1127results about How to "Improve labeling efficiency" patented technology

The invention discloses an automatic tag removing and labeling machine, a tag removing device, a tag labeling device and a tag band conveying device are arranged on an installation panel, a tag labeling cylinder of the tag labeling device is arranged vertically on one side of the installation panel, and a tag labeling head is fixed on a piston rod of the tag labeling cylinder; a tag removing plate of the tag removing device inclines upwards and is fixedly arranged on the installation panel, and a photoelectric control switch is arranged on the upper portion of a tag removing cutter edge; a gas blowing pipe is arranged on the lower portion of the tag removing device, and a gas blowing hole faces toward the bottom of the tag labeling head; and a traction roll of the tag band conveying device is driven by a driving motor to rotate, and a rolling tension wheel is connected with the driving motor through a synchronous belt. The automatic tag removing and labeling machine ingeniously utilizes blowing to bear removed tags, transfers the removed tags, attaches the removed tags to the tag labeling head by using vacuum, adopts pneumatic pressure to label and achieves automatic cycling operation by utilizing a magnetic switch and the photoelectric control switch. The labeling efficiency is high, labeling quality is good, and the machine is suitable for highly automatic assembly line work.

The invention relates to an interactive method of image semi-automatic annotation, comprising S1 dividing an initial sample into three different types of annotation samples according to different category attributes; labeling the three types of labeling samples manually to get different kinds of labeling results, and then using three models of Mask-RCNN, Fast-RCNN and FCN to train separately; S2 processing the data set of the picture to be annotated in an offline manner, wherein the annotating process is that the data set of the picture to be annotated passes through the three depth learning models in turn to output the json format files of all types and coordinate points of the data samples; S3 calling the relevant attribute tag value and coordinate point value of the json format file according to the name of the annotated image; S4 displaying the corresponding automatic marking result in the marking software, and judging whether the category and area marking of the target object arestandardized and reasonable by manpower; S5 carrying out data augmentation on the correctly labeled labeling samples and feeding back the augmented data to the model for retraining.

The invention relates to the image processing technology field and provides an image annotation method and a terminal device. The method comprises the following steps of acquiring an image to be annotated, and inputting the image to be annotated into a target detection model so as to obtain the first annotation set of the image to be annotated; displaying the image to be annotated containing the first annotation set; acquiring adjusting information input by a user, and according to the adjusting information, adjusting the first annotation set; and according to the adjusted first annotation set, determining the final annotation set of the image to be annotated. In the invention, the automatic annotation and the manual annotation of the image can be combined, image annotation efficiency is greatly increased, and annotation accuracy can be ensured.

The invention discloses a method and device used for processing point cloud data. A concrete implementation method includes displaying a to-be-marked point cloud frame and a camera image formed by photographing one scene at the one moment by the point cloud frame; determining an area of an object in the point cloud frame in response to operation of selecting the object in the point cloud frame; projecting the area into the camera image from the point cloud frame and obtaining a projection area in the camera image; adding a mark in the projection area so as to enable a user to mark the selectedobject in the point cloud frame according to the object indicated by the mark in the camera image. By adopting the implementation method, aid can be provided to a marking worker to mark the object inthe point cloud frame quickly and accurately.

The invention discloses a 3D point cloud data processing method. A ground filtering method for a 3D point cloud is achieved by establishing a 3D raster map and fitting a ground plane curve, a data structure is simple, the obtained ground plane curve is accurate and reliable, and filtering effect and real-timeliness are very good. A provided partition method adopts a method for clustering search windows in the cylindrical coordinate raster map, the calculation amount in the clustering process is greatly decreased, real-timeliness is good, and a clustering result is accurate. A provided training sample marking method is formed by combining point cloud partition with an appropriate display and storage method and is easy to achieve, multiple categories of samples can be marked in point cloud data of each frame, and sample marking efficiency is greatly improved.

