383results about How to "High identification accuracy" patented technology

A 1D-CNN-based ((one-dimensional convolutional neural network)-based) distributed optical fiber sensing signal feature learning and classification method is provided, which solves a problem that an existing distributed optical fiber sensing system has poor adaptive ability to a complex and changing environment and consumes time and effort due to adoption of manually extracted distinguishable event features, The method includes steps of: segmenting time sequences of distributed optical fiber sensing acoustic and vibration signals acquired at all spatial points, and building a typical event signal dataset; constructing a 1D-CNN model, conducting iterative update training of the network through typical event signals in a training dataset to obtain optimal network parameters, and learning and extracting 1D-CNN distinguishable features of different types of events through an optimal network to obtain typical event signal feature sets; and after training different types of classifiers through the typical event signal feature sets, screening out an optimal classifier.

A red-eye detection device includes a red-eye candidate detection section, a red-eye pair specification section, and an isolated red-eye candidate check section. The red-eye candidate detection section detects a red-eye candidate that can be estimated to be a red-eye, by identifying a feature of the pupil that has a region displayed red from among features of an image. The red-eye pair specification section specifies the red-eye candidate as a pair of a right red-eye candidate equivalent to a right eye and a left red-eye candidate equivalent to a left eye, using information on a face region obtained from the image. The isolated red-eye candidate check section checks whether an isolated red-eye candidate, detected by the red-eye candidate detection section but not specified as the pair by the red-eye pair specification section, is a true red-eye.

The invention discloses a mobile terminal identification method and device. The method includes the steps that a server receives a verification request sent by a client side, wherein the verification request comprises parameter information of a mobile terminal to be verified, and the parameter information comprises information of a manufacturer which manufactures the mobile terminal, type information of the mobile terminal and hardware parameter information of the mobile terminal; a hardware feature information database is queried according to the information of the manufacturer and the type information, and hardware feature information matched with the information of the manufacturer and the type information is acquired; whether the hardware parameter information of the mobile terminal is matched with the acquired hardware feature information or not is judged, if yes, it is determined that the mobile terminal is a real machine, if not, it is determined that the mobile terminal is a fake machine. The problem that existing detection software is high in identification error rate can be solved.

The invention relates to a thyroid CT image computer-aided diagnosis system and method. The problem that currently, many defects exist in the thyroid disease diagnosis through physical examination, ultrasonic scanning and radioisotope scanning is solved. The system comprises an input module, an image texture characteristic extracting module, a classified diagnosis module and an output module which are sequentially connected. The method includes the steps of conducting outline segmenting and extracting on an image, then conducting texture characteristic analysis on the image to obtain the 28-dimension texture characteristic, and finally substituting the 28-dimension texture characteristic into a diagnosis model to obtain a diagnosis result and a statistics index. The thyroid CT image computer-aided diagnosis system and method have the advantages that non-invasiveness, rapidness and timeliness are achieved; no chemical reagents or the like are needed, and cost is low; complexity of a lesion thyroid texture characteristic sample set is effectively reduced, and identification accuracy can be further improved; the result is not affected by man-made subjective factors and is prevented from being affected by man-made subjective factors in the pathological examination and other examinations.

Disclosed are a method and a device for real-time mark for a high-energy X-ray dual-energy imaging container inspection system in the radiation imaging field. The method comprises the steps of emitting a first main beam of rays and a first auxiliary beam of rays having a first energy, and a second main beam of rays and a second auxiliary beam of rays having a second energy; causing the first and second main beams of rays transmitting through the article to be inspected; causing the first and second auxiliary beams of rays transmitting through at least one real-time mark material block; collecting values of the first and second main beams of rays that have transmitted through the article to be inspected as dual-energy data; collecting values of the first and second auxiliary beams of rays that have transmitted through the real-time mark material block as adjustment parameters; adjusting the set of classification parameters based on the adjustment parameters; and identifying the substance according to the dual-energy data based on adjusted classification parameters. The method according to the invention simplifies the mark procedure for a substance identification subsystem in a high-energy dual-energy system while improves the stability of the material differentiation result of the system.

The method of identifying an effective pigment comprises:

a first step of imaging a target effective pigment to obtain image data thereof;

a second step of subjecting the obtained image data to background processing and extracting image data concerning a region containing one particle of the effective pigment as image data for processing;

a third step of extracting image characteristic parameters from the image data for processing; and

a fourth step of identifying the target effective pigment, based on the image characteristic parameters of the target effective pigment extracted in the third step, using a pre-prepared database that stores information on various kinds of effective pigments in such a manner as to correlate with the image characteristic parameters of various kinds of effective pigments extracted by conducting the second and third steps.

