156results about How to "Reduce recognition" patented technology

A method of providing information including providing a communication session of at least one of audio and video media and applying automatic recognition to media transferred on the communication session. An advertisement is selected by a processor, based on the automatic recognition and non-advertisement information is selected by the processor, responsive to the automatic recognition. The selected advertisements and the selected non-advertisement information, are presented during the communication session.

A personal identification device and method prevent the reduction in the finger vein recognition rate which otherwise occur due to erroneous insertion of a finger by a user not accustomed to operation or insertion of a false finger at low cost. The device includes an imager picking up an image of a finger vein pattern, a light source emitting light adapted to be transmitted through the finger, an image operating unit matches the image, guides indicating the position of picking up the finger image, a detector detecting the contact between the finger and the guides, another light source radiating light reflected from the thick of the finger, a switch which is depressed by the forward end of the finger, a further light source emitting light transmitted through the forward end of the finger, and a light-sensor receiving the light from the further light source through the finger.

A computer (16) for capturing a colored moving image photographed by photographing means (14, 15) has an extraction means for extracting images having necessary swing postures as check-point images from a large number of still images constituting the color moving image; a means for obtaining a coordinate of a position of each of attention-focused points, which operate, in each of the check-point images, while a golfer (11) is swinging; a means for diagnosing a golfer's swing form by setting a plurality of diagnosis items for each trajectory pattern obtained by a ball motion measuring apparatus (20) to classify behavior of a golf ball and by comparing numerical data generated from data of the coordinate of the position of each of the attention-focused points with a judgement value set in each of a plurality of diagnosis items; and a means for outputting an advice drill corresponding to a result of a diagnosis.

Methods and apparatuses are provided for facilitating gesture recognition. A method may include constructing a matrix based at least in part on an input gesture and a template gesture. The method may further include determining whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold. In an instance in which the relationship does not satisfy the predefined threshold, the method may also include eliminating the template gesture from further consideration for recognition of the input gesture. In an instance in which the relationship satisfies the predefined threshold, the method may further include determining a rotation matrix based at least in part on the constructed matrix. Corresponding apparatuses are also provided.

A system and method for diminishing false positive classifications of unsolicited electronic-mail is disclosed. An electronic-mail message is received whereby a set of message classifiers are applied the message. One or more signatures indicative of unsolicited electronic-mail based on at least the application of the aforementioned classifiers is generated. The one or more signatures are applied to subsequently incoming electronic-mail messages whereby unsolicited electronic-mail may be more accurately identified and false positive identification of normal electronic-mail messages are reduced.

The invention provides compositions containing hemoglobin, particularly PEGylated hemoglobin. The PEGylated hemoglobin molecule is capable of transferring oxygen or carbon monoxide bound thereto to a tissue with which it is in proximity. Exemplary PEGylated hemoglobin formulations of the invention are virally inactivated. Various compositions of the invention include deoxygenated hemoglobin, which may be conjugated with one or more water-soluble polymer. PEGylated hemoglobin includes those species in which the iron atom of the hemoglobin molecule is not bound to oxygen or any other species, and hemoglobin molecules in which a species other than oxygen, e.g., carbon monoxide, is bound to the iron atom. The compositions of the invention are formulated as hypo-, iso- or hypertonic solutions of the PEGylated hemoglobin. The compositions are of use to treat and / or ameliorate disease, injury and insult by providing for the oxygenation of tissues and / organs.

The invention discloses a visual capture method and device based on a depth image and a readable storage medium. The method comprises steps that a point cloud image is acquired through a depth cameraKinect, the acquired point cloud image is segmented through an RANSAN random sampling consensus algorithm and an Euclidean clustering algorithm, and an identification-needing target object is acquiredthrough segmentation; 3D global characteristics and color characteristics of the object are respectively extracted and are fused to form a new global characteristic; off-line training of a multi-class support vector machine classifier SVM is carried out through utilizing the new global characteristic of the object, category of the target object is identified through utilizing the trained multi-class support vector machine classifier SVM according to the new global characteristic; then the category and the grasping position of the target object are determined; and lastly, according to the category of the target object and the grasping position of the target object, a manipulator and a gripper are controlled for grasping the target object to the specified position. The method is advantagedin that the target object can be accurately identified and grasped.