The invention discloses a face image gender marking method and a face gender detection method. The detection method includes the following steps that: 1) face images and context information thereof are obtained; 2) the genders of each of obtained face images to be marked is marked; 3) feature vectors of each of gender marked images are extracted, and a machine learning algorithm is utilized to train the face images which have been subjected to gender marking so as to generate a face gender recognition model; and 4) as for face images to be detected, the feature vectors of the face images to be detected are extracted, and the face gender recognition model is utilized to perform gender detection on the face images to be detected. The gender of each of the obtained faces to be marked is marked in the following manners that: name keywords of candidates are extracted from the context information of the images, and a network is searched, and the method returns a result webpage; the genders of the images are determined according to the word frequency of gender relevant words in the result webpage; and a face image technology platform and a face attribute analysis algorithm are respectively adopted to detect the genders of the images; and the gender of the images are marked based on above recognition results. With the face image gender marking method and the face gender detection method of the invention adopted, face image marking efficiency and gender detection efficiency can be greatly improved.

The invention provides a sample marking method and device based on artificial intelligence prosody prediction. The method comprises steps that a first text sequence of unmarked prosodies corresponding to a first sample audio file is acquired; text characteristics and pronunciation duration of each character of the first text sequence are acquired; a pre-trained prosody marking model is applied to the text characteristics and the pronunciation duration of each character of the first text sequence to acquire an output mark of each character of the first text sequence; prosodic hierarchy marking for the first text sequence is carried out according to the output mark of each character of the first text sequence. The method is advantaged in that text marking cost is reduced, text marking efficiency and accuracy are improved, more training samples required for prosodic hierarchy marking can be provided, prosodic marking model performance is improved, and the voice synthesis effect is more natural.

An automatic vision-based labeling device for end faces of reinforcing steel bars in a bundle comprises a positive and negative pressure supply device (1), a machine vision device (2), a label printing and stripping integrated machine (3) and a labeling unit (4). The label printing and stripping integrated machine (3) is arranged below the front of an operation object which is the reinforcing steel bar bundle and next to the reinforcing steel bar bundle. The machine vision device (2) is arranged right in front of the reinforcing steel bar bundle. The positive and negative pressure supply device (1) is arranged on the left side of the front of the reinforcing steel bar bundle. The labeling unit (4) is arranged on the right side of the front of the reinforcing steel bar bundle. According to the complete device, machine vision is used for obtaining the central coordinates of the end faces of the reinforcing steel bars in the bundle, a robot is used for conducting automatic labeling, manual intervention is not needed, management is facilitated, and a foundation is laid for achieving internet+ intelligent production of iron and steel plants.

The embodiment of the application discloses a training method, a matting method, a device, a medium and a terminal of an image processing model. The training method of the image processing model includes obtaining a trichotomy of the original image; Generating a training sample set according to the original image and the trichotomy; The preset depth learning network is trained based on the training sample set to obtain an image processing model, wherein, the image processing model is used for labeling the original image to obtain a trichotomy. By adopting the technical proposal, the input original image can be automatically annotated to obtain a trichotomy, and a large amount of hairline level data annotation can be carried out without manual annotation, the annotation workload can be reduced, and the image annotation efficiency can be improved. In addition, the matting effect can be optimized by using image processing model to label the original image, avoiding the error that may be introduced by manual labeling.

The invention discloses a double detection line SAA (Serum amyloid A protein) immunofluorescence chromatography quantitative detection reagent and a preparation method thereof. The double detection line SAA immunofluorescence chromatography quantitative detection reagent can simultaneously promote sensitivity and detection scope and can be applied to clinical detection for SAA level in patients of acute inflammation and chronic inflammation. According to the technical key points, the reagent comprises a base plate, a combining cushion, a coating film and an absorbing cushion, wherein a sample cushion is connected with the base plate; anti-SAA monoclonal antibody 1 and chick IgY are sprayed on the combining cushion and are marked with a same fluorescent microsphere; a detection line T1, a detection line T2 and a quality control C line are arranged on the coating film; anti-SAA monoclonal antibody 2 is coated with the detection line T1; antigen SAA protein is coated with the detection line T2; goat-anti-chick IgY is coated with the quality control C line. The reagent belongs to the technical field of in-vitro diagnostic reagents.

