62results about How to "Meet identification needs" patented technology

The invention provides a method and device for recognizing image characters. The method includes the steps of S1, obtaining a character area in an image to be recognized, S2, carrying out recognition on various character blocks in the character area respectively, and recording position information of the character blocks, S3, based on the position information of the character blocks, carrying out layout analysis to obtain statement structure distribution, and S4, based on the statement structure distribution, carrying out correction based on semantic analysis on recognition results of the character blocks to obtain the corrected recognition results. According to the method and device, semantic information among the characters is effectively used for correcting the recognition results of the character blocks, the image character recognition accuracy is improved, and the recognition requirements of users are better met.

The invention discloses a railway vehicle number identification system and an information transmission method and aims to solve the technical problem of improving the identification rate of an electronic tag of the railway vehicle number identification system. The system consists of an electronic tag programmer, an electronic tag, an electronic tag reader antenna, an electronic tag reader and an upper computer. The method comprises the following steps that: the electronic tag programmer carries out FMO (Flexible Macroblock Ordering) programming on the electronic tag and encoded data is written into a storage; the electronic tag reader transmits carrier waves to irradiate the electronic tag and the electronic tag reflects the data in the storage; the electronic tag reader receives a reflection signal and the reflection signal is demodulated; and FMO decoding is carried out to obtain tag data. Compared with the prior art, due to the adoption of the FMO decoding, the equivalent transmission rate of the tag information in the process of identifying the tag is improved by 4 times, the frequency of transmitting data frames between the reader and the tag is improved, the effective information transmission rate is improved, and the highest adaptation vehicle speed of the electronic tag reaches over 300km per hour.

The invention provides a ship water gauge image automatic number reading method based on a deep learning algorithm. According to the method, the deep learning algorithm is used for performing identification positioning on the number in a ship water gauge image, thereby obtaining a digital number and a frame coordinate in the image, and a digital frame coordinate is corrected. By means of a numberarrangement rule and a human eye number reading principle in the image, a digit combination algorithm based on the human eye number reading principle is designed. By means of image color information of a ship body and water body, a method for identifying a water level in different color body color backgrounds is designed, wherein different identification methods can be selected according to different backgrounds, thereby ensuring high accuracy and high speed in water level identification. According to the position coordinate of the oblique number in each line and the position coordinate of thewater level, a length reference and oblique number correction algorithm is designed; wherein the actual pixel distance between water level and the number is calculated, and percentage of the pixel distance between the water level and the number in the actual length reference is calculated. Furthermore the number of the ship water gauge image is obtained.

The invention discloses a water gauge image water level automatic reading method based on a Mask RCNN algorithm in the technical field of water conservancy informatization water level automatic measuring and reporting, and the method comprises the following steps: (1), installing a camera and a water gauge, recording and confirming four corner point coordinates of each preset point of a dome camera after water gauge imaging, and setting the four corner point coordinates as preset point parameters; (2) acquiring water gauge images of different cameras and correcting the water gauge images in batches; (3) marking a water gauge detection frame for the corrected image, and constructing a training set; (4) obtaining the optimal anchor frame size anchors, adjusting the learning rate and the number of iterations, and starting to train, verify and test the Mask RCNN model to obtain a final model parameter file; (5) deploying a model parameter file trained in the step (4), correcting a picture collected in real time, and predicting a detection box and a segmentation mask; and (6) calculating the water level in combination with the coordinates of the preset point in the step (1); the method can adapt to water gauge image water level automatic reading in a complex environment, and has the advantages of being high in recognition accuracy, wide in application range, high in intelligent degree and the like.

The invention discloses a method for rapidly obtaining a large number of wheat double-haploid homozygous populations. According to the method, based on a wheat and corn double-haploid breeding technology, through the key links of wheat and corn sowing at different stages, haploid induction, transplantation and vernalization, reduplication and transplantation and winter sowing treatment, after wheat young embryos differentiate into haploid seedlings, transplantation, vernalization and haploid plant reduplication are completed in the same year without over-summer treatment, wheat double-haploid seeds can be harvested in the same year, the requirement for sowing once more can be met after the harvest on the perspective of time, a large number of stable new strains of the wheat homozygous populations can be obtained within one year, the requirement for identifying the new strains at the next stage is met, the natural environment is utilized to the maximum degree, and the time of wheat double-haploid breeding is shortened to one year from two to three years. In this way, the wheat breeding speed is increased, the breeding efficiency is improved, the breeding cycle is shortened, and the breeding cost is lowered.

