13 results about "Photo identification" patented technology

The embodiment of the invention discloses a merchant door head photo identification method, device and equipment and a medium, and relates to the technical field of door head photo identification. The method comprises the following steps: acquiring a target door head picture of a merchant, and inputting the target door head picture into a door head segmentation model to obtain a door head region; performing text extraction on the door head region to obtain a text set, and determining a text position and text size information corresponding to each text in the text set; inputting the text set into a text classification model to obtain a classification result of each text; the classification result reflects whether each text is a merchant name; determining a target text in each text of the text set according to the classification result of each text, the text position and the text size information; the content of the target text is a merchant name. According to the technical scheme, the effect of automatically recognizing the merchant name is achieved, the recognition efficiency is greatly improved compared with a manual labeling mode, and the recognition accuracy is greatly improved compared with an OCR recognition mode.

A method for generating a digital ID comprising capturing one or more user images of user's face, transmitting the one or more user images or data derived therefrom to a verification server and determining if the one or more images represent a live person. Capturing an ID image of a photo identification for the user and transmitting the ID image to the verification server. Comparing at least one of the one or more user images or data derived therefrom to the image of the user on the photo identification to determine if user in the one or more user images is the same person as the image on the photo identification. Responsive to a match from the comparing and a determination that a live person was captured in the one or more user images, generating a user digital ID, and transmitting the user digital ID to the user.

The invention discloses a borehole stratum handwritten record information identification method. The method comprises the following steps: S1, constructing a basic sample set of borehole stratum handwritten records; s2, training an information identification basic model of the hand-written record of the drilling stratum; s3, constructing a project-level sample set of the hand-written record of the drilling stratum; s4, training a project-level identification model of the hand-written record of the drilling stratum; s5, constructing a stratigraphic record space nested confusion text dictionary; s6, identifying and automatically correcting the handwritten record picture of the drilling stratum information; s7, manually checking an identification result; s8, adding the recognition text corrected in the step S7 and the corresponding handwritten record photo to the item-level sample set in the step S3, training the item-level recognition model, and adding an error recognition text and a corrected text to a confusion text dictionary; and S9, executing S6 and S7 for a next to-be-identified task to obtain a final identification result. According to the method, the recognition accuracy and the working efficiency of the handwritten record of the drilling stratum are remarkably improved.

Methods and systems can protect information shown on a screen of a device. A user associated with the device can be authenticated, e.g., using photo identification of the user. In response to authenticating the user, data can be displayed on the device. A camera associated with the device can be automatically activated to take one or more images in response to a triggering event, a predetermined time interval, or randomly generated time intervals. An enhanced privacy environment is detected by analyzing the one or more images to identify that there are more than a threshold number of faces or people in the picture, or by identifying that the user is not in the picture based on a comparison of the picture to the photo identification of the user. In response to detecting the enhanced privacy environment, a privacy mode is enabled. The privacy mode can include various security measures such as concealing sensitive content or providing various security notifications.

A method is implemented by an electronic device and includes transmitting a registration request of a first user; receiving photo identification information including performance image information; identifying a preliminary group of images stored on the electronic device, at least in part based on the performance image information; and displaying the preliminary group of images.

The present application relates to the technical field of solid waste transportation data management, and provides a pollution solid waste transportation whole-process digital closed-loop management method and system, which establishes a transportation basic information database, creates transportation plans and transportation tasks based on the transportation basic information database, combines the exit information collected by the starting point barrier equipment, the transportation track collected by the GPS positioning equipment, and the on-site photo and scale photo identification results uploaded in the exit, weighing and unloading links, carries out associated processing on the time information, vehicle identification information and weight information in the transportation process, generates transportation metering records and digital accounts, can realize unified digital management of plans, execution, track, metering and records in the whole process of pollution solid waste transportation, improve the completeness and correspondence of transportation process information, and reduce the management cost and error risk caused by manual recording and paper circulation.

A method for generating a digital ID comprising capturing one or more user images of user's face, transmitting the one or more user images or data derived therefrom to a verification server and determining if the one or more images represent a live person. Capturing an ID image of a photo identification for the user and transmitting the ID image to the verification server. Comparing at least one of the one or more user images or data derived therefrom to the image of the user on the photo identification to determine if user in the one or more user images is the same person as the image on the photo identification. Responsive to a match from the comparing and a determination that a live person was captured in the one or more user images, generating a user digital ID, and transmitting the user digital ID to the user.

The invention provides a proof photo conformity judgment method. The proof photo conformity judgment method comprises the steps of obtaining a reported land class and n proof photos matched with the reported land class; using a recognition model to perform land type recognition on the n proof photos, and averaging recognition results to obtain a quasi-recognition result, the quasi-recognition result including r prediction probabilities indicating r land types; judging the confidence coefficient of the quasi-recognition result, if the quasi-recognition result is credible, constructing a nearest land class set by using k land classes indicated by the maximum k prediction probabilities in the quasi-recognition result, and judging whether the reported land class falls into the nearest land class set, and if so, proving that the photo is consistent with the reported land class; and if not, turning to manual auditing. According to the method, land type identification is directly carried out on the proof photo through the identification model, the manual workload can be reduced, the conformity judgment efficiency is improved, the pattern spot land type is determined based on a group of proof photo identification results, judgment is carried out by utilizing the closest land type set, and the conformity judgment accuracy can be improved.

The application discloses a kind of road mileage stake number identification device and correction method, it is related to road mileage measurement technical field, including mounting frame, mounting frame is installed with mileage wheel, the wheel surface of mileage wheel is contacted with ground, camera is installed at mileage wheel, and mileage wheel is also provided with trigger mechanism, trigger mechanism and camera are configured, mileage wheel is after driving a fixed distance, trigger mechanism triggers camera to take a photo to stake number direction once.This application is aimed at the position of vehicle when taking a photo in the actual photo identification in prior art, the position of vehicle when taking a photo can exist in the misalignment of stake number, therefore, the actual distance of vehicle at this time cannot accurately represent the actual distance of this stake number, and the correction coefficient obtained also has error and other problems are improved.This application has the advantages that by setting two laser emitters, when taking a photo, the laser points emitted by the two laser emitters can be used as reference to obtain more accurate data.

A method is implemented by an electronic device and includes transmitting a registration request of a first user; receiving photo identification information including performance image information; identifying a preliminary group of images stored on the electronic device, at least in part based on the performance image information; and displaying the preliminary group of images.

A method of ordering and receiving goods is disclosed. According to an example embodiment, the method comprises: registering a user with an online entity to create a user account, the registration process includes: taking a photograph of the user's face next to a photo identification (ID) issued to the user, transmitting the photograph and the user's signature to the online entity, and receiving confirmation of creation of the user account from the online entity; submitting an order under the user account for the goods; receiving a delivery of the goods in a secured container; receiving a passcode separate from the delivery; and utilizing the passcode to unlock the secured container and retrieve the goods.

A transaction terminal captures at least one image of a customer during a checkout and the customer is asked to place a photo identification card in view of the camera where a second image is captured of the card. The second image is converted to text and various components of the card are validated. Any hologram on the card is verified from the second image. The photo on the card is compared to facial features in the customer image and a determination is made as to whether the customer's identification can or cannot be verified. When verified, a message is sent to an attendant's device with the determination that the customer and card were verified along with the customer image and card image. The attendant is asked to confirm the verification and when confirmed the terminal resumes processing the checkout on behalf of the customer.