The invention discloses a medical image labeling method and device for deep learning, and the method comprises the following steps: carrying out the preprocessing of an inputted image diagnosis report, electronic medical record information and a medical image, and generating data comprising the medical image and the extracted related diagnosis information, wherein the medical image is pre-annotated based on deep learning, the image is segmented based on an image semantic segmentation technology to obtain a boundary range of each lesion area, pixel-level segmentation annotation is performed onthe image, and classification annotation is performed on a disease type to which the image belongs based on an image classification technology in combination with image related diagnosis information;and displaying the pre-annotated image and the related diagnosis information through an interface to receive an interactive instruction for a doctor to finely adjust a pre-annotated image result, andexporting an annotation result. According to the method, the labeling efficiency is improved, and the labeling precision is ensured.

The embodiment of the invention discloses a method and a device for generating three-dimensional data, an apparatus and a storage medium. The method comprises the following steps: obtaining a contourinformation labeling result of a target object in a two-dimensional image; Calculating a depth of field of the target object and a three-dimensional orientation of the target object according to the outline information labeling result and a standard three-dimensional size of the target object; Determining three-dimensional coordinates of the reference two-dimensional image point according to two-dimensional coordinates of the reference two-dimensional image point in the two-dimensional image in the target object and the depth of field; Generating three-dimensional data matching the target object according to the three-dimensional coordinates of the reference two-dimensional image point and the three-dimensional orientation of the target object. The technical scheme of the embodiment of theinvention can reduce the cost of the three-dimensional annotation and improve the efficiency of the three-dimensional annotation.

The invention discloses a POI (Point Of Interest) labeling method and device. The method comprises the steps of receiving multiple POI data uploaded by multiple users; carrying out primary clustering on the multiple POI data according to position information by employing a clustering algorithm to generate multiple clustering areas; carrying out secondary clustering on the multiple clustering areas respectively according to names of POIs to generate multiple clustering result sets; and labeling position areas in which the POIs exist according to the multiple clustering result sets. According to the method, by employing mass POI position and attribute information uploaded by the users, the POIs are dug out quickly and accurately, so the cost of manpower and material resources is saved, the POI update speed is improved, and the POI labeling efficiency is improved.

Embodiments of the invention provide a voice processing method. The method comprises the following steps: acquiring to-be-processed audio data; extracting voiceprint information of the to-be-processed audio data; matching a target identity from a preset audio database according to the voiceprint information, wherein the preset audio database comprises a plurality of pieces of voiceprint information, each of which corresponds to an identity; and marking the to-be-processed audio data according to the target identity. The embodiments of the invention furthermore provide a terminal. Through the voice processing method and the terminal, the audio marking frequency can be improved.

The invention discloses an enzyme immunoassay of testing the bice green residues in animal derived food, which comprises an enzyme label plate covering bice green antigen, enzyme label bice green antibody working solution, bice green standard solution, substrate solution, substrate buffer solution, reaction termination solution, concentration washing liquid and sample dilute solution. The invention further discloses a method for using the immunoassay to test bice green residues, which comprises sample pretreatment, testing via the immunoassay, processing and analyzing result. The inventive immunoassay of bice green test uses direct competition enzyme-linked immunoassay adsorption analysis technique, with high sensitivity, high stability, simplified operation, reduced reaction time, reduced error caused by complex operation, reduced cost, wide application for testing samples and high practicality.

The invention provides a vehicle following distance automatic recording system and method. The vehicle following distance automatic recording system comprises multiple vehicle following distance recording units. All the vehicle following distance recording units are distributed at a monitored road according to preset distance. Each vehicle following distance recording unit comprises a supporting vertical rod. A supporting transverse rod is fixedly installed at the top end of the supporting vertical rod. The supporting transverse rod is provided with radar, at least one video camera, a light supplementing lamp and a controller. The vehicle following distance automatic recording system and method have the following advantages that (1) the monitoring recording system of combination of radar and the video cameras is adopted so that illegal vehicle position information and corresponding vehicle speed information and other driving information can be automatically recorded, the illegal vehicle position information and the corresponding vehicle speed information and other driving information can be marked on the snapshot images, and thus the vehicle illegal state can be visually and accurately reflected and sufficient legal basis can be provided for evidence obtaining and punishment of illegal vehicles.