The invention discloses a kit for detecting common drugs in hair, a pretreatment method and a detection method. The kit comprises first extracting solution and second extracting solution, wherein thefirst extracting solution is borax buffer solution, and the second extracting solution is mixed solution of chloroform and isopropanol. Compared with a conventional detection method, the detection method provided by the invention employs the kit containing the extracting solution of common drugs in hair for extraction operation in sample pretreatment, is good in effect for the extracting solutionand can provide a good basis for qualitative analysis, and the whole pretreatment process can be completed within about 0.5h, so that the pretreatment time is effectively shortened; moreover, the pretreatment method combining the kit with liquid-liquid extraction is adopted during sample pretreatment, so that the cost can be effectively saved, the universality of an identification mechanism is higher, and the superiority is more obvious.

The embodiment of the invention provides a short message processing method and short message processing equipment. The method comprises the following steps of: receiving a short message which is transmitted according to a public mobile station international ISDN number (MSISDN) by a short message entity, wherein the short message comprises a first identifier, and the public MSISDN is used for identifying at least two pieces of terminal equipment; acquiring a corresponding international mobile subscriber identifier (IMSI) according to the first identifier; and transmitting the short message to called terminal equipment corresponding to the IMSI. The embodiment of the invention can save an MSISDN identification space, so that the identification capability of the MSISDN can satisfy the identification needs of a rapidly increased amount of terminal equipment.

The invention provides a Xyleborus sp insect gene barcode detection kit. The Xyleborus sp insect gene barcode detection kit is used for rapidly detecting 12 kinds of Xyleborus sp, and comprises a primer reagent and a gene barcode sequence disk, wherein 37 standard barcode sequences are saved in the gene barcode sequence disk. The invention further discloses a method for performing Xyleborus sp insect molecular detection method by using the Xyleborus sp insect gene barcode detection kit. By adopting the kit and the method, convenient and efficient Xyleborus sp insect molecular detection can be performed, 12 kinds of Xyleborus sp insects can be distinguished on a molecular level, the use demand of quarantine identification can be met, and high practicability is achieved.

The invention discloses a thermal infrared face recognition method and system. The method comprises the steps of determining a thermal infrared image of a to-be-recognized face; inputting the thermalinfrared image of the to-be-recognized face into a trained three-function component extractor, positioning eyes, a nose and a mouth of the face in the image, and performing region positioning on the left eye, the right eye, the nose and the mouth to form a corresponding key area group; according to the difference between the key area group of the standard face and the key area group of the to-be-recognized face, affine transformation is carried out on the thermal infrared image of the to-be-recognized face, acquiring a thermal infrared image after face alignment calibration; inputting the thermal infrared image after face alignment calibration into a trained face feature extractor, and extracting corresponding face features; and inputting the extracted face features into a trained classifier, and identifying information of a person to which the classifier belongs. According to the invention, the human face can be recognized under the condition of no light source, and the recognition rate is high.

The invention provides a handwriting input method and device based on temperature touch. The method comprises the steps of parameter initialization, data reading, acquisition of a temperature rise maximum value, fingertip touch judgment, acquisition of a temperature rise maximum value during movement, fingertip movement judgment and numeric character recognition. The device comprises a controller, and a temperature sensing array and a memory which are connected with the controller, wherein the controller comprises an initialization module, a data reading module, a temperature acquisition maximum value module, a fingertip touch judgment module, a movement acquisition module, a fingertip movement judgment module and a number recognition module. The handwriting input method and device based on temperature touch do not need interaction between any special stylus and a digital converter, working normally is realized even when a screen is wet, and a more attractive substitute for the traditional man-machine interaction interface is provided.

