides realtime images of entering vehicles. The trigger-t0 signal causes one video frame of the image of vehicle to be stored or “frame-grabbed” in an entrance subsystem. A time-of-entry clock-time signal is used to time-stamp the image which is then forwarded on a connection to a matcher. The passing of a vehicle through an exit generates a “trigger-t1” signal. An exit video camera 116 provides realtime images of exiting vehicles. The trigger-t1 signal causes one video frame of the image of vehicle to be stored or “frame-grabbed” in an exit subsystem. A clock-time signal is used to time-stamp the image which is then forwarded on a connection to the matcher. A output automatically provides a length-of-stay for each exiting vehicle according to its time-of-entry.

Abstract: A tailgating safety system for a vehicle includes a distance determiner for determining a distance of the vehicle from objects which are leading or following the vehicle. The system also includes a speedometer for determining a speed of the vehicle and an alarm. If the speed of the vehicle is greater than a predetermined speed, and the distance of the vehicle from another object is less than a predetermined distance, then the alarm is activated to advise the driver that at the speed the vehicle is traveling, the distance between the vehicle and the object is not a safe traveling distance.

Abstract: An opto-electronic apparatus for the monitoring of a protection area which has at least one protection device, which works in a non-contact manner, is described. The protection device, which works in a non-contact manner, has an evaluation unit for the generation of an object detection signal on the intrusion of an object into the protection area. An image detection unit is coupled to the protection device, which works in a non-contact manner, for the detection of an areal or spatial image detection area, with a secondary monitoring area disposed close to the protection area, but outside the protection area, being detected by the image detection unit. The protection device, which works in a non-contact manner, is controllable by the image detection unit.

Abstract: A fuel dispenser and method to detect the presence of a human being at a fuel dispenser as well as gather data about the human being using the fuel dispenser. The data is used to determine the language or dialect of the fueling instructions as well as the language or dialect of the advertisements understood by the human being. The data is also used to retrieve advertisements tailored to the human being. The fueling instructions and advertisements are displayed on the fuel dispenser in the language or dialect understood by the human being using the fuel dispenser.

Abstract: Disclosed is a vehicle antitheft device not requiring a contract with a security company, etc., and increasing a vehicle antitheft effect. In the vehicle there are provided a camera 4 or a microphone, and a control device 2 for distinguishing a face or voice of a fuman by means of an image or sound captured by the camera 4 or microphone, and based on distinction results, executing vehicle theft prevention control operations. The camera 4 is provided at a position capable of capturing a normally seated driver and the outside through a window next to a driver's seat. Further, in the vehicle there is provided a radio communications unit. The control device 2 records the captured image from the camera, judges whether the it is the face image of the person, and if it is, performs control so that the image is sent to a given reporting destination via the radio communications unit.

Abstract: Digitized signatures are recorded in respective digitized signature records. Each digitized signature record includes at least the position of each point of a signature in coordinates relative to a coordinate of a previous point thereof and time. Digitized signatures are identified, verified or authenticated by comparing characteristics thereof, may be indexed for facilitating comparison, may be utilized for network and Internet transactions, and may be converted to image format.

Abstract: A method of authenticating a signature including the steps of sampling a signature and storing data representative of the signature, converting the data to high dimensions vectors, feeding the high dimension vectors to an unsupervised neural network, performing a high order principal component extraction process on the high dimensions vectors to thereby identifying clusters of high dimension points, and analyzing the clusters of high dimension points to determine, based on previously stored information, the authenticity of the signature.

Abstract: A system for determining a kind of vehicle and a method therefore, including a vehicle detection unit for detecting a vehicle which reaches to a vehicle detection region on a roadway, a wheel shaft number counting unit for counting a number of wheel shafts of the detected vehicle, an image photographing unit for photographing a front or rear image of the detected vehicle and a vehicle kind determination unit for yielding distances and widths of the tires of the detected vehicle on the basis of the photographed image from the image photographing unit and determining the kind of the vehicle on the basis of the number of wheel shafts detected from the wheel shaft counting unit and the yielded distance and width values can precisely determine the kind of vehicle traveling the roadway.

Abstract: Terrorist attacks, threats, or hoaxes, in which there is the possibility of nuclear, biological, and chemical (NBC) attacks, disease, terrorism, civil unrest, disobedience, hostage standoffs, or the like, may require large numbers of victims and suspected cases to be processed through mass decontamination lines prior to mass casualty care. Perpetrators may also attempt to lose themselves in large crowds and hide among the victims, or among bystanders, when the crime scene is cordoned off by the authorities. Accordingly, an evidence collection station is disclosed, along with a method of collecting evidence as victims and suspected cases process through decontamination lines. The evidence collection system preferably includes the collection of videometric and biometric data, along with the tracking of physical evidence recovered from victims and suspected cases.

Abstract: A method 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: In a face image recording apparatus, a camera photographs the face of a person a plurality of number of times, a processor extracts at least one high-quality image from the plurality of images photographed by the camera, and this high-quality image extracted by the processor is recorded in a memory.