68results about How to "Reduce false reject rate" patented technology

A plurality of iris codes are registered for each registrant in an iris database (12) together with pupil diameter-iris diameter ratio R. At the time of authentication, an iris code is obtained from a captured iris image by feature extraction while pupil diameter-iris diameter ratio R is obtained. Ratio R obtained at the time of registration and ratio R obtained at the time of authentication are compared to specify an appropriate iris code from the iris database (12) as an item to be collated before authentication.

A cryptographic system for reproducibly establishing a reliable data string, such as a cryptographic key, from a noisy physically unclonable function (PUF, 110) is provided. The system comprises a hard decision decoder (150) to decode a first multiple of error correctable data words to obtain a second multiple of corrected and decoded data words and a reliability information extractor (180) to determine reliability information, e.g. soft decision information, that is indicative of a reliability of corrected and decoded data words. The system further comprises a soft decision decoder (160) configured to use the reliability information to decode at least one further correctable data word. Error correcting a PUF using reliability information decreases the false rejection rate.

The embodiment of the present invention discloses a fingerprint identification device and an electronic device. The fingerprint identification device is applied to an electronic device having a display screen, the fingerprint recognition device comprising an optical fingerprint sensor module, wherein the optical fingerprint sensor module is configured to be disposed under the display screen such that the fingerprint collection area is at least partially located in the display area of the display screen. The optical fingerprint sensor module comprises a plurality of sensor chips, and the sensing areas of the plurality of sensor chips respectively correspond to a plurality of sub-areas in the fingerprint collection area, wherein each sensor chip is used for detecting optical signals from above their corresponding sub-areas. The technical solution of the embodiment can improve the user experience in the fingerprint identification process and simultaneously improve the security of fingerprint recognition.

The invention discloses a method for protecting mobile terminal privacy based on voiceprint recognition. The method comprises the following steps: analysis and extraction of voice message characteristics, model training and voiceprint recognition. In the method, the efficiency of the voiceprint recognition is high, and the performances and the recognition efficiency of the voiceprint recognition are not associated with the texts and the language. The voice length of a speaker is not required specially, and only voice messages in minutes are required so as to acquire the voice feature messages of the speaker, thereby carrying out the model training and the recognition. Applications of a voiceprint recognition algorithm in the intelligent mobile terminal have the advantages of high stability and recognition accuracy, and a voice feature model which is trained occupies small memory space of the intelligent mobile terminal. The method can be utilized to preferably protect the private information of a user in the intelligent mobile terminal and avoid the private information from being revealed and stolen when a mobile phone is lost.

In a geo-security system, a device receives RF signals from multiple distinct classes of RF communication systems and extracts location-dependent signal parameters. A current geotag is computed from the parameters by fuzzy extractors involving quantization of the parameters and Reed-Solomon decoding to provide a reproducible unique geotag. The current geotag is compared with a stored geotag, and a geo-secured function of the device is executed based on the result of the comparison. The use of multiple signal sources of different types, combined with special fuzzy extractors provides a robust geotag that allows both lower false rejection rate and lower false acceptance rate.

An identity recognition system and method capture an image of a subject that is projected by light of different wavelengths, extract various biometric informations from the image, analyze and compare for each of the biometric informations to generate a matching score, and determine an identity for the subject according to all of the matching scores. The system and method have higher recognition accuracy, lower false acceptance rate, lower false rejection rate, and higher flexibility.

A method and system of irradiating a liquid-carrying container for inspection, including rotating the container, its contents or both around a rotation axis and irradiating the container with an electromagnetic radiation beam, wherein the irradiated cross-section of the container, irradiated by the electromagnetic radiation beam, is less than the cross-section of the container; and, a method and system for inspecting a liquid-carrying container for one or more test parameters of the container, the contents of the container, or both, including rotating the container, the contents or both around a rotation axis, irradiating the container with an electromagnetic radiation beam from a first direction along an irradiation center plane substantially parallel to the rotation axis, capturing a representation of a section of the container from a second direction along a detection center plane substantially parallel to the rotation axis, and processing the representation, wherein the irradiated cross-section of the container, irradiated by the electromagnetic radiation beam, is less than the cross-section of the container.

The invention provides an identity authentication method of an identity card and a holder based on multi-biological characteristics. The invention mainly assists in solving potential safety hazard problems existing in a cross-application process in the prior art. An embodiment comprises the steps that: when identity card registration transaction is carried out, characteristics of fingerprints, iris information and face image of a citizen are acquired; a uniform matrix image AI, a domain element matrix image UI and an offset matrix image SI are acquired and saved respectively in a population information database and an identity card chip; when authentication is carried out, an authentication terminal acquires characteristics of the fingerprints, the iris information and the face image of an identity card holder; the uniform matrix image AI and the domain element matrix image UI are searched for in the population information database based on personal basic information PI; and identity authentication of the identity card and the holder is carried out by using three biological characteristics of the fingerprints, the iris information and the face image, the uniform matrix image AI, the domain element matrix image UI and the offset matrix image SI. According to the invention, an authentication accuracy rate and overall authentication system safety are improved and potential safety hazard existing in the cross-application process is effectively reduced.

The invention describes the first practical, cost effective, truly non-contact implementation of a subcutaneous vein pattern biometric sensor. A laser diode (LD) illuminates the hand in such a way that the pattern of reflected radiation, when viewed by a conventional vein pattern infrared imager, provides a direct measure of target range. Said target range measurement is used to create a visual or audio signal that instructs the individual being scanned to place the hand at precisely the optimum range, such that the vein pattern is in focus. Furthermore, a system and apparatus are described to direct the individual being scanned to move the hand to an optimal horizontal registration or position with respect to the infrared imager.