The invention discloses a genetic bar code detection kit of a dermestidae insect. The kit can be used for quickly detecting 19 carpet beetles, comprises at least one primer J1837 / N2110 of more than 20 doses and a genetic bar code sequence disc, wherein the primer J1837 sequence is 5'-TATAGCATTCCCACGAATAAATA-3', and the primer N2110 sequence is 5'-ATTTCGGTCAGTTAATAATATAG-3'; 61 standard code sequences are stored in the genetic bar code sequence disc; the detailed sequences are shown from SEQ ID NO.1 to SEQ ID NO. 61. The genetic bar code detection kit of the dermestidae insect is an efficient, accurate and convenient dermestidae insect molecular detection technology; the types of 19 dermestidae insects can be distinguished in the molecular level; the use requirements can be met.

The invention belongs to the technical field of biology, and particularly relates to a method for analyzing and identifying clinical difficult strains by a 16S rRNA gene sequence. The method for identifying the clinical difficult strains adopts a 16S rRNA gene sequence analysis method, and comprises the following steps: S1, extracting bacterial DNA of a strain to be identified, selecting a bacterial universal primer, and establishing a PCR method for amplifying bacterial 16S rRNA; S2, optimizing a PCR reaction system and reaction conditions to obtain an amplification product; and S3, performing sequence comparison on the amplification product and a gene database to obtain the strain of the strain to be identified. The invention establishes a new method for effectively identifying the difficult strains by applying a 16S rRNA gene sequence analysis technology, expands the identification spectrum of clinical strains, and meets the clinical identification requirements on the difficult strains.

The invention relates to the technical field of computer application, in particular to an image-based Chinese character recognition method. The method comprises the following steps of: obtaining an image to be recognized; 2, preprocessing the acquired image; 3, progressively recognizing the character carrier in the image, scanning the next line of characters sequentially after the line of characters is scanned, and obtaining the outline of the character carrier; 4, matching that outline of the carrier with the standard outline in the database, and convert the matched character information intocharacters corresponding to the character information; 5, recording that position information of the character; 6, carrying out panel analysis according to that position of each character to obtain sentence structure distribution; 7, correcting that distribution of the sentence structure to obtain a corrected recognition result to determine the semantics of the image; Step 8, deriving the corrected recognition result. The precision of image character recognition is improved.

The invention relates to a hydroelectric industry digital object identifier processing method, device and system. The method comprises the following steps: receiving an identifier generation request;when the identifier generation request contains the domain code, determining a newly added meta-class sequence number of the domain code, and allocating a meta-class identifier to the hydropower industry digital object according to the newly added meta-class sequence number; when the identifier generation request contains a meta-class identifier, determining a newly added class sequence number ofthe meta-class identifier, and allocating a class identifier according to the newly added class sequence number; when the identifier generation request contains a class identifier, determining a newlyadded instance sequence number of the class identifier, and allocating an instance identifier according to the newly added instance sequence number; and returning at least one of the meta-class identifier, the class identifier and the instance identifier to the user terminal. By adopting the method, the identification requirement of the hydropower industry field on the digital object can be met.

The invention provides a face depth image quality evaluation method and system, an electronic device and a storage medium, and the method comprises the steps: obtaining three-dimensional face recognition image data based on an input target image, and the three-dimensional face recognition image data comprises aligned face depth images and corresponding identity category information; inputting the aligned face depth image and the corresponding identity category information into a face depth image quality evaluation model to generate a corresponding face depth image quality score; wherein the face depth image quality evaluation model is obtained by training based on face depth image sample data and a predetermined face depth image real quality score label. According to the invention, end-to-end face depth image quality evaluation is realized, and the face depth image quality is comprehensively evaluated; the three-dimensional face recognition image is screened through the face depth image quality result, it is ensured that the face depth image quality meets the three-dimensional face recognition requirement, and therefore the improvement of the three-dimensional face recognition performance is promoted.

The embodiment of the invention provides a textile QR code identifier and a production method thereof. The textile QR code identifier comprises a dark-color module and a light-color module formed through weaving, wherein the dark-color module is formed by weaving dark-color threads in the same color as the dark-color module; the light-color module is formed by weaving light-color threads in the same color as the light-color module; and the dark-color module and the light-color module are distinguished according to a preset grayscale threshold. Through the textile QR code identifier and the production method thereof in the embodiment, since the dark-color module and the light-color module of the textile QR code identifier are formed through the textile technology, compared with a QR code obtained through a printing mode traditionally, the textile QR code identifier has the remarkable advantages of wear resistance, washing resistance and the like, the damage rate of the QR code is effectively lowered, permanency is improved, identification demands in different scenes are met, and extended application of the QR code is benefited.