The invention discloses a quick edible oil variety identification method based on multisource spectral feature fusion. The method comprises the steps of selecting an unknown variety of edible oil sample to be identified, acquiring a Raman spectrum chart and a near infrared spectrum chart, preprocessing the Raman spectrum chart and the near infrared spectrum chart to obtain a preprocessed Raman spectrum chart and a preprocessed near infrared spectrum chart, conducting feature extraction on the preprocessed Raman spectrum chart and the preprocessed near infrared spectrum chart to obtain a Raman characteristic variable and a near infrared characteristic variable, conducting spectral characteristic fusion on the Raman characteristic variable and the near infrared characteristic variable to obtain a characteristic fusion spectrum chart, and conducting variety identification on the unknown variety of edible oil sample by means of an optimized qualitative model. The method is safe and quick, detection is convenient, identification accuracy is high, and practical value and popularization value are high.

The invention provides a method for identifying a hyperspectral material. First a standard light source spectrum database is established, a spectral material standard database is established, and standard light source spectra are obtained through a difference method and a control variable method; spectral data information is shot for a material needing to be identified; through preprocessing and intrinsic material information extraction, spectral characteristics of the material are obtained, and then the spectral characteristics are matched with data in the spectral material standard database, so as to perform high-precision identification of the material. According to the method, the interference to spectral information of the material caused by complex factors such as different illumination conditions and material shape changes and the like can be resisted, the problems of metamerism and homogeneity and heterochrome which cannot be solved through conventional red green blue (RGB) and RGBD cameras are solved, and the identification precision rate is high.

The invention provides an identity identification method in bitcoin transaction. The method comprises: a probe node that can be connected to nodes as many as possible is deployed in a bitcoin network;a to-be-monitored node in the bitcoin network is selected; a neighbor node of the to-be-monitored node is determined by the probe node; and transaction information and a transaction propagation pathof the bitcoin network are monitored and obtained; matching values of the transaction propagation path with the to-be-monitored node and the neighbor node are calculated; a matching transaction of theto-be-monitored node is screened out by a threshold value; and the matching transaction is outputted and an IP tag is assigned for the transaction. Therefore, with the matching identifier for the bitcoin transaction and the trader's IP address, the identity of the trader is identified, so that the high identification accuracy is improved; and compared with the prior art, the method provided by the invention enables the cost to be reduced substantially.

A projector includes: a determination section to specify a reflection position of a reflected light received by a light receiving sensor based on a horizontal synchronizing signal and a pixel clock signal of an image signal, and to determine an amplification quantity of the intensity of a reflected light reflected at the specified reflection position to be received by the light receiving sensor; an amplification section to amplify the intensity of the reflected light received by the light receiving sensor by the determined amplification quantity; an identification section to identify an external obstacle when the intensity of the amplified reflected light exceeds a predetermined threshold value; and a calculation section to calculate the position information of the external obstacle based on the timing of identifying the external obstacle, the horizontal synchronizing signal, and the pixel clock signal of the image signal.

The invention relates to a print file identification method based on print font library analysis and belongs to the technical field of print file identification. The method mainly comprises the steps of extracting the characteristics of Chinese character images of various types of sample printers, through a learning process, training samples into a characteristic value library corresponding to the same Chinese character of various types of printers used by a system, and matching the characteristic value library with characteristic Chinese character libraries sequentially to complete rough classification of the Chinese character libraries; based on the step above, characterizing Chinese characters more deeply through HU-moment characteristic values until the characterized characteristic information can uniquely identify the Chinese characters in the images. The computer identification method for identifying character images of different types of the printers through commonly-used character libraries is clear in theory, simple in process, convenient to operate, rapid and accurate and is an effective and workable method. The method integrates various technologies and useful information to improve the identification accuracy and provides an automatic computer print file identification system for public security and physical evidence identification departments.