A system and method for generating dynamic grammars for use by a speech recognition system in response to signals from sensors indicative of the position and / or movement of a vehicle or platform, such as an aircraft or helicopter.

An image display unit having a back-side substrate on which a number of electron emission elements are arranged, and a front-side substrate which is opposed to a back-side substrate and has fluorescent patterns and light-shielding patterns arranged at positions corresponding to electron emission elements, wherein a marking area is provided at least two locations in an ineffective part of the inside of the front-side substrate, corresponding to alignment marks of a dry plate, and each marking area has three alignment marks. According to the present invention, it is unnecessary to change R, G, B masks whenever three color fluorescent patterns are exposed, and realignment between a mask and a substrate is unnecessary.

The invention discloses a method for identifying an image with a watermark and an identifying system. The method includes the steps of selecting all candidate watermark areas of an image to be identified, identifying watermarks on each candidate watermark area through a deep convolution neural network classifier to determine whether the image to be identified is an image with a watermark, and realizing identification of images with watermarks. Lots of image training data can be conveniently and rapidly obtained, and a deep convolution neural network classifier is established through a convolution neural network algorithm via the image training data to solve the problem of insufficient training data in the prior art. The deep convolution neural network classifier established in the invention effectively simulate a visual processing system of human eyes, can identify local fine watermark texture, and effectively solves the problem of small area, light color and high transparent level of watermark in an image with a watermark. A process for identifying areas without watermarks can be reduced, the identification time is shortened, and identification efficiency is improved.

An unmanned aerial vehicle-based expressway violation monitoring system, including a flight control subsystem, a violation monitoring subsystem, an information transmission subsystem, and a road information release subsystem; the flight control subsystem controls the flight route, flight height and flight speed The violation monitoring subsystem processes the collected images, obtains the emergency lane occupancy of the expressway, and transmits the photos of the violation (or emergency rescue) situation, the license plate number of the violation vehicle and the road section information of the violation vehicle to the information transmission subsystem; The information transmission subsystem sends the received picture data together with the illegal license plate number and illegal road section information through the wireless transmission module; the road information publishing subsystem receives the information and stores the processed picture, illegal license plate number and illegal road section information in the expressway Publication in the database of the highway management department or on the road information publishing platform.

An image based motion gesture recognition method and system thereof are disclosed. In embodiment, a hand posture detection is performed according to the received image frames, to obtain a first hand posture. It is then determined whether the first hand posture matches a predefined starting posture or not. If the first hand posture matches said predefined starting posture, movement tracking is performed according to hand locations on image frames, to obtain a motion gesture. During said movement tracking, the hand posture detection is performed according to said image frames to obtain a second hand posture, and it is determined whether the second hand posture matches a predefined ending posture. If the second hand posture matches the predefined ending posture, the movement tracking is stopped. Therefore, reduce complexity motion gesture recognition can be reduced and the reliability in interaction can be improved.

An image based motion gesture recognition method and system thereof are disclosed. In embodiment, a hand posture detection is performed according to the received image frames, to obtain a first hand posture. It is then determined whether the first hand posture matches a predefined starting posture or not. If the first hand posture matches said predefined starting posture, movement tracking is performed according to hand locations on image frames, to obtain a motion gesture. During said movement tracking, the hand posture detection is performed according to said image frames to obtain a second hand posture, and it is determined whether the second hand posture matches a predefined ending posture. If the second hand posture matches the predefined ending posture, the movement tracking is stopped. Therefore, reduce complexity motion gesture recognition can be reduced and the reliability in interaction can be improved.