Various examples of the present invention relate to a method by which an electronic device updates a biological characteristic pattern, comprising the steps of: acquiring a plurality of biological images; comparing each of the plurality of biological images with pre-identified characteristic patterns; determining the biological image, from among the plurality of biological images, that matches a pre-identified characteristic pattern; and updating the pre-identified characteristic patterns by adding, to the pre-identified characteristic patterns, at least one biological image characteristic point which does not match the pre-identified characteristic patterns among a plurality of iris images, and various examples can be achieved.

A fingerprint recognition method includes the following steps: obtaining a to-be-recognized fingerprint image of a to-be-recognized finger; extracting to-be-recognized data of the to-be-recognized fingerprint image, the to-be-recognized data including a to-be-recognized minutiae data set and a to-be-recognized skeleton; loading a minutiae-skeleton array of a registered finger, the minutiae-skeleton array including a plurality of elements, each of the plurality of elements including a registered minutiae data set and a registered skeleton; performing minutiae-skeleton verification on the to-be-recognized data and the minutiae-skeleton array to generate a verification result.

The invention discloses a method for omnibearing detection of the defect of a PET bottle cap antitheft ring. The method comprises a PET bottle to be detected goes through the front light detection station I and the front light detection station II of a first detection cabinet and the back light detection station I and the back light detection station II of a second detection cabinet, a bottle cap top positioning, equalization processing, defect feature extraction and defect judging technology is adopted to realize prepositioned light image processing, an adaption ring positioning, defect feature extraction and defect judging technology is adopted to realize back light image processing, and non-blind area detection of defects in different positions of the bottle cap antitheft ring is carried out. The method has the advantages of low cost and high detection precision.

The invention belongs to the field of identity authentication, and particularly relates to a three-branch identity authentication method and system based on mouse behaviors, and the method comprises the steps: carrying out mouse data collection, and carrying out duplicate removal processing and abnormal removal processing on the collected data; using a data sequence composed of a plurality of basic mouse operations as a mouse behavior, and a feature vector is calculated according to the mouse behavior, so that a related feature value is calculated; Modeling the obtained mouse features to obtain three identity authentication models, outputting probability values of samples belonging to legal mouse users by the models, obtaining threshold values required by classification through a loss function, and dividing sample objects into a positive domain, a boundary domain or a negative domain; and judging the negative domain sample object as an illegal mouse user, judging the positive domain sample object as a legal mouse user, and continuing to authenticate the boundary domain mouse user. According to the method, a decision is made in advance before the number or time of the mice is determined, and higher authentication precision is achieved within lower expected authentication time.

The invention discloses a biometric key generating method adapting to dynamic quantization. The method comprises the following implementation steps: 1, acquiring a human electrocardiograph signal, and performing wavelet transform de-nosing and normalization processing on the human electrocardiograph signal; 2, performing R-wave detection on the normalized electrocardiograph signal, and extracting a pulse spacing feature; 3, performing statistics to obtain a mean value and a variance of the pulse spacing feature, and calculating information entropy of the pulse spacing feature according to the variance; 4, adaptively and dynamically determining a quantization bit of the pulse spacing feature according to the information entropy of the pulse spacing feature; 5, performing quantization coding on pulse spacing according to the determined quantization bit to generate a biometric feature sequence; and 6, performing key negotiation on the generated biometric feature sequence through a sensor node and a coordinator node to generate a biometric key shared by the two nodes. Through adoption of the method, key randomness is ensured; the biometric key generation efficiency is increased; and the fault probability of identity authentication is lowered. The method can be applied to authentication among wireless body area network nodes.

The present invention generally relates to a method for analyzing biometric measurements of a user, and specifically to determination of an alignment level between features of different biometric measurements acquired using a biometric sensor. The invention also relates to a corresponding fingerprint sensing system and to a computer program product.

The invention discloses a dynamic weighing detection device with a self-learning function and in particular relates to the field of product package production. The device comprises a dynamic check weigher, an industrial control computer, a programmable logic controller and a plurality barcode scanners, wherein the dynamic check weigher, the industrial control computer, the programmable logic controller and the barcode scanners are mutually connected and communicate with each other by virtue of an Ethernet gateway, a digital quantity input port of the programmable logic controller is connectedwith an entrance photoelectric switch signal, a digital output port of the programmable logic controller is connected with a rejection cylinder. The device is mounted on a product conveyor line, whena product on the product conveyor line passes the device, two barcode scanners scan a project code and a case code at the same time, when both of the two barcodes can be scanned, a working mode is setto be consistency comparison, if consistency is achieved, whether weight is in a normal range is judged, if the weight is in the normal range, the product is released, and if the weight is not in thenormal range, the product is rejected; and if the consistency is not achieved, the product is rejected as a product with abnormal barcodes no matter whether the weight is qualified or unqualified.

The inventioin relates to a device and method used for detecting a sealing piece. The sealing piece (14) seals a container (12). An analysis processing unit (23) is arranged for obtaining quality criteria (40, 47) especially the gap size between the sealing piece (14) and the container (12). A sensor used for obtaining the height outline of the sealing piece (14) is arranged. At least one output signal of the sensor (18) is conveyed to the analysis processing unit (23). The analysis processing unit obtains the quality criteria (40, 47) according to the output signals of the sensor (18).