The invention provides a gait data-based identity recognition method. The method comprises the following steps of: firstly extracting gait profile curves of training samples and a to-be-recognized sample; processing the gait profile curves by utilizing a line-by-line scanning method so as to obtain a high-dimensional gait feature matrix; carrying out dimensionality reduction on the high-dimensional gait feature matrix by utilizing an improved smooth auto-encoder; and finally judging which category of training samples is nearest to the to-be-recognized sample by utilizing a nearest neighbor algorithm. According to the identity recognition method provided by the invention, a new gait feature is adopted, and the improved smooth auto-encoder and a nearest neighbor theory are utilized to carry out feature dimensionality reduction and similarity judgement, so that structure information in two-dimensional gait images can be sufficiently utilized to describe gait differences between different persons, thereby improving the gait information-based identity recognition correctness.

A highly accurate identification system is built by using an identification module, which has predetermined values of FAR and FRR. A plurality of (m) biometrics are registered and managed. At the time of identification, a collation process is executed by using the m biometrics, and also a collation process is executed a plurality of (n) times with each biometrics. An identification result of the system is judged and outputted by combining the results of the m-biometrics collation and n-time collation trials. As conditions of judgment, when the collation is judged to be successful even once in the n-time collation trial, the collation is judged to be successful with respect to that biometrics. In the in-biometrics collation trial, when the collation is judged to be successful with respect to all the m biometrics, a judgment of identification success is given in the system as a whole.

The invention provides a method for quickly identifying tea varieties through a near-infrared spectroscopy technology. The method comprises the steps that firstly, near-infrared diffuse reflection spectrum of tea is collected through a near-infrared spectroscopy instrument, dimension reduction treatment is conducted on the high-dimension near-infrared spectrum of the tea through principal component analysis (PCA), the variety classification information of tea spectrum data is extracted through linear discriminant analysis (LDA), and finally, the tea varieties are identified and analyzed through a new generalized noise clustering method. The method is high in detection speed, high in identification accuracy, environmentally friendly and capable of accurately identifying the tea varieties.

The invention discloses a breeding method of an induction line for efficiently identifying a corn haploid young embryo. The method comprises the following steps of hybridizing a corn haploid inductionline with a corn inbred line S23 to obtain a hybrid F<1> generation; backcrossing the hybrid F<1> generation and the corn haploid induction line to obtain a backcross posterity BC<1>F<1>; selecting asingle plant of the corn from the backcross posterity BC<1>F<1> to continuously self-cross to obtain the induction line for efficiently identifying the corn haploid young embryo, wherein the single plant of the corn is high in color developing degree of the young embryo after being hybridized with corn hybrids, high in haploid induction rate and high single-ear haploid number after being hybridized with the corn hybrids and is homozygous for both Zmpla1 gene and Zmdmp gene; and the haploid inductivity, the single-ear haploid number, the plant height, the ear position, the tassel branch number, the single-ear fructification number and the haploid young embryo identification accuracy of the induction line for efficiently identifying the corn haploid young embryo are all higher than those ofthe corn haploid induction line. The breeding method of the induction line for efficiently identifying the corn haploid young embryo has important application value.

The invention discloses roe and fry quick classification and determination methods based on CoI DNA bar codes. The methods comprise the following steps: collecting fish samples capable of being subjected to accurate classification and determination in a water region under investigation, respectively carrying out PCR amplification and sequencing on mitochondria CoI fragments of various fishes, establishing a CoI DNA bar code database of the fishes in the water region under investigation according to the amplification and sequencing results, numbering the roe and fry samples in the water region under investigation, respectively extracting DNAs of the roe and fry samples, carrying out amplification and sequencing on feature fragments, comparing the amplification and sequencing results with the established CoI DNA bar code database, and thus rapidly and accurately determining the varieties of the roe and fry samples. With the adoption of the methods, the defects that the existing classification and determination methods are large in error and fail in identification, samples to be classified need to be cultured in large quantities, genetically close species can not be distinguished, and the classification and determination cost are high are overcome, and the advantages of rapidness and accuracy of the roe and fry quick classification and determination methods are exerted.

The invention discloses a method for inducing corn haploids. The method comprises the following steps: pollinating a female parent by a male parent corn haploid induction line with a higher corn haploid inductivity than a corn haploid induction line CAU5, and harvesting hybridized F1 generation grains to obtain corn haploids. A method for realizing the corn haploid induction line comprises the following steps: 1, introducing coding gene of a specific centromere histone mutant into a hybrid first generation plant of a corn inbred line HiIIA and a corn inbred line HiIIB to obtain a transgenic corn plant; and 2, hybridizing the specific histone mutant as a female parent with the CAU5 to obtain an F1 generation, hybridizing the F1 generation as a female parent with the CAU5 to obtain a BC1F1 generation, hybridizing the BC1F1 generation as a female parent with the CAU5 to obtain a BC2F1 generation, and continuously selfing the BC2F1 generation at least five generations to obtain the corn haploid induction line.