Embodiments of the present invention provide a communication fraud identification method and system. The method includes: obtaining a real-time bill, where the real-time bill includes at least a calling number and a called number; if it is determined that the calling number meets a preset condition, obtaining user behavior data related to the called number within a preset time, where the user behavior data includes at least communication data, base station data, signaling data, and service data that are related to the called number; generating a user behavior vector of the called number according to the user behavior data; determining a judgment model corresponding to the user behavior vector in a preset judgment model pool according to the user behavior vector; and determining whether a call corresponding to the real-time bill is a fraudulent call according to the judgment model. In embodiments of the present invention, the real-time bill is identified by using the user behavior datarelated to the called number within the preset time, so that identification of the fraudulent number that appears for the first time or only once is implemented, and time validity of communication fraud identification is improved.

A method of providing information including providing a communication session of at least one of audio and video media and applying automatic recognition to media transferred on the communication session. An advertisement is selected by a processor, based on the automatic recognition and non-advertisement information is selected by the processor, responsive to the automatic recognition. The selected advertisements and the selected non-advertisement information, are presented during the communication session.

The invention provides compositions containing hemoglobin, particularly PEGylated hemoglobin. The PEGylated hemoglobin molecule is capable of transferring oxygen or carbon monoxide bound thereto to a tissue or red blood cells with which it is in proximity. Exemplary PEGylated hemoglobin formulations of the invention are virally inactivated. Various compositions of the invention include hemoglobin, which may be conjugated with one or more water-soluble polymer. PEGylated hemoglobin includes those species in which the iron atom of the hemoglobin molecule is not bound to oxygen or any other species, and hemoglobin molecules in which a species other than oxygen, e.g., carbon monoxide, is bound to the iron atom. The compositions of the invention are formulated as hypo-, iso- or hypertonic solutions of the PEGylated hemoglobin. The compositions are of use to treat and / or ameliorate disease, injury and insult by providing for the oxygenation of tissues and / organs.

A face identification system includes a face data generator to generate face data of an objective person and a face data register to register the face data to be stored in a temporary face data storage, which stores the face data as reference face data. The system also includes a face identifier to identify the face of the objective person by comparing the face data with the reference face data. The system also includes a robot mechanism to move to plural areas, a data base to store face data of plural persons and a controller to transmit the retrieved face data from the data base as reference face data to the robot. By this system configuration, the face identification can be correctly carried out and improved in its process speed.

Methods and apparatuses are provided for facilitating gesture recognition. A method may include constructing a matrix based at least in part on an input gesture and a template gesture. The method may further include determining whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold. In an instance in which the relationship does not satisfy the predefined threshold, the method may also include eliminating the template gesture from further consideration for recognition of the input gesture. In an instance in which the relationship satisfies the predefined threshold, the method may further include determining a rotation matrix based at least in part on the constructed matrix.

Inputting speech includes receiving feature information obtained by a client, the feature information comprising speech signals and user feature image signals, recognizing first candidate recognition data matching the user feature image signals, determining target recognition data based at least on the first candidate recognition data, and outputting the target recognition data.

A speech processing system has an arbitrary number of speech recognition modules (Ei, i=1 . . . n) and speech output modules (Aj, j−1 . . . m). The modules provided respectively for a particular type of speech recognition or, respectively, speech output are selected and activated and parameterized according to the situation of application, dependent on an input signal (ES), by a device (MA) for selecting the modules, so that the selected modules are applied for speech recognition or, respectively, speech output corresponding to their construction.

Systems and methods that facilitate the de-speckling of a laser source in a projection televisions. In a preferred embodiment, laser light from a laser source strikes first and second mirrors on its way to a spatial light modulator and projection optics. Preferably the mirrors are incompletely flat, and preferably move or are caused to rotate. The mirrors preferably deviate from flatness by an amount of at least one or more wavelengths, and rotate at a rate different than the video frame rate and at different rates from one another to ensure that light encountering the deviation of the first mirror strikes the second mirror at a different location than on the first mirror. As the coherent light is reflected by the mirrors the path length it takes continuously changes thereby continuously changing the phase of the light striking the screen causing the bright spots in a speckle pattern to continuously disappear and reappear elsewhere on the screen.