The invention relates to an automatic identification adapter for an ATE automatic test system and an identification method of the automatic identification adapter. The automatic identification adaptercomprises a processing module, and a cable resistance identification module, a state indication module and a power supply control module which are respectively connected with the processing module, wherein the processing module is used for receiving the ID number of the adapter and then comparing the ID number with the solidified ID number of the adapter so as to judge whether the model of the adapter is matched or not and give a judgment result. According to the adapter for safe connection and reliable test of the ATE test system and the tested product, on one hand, faults of the tested product caused by wrong connection of the adapter and a cable are avoided, and the effect of safety protection of the tested product is achieved; measurement and identification are carried out through theprocessing module, testing of ATE hardware resources is replaced, and occupation of equipment resources is reduced. In addition, the processing module can meet the recognition requirements of variousATE test systems by changing the ID number and the cable resistance value in the solidification program of the recognition module, and has certain universality.

The invention discloses an end-to-end voice print recognition method and a voice print recognition device. The voice print recognition method comprises the following steps: executing a speaker voice extraction task by using a speaker voice extraction module of an end-to-end deep learning network based on received input voice so as to extract voice features of a target speaker; and based on the speech features of the target speaker, making a speaker recognition module using an end-to-end deep learning network perform a speaker recognition task to recognize the target speaker in the received input speech.

The invention discloses a material identification code scanning method, device and system. The method comprises the steps: receiving the current position information of a material identification code generated by a first image obtaining device; determining the target position information of a second image obtaining device according to the current position information; driving the second image obtaining device to move to a position indicated by the target position information, wherein the second image obtaining device scans the information of the material identification code when the material identification code moves into a view field of the second image obtaining device; and receiving the information of the material identification code returned by the second image obtaining device. The invention solves a technical problem of poorer adaptability caused by that an array camera technology is employed in the prior art.

The invention discloses a test method of aphelenchoides ritzemabosi, and the method comprises the following steps: using SEQ ID No. 1 and SEQ ID No.2 in a sequence table as a primer pair, carrying out polymerase chain reaction, knowing whether a special fragment is obtained or not through electrophoresis and further detecting or identifying whether the special fragment is the aphelenchoides ritzemabosi or not. In addition, the invention further provides a kit for diagnosis of the aphelenchoides ritzemabosi, and the kit contains the primer pair. The method and the kit have very high reliability and sensitively, the operation is convenient without depending on the experiences of staff, the accuracy is high, and the practicality is strong, thereby meeting the requirements on rapid and reliable test and identification of the aphelenchoides ritzemabosi before planting crops and during the plant quarantine process.

The invention discloses a method and device for automatically obtaining a suspected card raising channel, and relates to the field of intelligent risk control. The method comprises the steps of collecting basic features of a to-be-identified user; acquiring input basic characteristics of a user to be identified, performing weighted fusion through a trained random forest model with acquired suspected card raising rules in combination with a trained linear regression model to acquire a suspected card raising user list in the user to be identified, and acquiring a corresponding card raising channel according to the suspected card raising user list. A random forest learning base algorithm fused by a plurality of decision tree classifiers is applied to extract potential suspected card raising rules from sample data, weighted fusion is carried out on the potential suspected card raising rules and a linear regression classification model, the integration generalization ability is enhanced, and the suspected card raising rules have diversity. Supervision and management of a card raising phenomenon in a daily operation process of a market department are satisfied so that a channel violationbehavior is effectively controlled.

The invention provides a method and device for recognizing image characters. The method includes the steps of S1, obtaining a character area in an image to be recognized, S2, carrying out recognition on various character blocks in the character area respectively, and recording position information of the character blocks, S3, based on the position information of the character blocks, carrying out layout analysis to obtain statement structure distribution, and S4, based on the statement structure distribution, carrying out correction based on semantic analysis on recognition results of the character blocks to obtain the corrected recognition results. According to the method and device, semantic information among the characters is effectively used for correcting the recognition results of the character blocks, the image character recognition accuracy is improved, and the recognition requirements of users are better met.