A control constant adjusting apparatus in a control apparatus of a robot or a machine tool, etc. is disclosed. This control constant adjusting apparatus includes a speed control part (12), an estimation part (13), an identification part (14) and an adjustment part (15) . The identification part (14) makes identification of inertia J obtained from a ratio between a value |SFTr| in which an absolute value |FTr| of a value FTr obtained by passing a torque command Tref of the speed control part (12) through a predetermined high-pass filter is integrated with respect to time at a predetermined interval [a, b] and a value |SFTr′| in which an absolute value |Ftr′| of a value FTr′ obtained by passing a model torque command Tref′ of the estimation part (13) through a predetermined high-pass filter is integrated with respect to time at the same interval only when a speed Vfb′ of a model in the estimation part (13) matches with a motor speed Vfb in the speed control part (12) at a value other than zero.

The invention discloses a method for fast identifying the variety of edible oil through a near-infrared spectroscopy method.The method comprises the following steps that a to-be-identified edible oil sample with the unknown variety is selected; a near-infrared spectrogram of the edible oil sample is collected; the near-infrared spectrogram of the edible oil sample is preprocessed, and a preprocessed spectrogram of the edible oil sample is obtained; according to the preprocessed spectrogram of the edible oil sample, a palmitic acid quantitative model, an oleic acid quantitative model and a linoleic acid quantitative model are sequentially adopted for predicting the palmitic acid content, oleic acid content and linoleic acid content of the edible oil sample respectively; an optimized qualitative model is adopted for identifying the variety of the edible oil sample according to the obtained palmitic acid content, oleic acid content and linoleic acid content of the edible oil sample.The method for fast identifying the variety of the edible oil through the near-infrared spectroscopy method is safe, fast and high in identification accuracy, detection is convenient and fast, and high practical value and popularization value are achieved.

The invention relates to a coin identifying or discriminating device and method, especially relating to the discrimination of the true coins from the false coins. The method vertically slides the tested coin along a guiding groove down onto a substrate, collects a sound signal emitted by the coin as striking the substrate through sound sensor, directly sends the sound signal or sends the sound signal amplified by a power amplifier to a frequency spectrum analyzing device for making frequency spectrum analysis so as to obtain an inherent frequency of the tested coin, and compares the inherent frequency with a standard data in a frequency spectrum standard memory for making frequency spectrum discrimination; then uses a pressure sensor to measure the weight of the tested coin and sends the generated force signal amplified by a power amplifier into a weight analyzing device and calculates to obtain the weight of the tested coin and compares it with a standard data in a weight standard memory for making weight discrimination; then by an operational policy maker, synthetically analyzes and obtains the final discrimination result. The discriminating device has simple structure, lower manufacturing cost, and high identifying accuracy, applied to identification of various coins and having a wide application prospect.

An optical disk device has reproduction signal detecting section, each of which detects a reproduction signal corresponding to a reflective wave of an optical disk, a first offset controller, which offsets the reproduction signal with a first offset value F1, an A/D converting circuit, which A/D converts the offset reproduction signal, and a second offset controller, which offsets the converted digital reproduction signal with a second offset value F2, and a decoder, which viterbi decodes the offset digital reproduction signal and outputs decoded data B. Because an offset is performed with each exclusive value to A/D conversion and viterbi decoding, it is possible to obtain high identification accuracy with nonlinear characteristic eliminated.

The invention discloses a method for cultivating a corn haploid inducer with higher corn haploid inductivity than a corn haploid inducer CAU5. The method comprises the following steps: 1, inducing coding gene of a specific histone mutant into a hybrid first generation plant of a corn inbred line HiIIA and a corn inbred line HiIIB to obtain a transgenic corn plant containing the specific histone mutant; and 2, hybridizing the specific histone mutant as a female parent with the corn haploid inducer CAU5 to obtain an F1 generation, hybridizing the F1 generation as a female parent with the corn haploid inducer CAU5 to obtain a BC1F1 generation, hybridizing the BC1F1 generation as the corn haploid inducer CAU5 to obtain a BC2F1 generation, and continuously selfing the BC2F1 generation five generations to obtain the corn haploid inducer with higher corn haploid inductivity than the corn haploid inducer CAU5.