The invention relates to a point cloud labeling method and device, computer equipment and a storage medium. The method comprises the steps of obtaining first annotation information of a first object in first frame point cloud data, wherein the first annotation information comprises size information and direction information of an annotation box and the type and number of the first object; Obtaining a second object in the to-be-labeled second frame point cloud data; And when the type of the second object is the same as that of the first object, configuring the first annotation information to the second object. According to the method, the marking efficiency of point cloud marking can be improved.

The invention provides a digital pathological image annotation method and system. The method comprises the steps that a standard graphic annotation tool based on a pathological term base is adopted to annotate a to-be-annotated digital pathological image; format management is performed on pathological annotation information on the annotated digital pathological image based on an XML format; and the annotated digital pathological image is allocated to at least three persons for review, the annotated digital pathological image passing review is stored in an annotation database, and data in the annotation database is transmitted to a machine learning sample base for machine learning. A professional, normalized and systematic digital pathological image annotation solution is provided, a user can utilize various terminal devices to perform annotation, retrieval, uploading and downloading, annotation efficiency can be improved, and formation of a uniform and collaborative pathological image annotation mechanism is promoted.

The invention provides a transfer printing plate, a display screen, a display device and a display device manufacturing method. The transfer printing plate comprises a printing region and a non-printing region, wherein the printing region comprises multiple sub-printing units corresponding to multiple unit display screens on a mother plate in one-to-one mode, different mark zones are arranged on each sub-printing unit respectively and used for forming marks for identifying the unit display screens on the mother plate on the unit display screens while forming alignment films on the unit display screens on the mother plate. By means of the scheme, the mark zones are set in the printing region of the transfer printing plate through improvement on the transfer printing plate structure, the unit display screens can be simultaneously marked on the same mother plate when the alignment films are formed on the mother plate, and the unit display screen marking efficiency of a current production line is improved.

The invention relates to a video playing method and apparatus, a computer readable storage medium and a computer device. The method comprises the steps of obtaining a target video; determining a videokey segment in the target video; playing the target video; when the video key fragment is played, playing the video key fragment at a first playing speed; when a non-key segment in the target video is played, playing the key video segment at a second playing speed; wherein the second playing speed is greater than the first playing speed. According to the scheme provided by the invention, a largeamount of unnecessary playing time consumed in the video playing process can be avoided.

Improved methods of genetic haplotyping and DNA sequencing and mapping, including methods for making amplified ssDNA, methods for allele determination, and a DNA barcoding strategy based on direct imaging of individual DNA molecules and localization of multiple sequence motifs or polymorphic sites on a single DNA molecule.

The invention discloses a method for video labeling and a device for video labeling and belongs to the field of video processing. The method for the video labeling comprises carrying out a shot segmentation to a video; extracting a key frame assembly in each segmented shot; extracting relevant low layer eigenvectors of each key frame assembly; using semi-supervised kernel density estimation arithmetic to label each unlabeled sample with a category label and labeling key frames corresponding to the unlabeled samples with category. Due to the fact that the eigenvectors combined by various low layer characteristics of an image are adopted to represent the key frames, and loss of pattern information is reduced. The semi-supervised kernel density estimation arithmetic is used for labeling each unlabeled sample with a category, unlabeled data is leaded to a kernel density estimation, feature information of the labeled samples and unlabeled samples are comprehensively applied, and efficiency of video labeling and accuracy of kernel density estimation are improved.