The present invention relates to computer-implemented methods for finding patterns in patterns in a set of k-sequences of symbols (where k≧2) and to a computer readable medium having instructions for controlling a computer system to perform the methods. Patterns of symbols common to each 2-tuple of sequences are identified. Each identified pattern of symbols is represented by a position index binary array (PIBA) which is a set of binary digits. The binary digit in each place in the array that corresponds to a location in a selected reference sequence of a symbol in the identified pattern has a first predetermined binary value. All of the other binary digits in the array have a second predetermined binary value. The position index binary array (PIBA) representations of patterns of each tuple at any order “n” may be combined with the PIBA pattern representations of all other tuples at that same order “n” or with the pattern representations in any selected m-tuple, where m may have any integer value from 2 to (n−1). The patterns of the resulting tuple are identified from the position index binary arrays (PIBAs) produced by the intersection of the set of binary digits in each position index binary array (PIBA) in the n-tuple with the set of binary digits in each position index binary array (PIBA) in the other tuple. The intersections are accomplished logically, as by performing a logical AND operation in a bit-by-bit manner on the binary arrays. Using the places in the position index binary array (PIBA) produced by the intersections having the first predetermined binary value as a guide, the symbols in corresponding locations in the reference sequence are identified. These symbols comprise the symbols in the identified pattern in the resulting tuple.

The invention relates to a security check and identification system and a control method thereof. According to the security check and identification system based on integration of a reinforcement learning algorithm and an attention area generation network comprises an object feature extraction module, a hazardous article region segmentation module, a preliminary classification module, a preliminary classification result determination module, and a fine graining identification module. According to the invention, with optimization of the hazardous article region segmentation module and setting of the fine graining identification module, the security checking accuracy and security checking efficiency are improved substantially; the security checking time is shortened; the congestion situationis alleviated; the manpower resources are saved; and the work pressure of the security checking staff is reduced.

Based on posture / motion information obtained from predetermined detection means for detecting a posture or a motion of an input device operated by a user, a virtual plane is calculated at a predetermined timing and set as reference plane. Then, based on motion information, the posture of the input device is calculated as necessary. In accordance with the posture of the input device with respect to the reference plane, predetermined game processing such as moving an object in a virtual space or the like is executed.

The invention discloses a method for establishing context-aware applications and a user terminal. The method includes: acquiring establishing instructions used for establishing the context-aware applications, wherein the establishing instructions include establishing factors generated from user input and / or the user terminal; according to the establishing factors, determining at least one terminal equipment relevant to the establishing factors, and acquiring context information and action messages of at least one terminal equipment; generating at least one operating items according to the context information and the action massages of at least one terminal equipment; generating the context-aware applications according to at least one operating items. By the technical scheme, abstraction, identification and compiling work of application scenarios is reduced when the context-aware applications are established by a user, existing technical problems about tedious development steps and low development efficiency of the context-aware applications are accordingly solved, and beneficial effects of development step simplification and development efficiency improvement are achieved.

The invention discloses an automatic recognition method of a transformer substation touring robot and the touring robot. Graphic image analysis results of an LED display screen and an indicator lamp panel are obtained according to shooting of the touring robot for the LED display screen and the indicator lamp panel, then, the steps of pretreatment, zoning, recognition and output are carried out, accordingly, the information of the LED display screen and the indicator lamp are displayed in a digital mode, and the touring robot can recognize the transformer substation state displayed on an instrument and then outputs the recognized result to engineering technicians. The process of manual image recognition is omitted, the dead zone and mistaken judgment possibly caused by manual operation are avoided, the touring efficiency is improved, the labor cost is saved, and touring stability and reliability are improved.