The invention discloses an identity recognition system. The identity recognition system comprises a terminal device and a rear-end controller. The terminal device is connected and communicated with the rear-end controller through a network. The terminal device comprises an image acquisition module, a living body detection module, a distance measurement module and an image preprocessing module 1. The rear-end controller comprises a training module, an identification module and a storage module; the system further comprises a feature extraction module and an image preprocessing module 2. The feature extraction module and the image preprocessing module 2 are arranged on the terminal device or the rear-end controller. By means of the system, the user identity can be efficiently recognized, theaccuracy and authenticity of the user identity are ensured, efficient and rapid authentication and passing are helped to be achieved, other auxiliary recognition and judgment such as identity certificates do not need to be combined, and convenience is brought to the user. The system is flexible in design architecture and high in service efficiency, and can meet the identification requirements ofdifferent user quantities and different networks and computing resources.

The invention provides a double-frequency ultrahigh-resolution depth-sounding side-scan sonar system, which relates to the technical field of sonar, can realize depth-sounding side-scan double-frequency-band work, and not only meets a wide-coverage scanning task, but also meets an ultrahigh-resolution identification requirement. The system comprises a double-frequency sonar transducer array used for transmitting a sonar signal with a preset frequency and receiving an echo signal; a sonar electronic extension which generates broadband linear frequency modulation signals meeting the Ping rate requirement, transmits the broadband linear frequency modulation signals to the double-frequency sonar transducer array for signal conversion and emission, and processes echo signals received by the double-frequency sonar transducer array; a control module used for controlling the sonar electronic extension set to work; and a sensor used for monitoring carrier environment data and providing a clock signal for the sonar electronic extension set. The double-frequency sonar transducer array adopts a multi-subarray broadband transducer array, and data of different subarrays are selected for processing and calculation according to needs during depth measurement and side scanning signal processing. The technical scheme provided by the invention is suitable for the underwater measurement process.

The invention discloses a text recognition method and a related device. The method comprises the steps of obtaining a text picture, wherein the text picture is a picture comprising a target text; inputting the text picture into a text recognition network for recognition to obtain a target text; enabling each hierarchy of the text recognition network to recognize the target text by using local information and sequence information of the text picture at the same time, wherein the local information comprises structure information of the target text, and the sequence information comprises context sequence information of the target text. According to the method, in the process of recognizing the text picture based on the text recognition network, the local visual information and the context sequence information of the text picture are extracted in parallel, and the local visual information and the context sequence information of the text picture are interactively fused; therefore, the binary information of the text picture can be utilized at each level of the text recognition network at the same time, the problem of text character omission or dislocation in the recognition process is solved, and the accuracy and efficiency of text recognition are improved.

The invention relates to a rock debris type identification method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-identified rock debris image; inputting the to-be-identified rock debris image into a pre-trained rock debris type identification model to obtain an identification result of the to-be-identified rock debris image; wherein the rock debris type identification model is obtained by training based on a ResNet34 classification network model. By means of the method, the property information of the rock debris and the rock sample of the drilled stratum can be rapidly analyzed, an effective stratum geological section is established, the defect that geological logging interpretation must depend on a deep geotechnician is overcome, and the automation and intelligence level of a drilling and logging site is improved.

The invention discloses a camera shooting exposure method and device of self-walking equipment. The camera exposure method of the self-walking equipment comprises the following steps: detecting the brightness of a region of interest in a collected image according to a preset rule; when it is detected that the brightness information does not meet the preset condition, adjusting the current exposure parameter; and performing local exposure in the image acquisition process according to the exposure parameters. The camera shooting exposure device of the self-walking equipment comprises an image brightness detection unit which is used for detecting the brightness of a region of interest in an image acquired by an image acquisition device according to a preset rule; an exposure parameter adjusting unit which is used for adjusting the current exposure parameter when detecting that the brightness information does not meet the preset condition; and a local exposure unit which is used for performing local exposure in the image acquisition process according to the exposure parameters. The device can work normally in an environment with insufficient light or darkness. Therefore, under the condition of high reflection along the wall and the ground, the AE under the light supplement lamp can still meet better object identification requirements.