The embodiment of the invention discloses a laser point cloud data labeling method and device. The method comprises the steps of obtaining laser point cloud data and a reference image which are collected at the same time and aim at the surrounding environment of the laser radar; obtaining a first labeling operation input for the displayed laser point cloud data; according to a predetermined firstmapping relation between an image coordinate system and a three-dimensional coordinate system, mapping the determined bounding box corresponding to the first labeling operation into the reference image to obtain an image bounding box in the reference image; displaying the image bounding box in an interface for displaying a reference image; and according to the bounding box and attribute information input by aiming at a reference image in the displayed image bounding box, determining marking information corresponding to the laser point cloud data. By applying the scheme provided by the embodiment of the invention, the accuracy of information labeling when the laser point cloud data is labeled can be improved.

Training sample generation is disclosed, Text data, A method for classify public opinion events and relate equipment, in a training sample generation method provided by an embodiment of the present application, At first, that text data is cluster, Because text data is clustered, When a clustering result corresponding to a target category is found, The training samples of the target category can beobtained only by selecting the text data that meet the target category conditions in the corresponding clustering results and then labeling the target category, without analyzing whether the text data in other clusters meet the target category conditions or not. Therefore, the selection range of text data is greatly narrowed, the efficiency of annotation and the accuracy of samples are improved,and the time of annotation text data is shortened. At the same time, it improves the efficiency and accuracy of text data classification and public opinion event classification process.

The embodiment of the invention provides an image annotation method and a device thereof. The image annotation method comprises the steps that an initial label set comprising a plurality of labels is obtained for an input image; the label set based similarity degree between the label set of the input image and a label set of a comparison image stored in a data base is calculated; the label set based similarity degree and the vision based similarity degree are subjected to consolidation, so as to obtain the consolidated similarity degree between the input image and the comparison image; and the label set of the input image is updated based on the consolidated similarity degree. According to the embodiment of the invention, low level characteristics and high level semantics of the image can be considered at the same time; the precision of image annotation can be improved; the automatic label annotation is realized; and the annotation efficiency is improved.

The invention discloses an image recognition model training method and device, an image recognition method and device, electronic equipment and a storage medium. A large number of marked training samples can be quickly generated, the training cost is reduced, and the training efficiency is improved. The image recognition model training method comprises the steps: extracting a mapping template containing an identifier from a first image containing the identifier; adding the mapping template into the plurality of second images to obtain a plurality of sample images; taking the sample image and alabeling label corresponding to the sample image as training samples and adding the training samples into a training sample set, wherein the labeling label is determined based on an identifier category to which an identifier contained in a mapping template in the sample image belongs; and training an image recognition model based on the training sample set to obtain an image recognition model capable of recognizing the identifier category to which the identifier contained in the image belongs.

The invention discloses a face sample picture labeling method and device, a computer device and a storage medium. The method comprises: identifying the to-be-labeled picture by using a preset emotionidentification model, the identification result is used as annotation information to be annotated into a to-be-annotated picture; obtaining an error data set in the to-be-labeled picture and outputting the error data set to the client; storing the corrected error data set sent by the client and the correct data set in the to-be-labeled picture as standard samples in a standard sample library; andtraining the emotion recognition model by using the standard sample to update the emotion recognition model, and returning to the step of identifying and labeling the to-be-labeled picture by using the preset emotion recognition model until the error data set in the to-be-labeled picture is empty. According to the technical scheme, the annotation information can be automatically generated for theface image, the annotation efficiency of the face image is improved, and therefore the generation efficiency of the standard sample library used for model training and testing is improved.

The invention discloses a labeling robot, a labeling machine and a labeling method of the labeling machine. The label robot comprises a spider claw robot body, an installation support, a rotary support, a swing mechanism, a label taking mechanism and a controller, wherein the installation support is installed at the lower end of a rotary shaft of the spider claw robot body, the rotary support is installed at the lower end of the installation support in a rotary mode, the swing mechanism is connected with the rotary support, the label taking mechanism is installed on the rotary support, and the controller is electrically connected with the spider claw robot body, the swing mechanism and the label taking mechanism. According to the labeling robot, the labeling machine and the labeling method of the labeling machine, labeling of cartons in different specifications can be achieved, the automation degree is high, and production efficiency is high.