Face model matrix training method, apparatus, and storage medium are provided. The method includes: obtaining a face image library, the face image library including k groups of face images, and each group of face images including at least one face image of at least one person, k>2, and k being an integer; separately parsing each group of the k groups of face images, and calculating a first matrix and a second matrix according to parsing results, the first matrix being an intra-group covariance matrix of facial features of each group of face images, and the second matrix being an inter-group covariance matrix of facial features of the k groups of face images; and training face model matrices according to the first matrix and the second matrix.

Methods of executing patching connection changes in a patching field are provided in which an electronic work order is received on a display located at the patching field, the electronic work order specifying the patching connection change. A technician may perform the patching connection change. Then, an electronic message may be sent from the patching field indicating that the patching change has been completed.

A system includes acquisition of an electronic image of items disposed in first locations, determination, based on the electronic image, of a visit image result comprising a first one or more linear groups, a first one or more facings per linear group and a first zero or more product identifiers per facing, determination of planogram reference data comprising a second one or more linear groups, a second one or more facings per linear group and a second zero or more product identifiers per facing, and determination of one or more corrective actions based on the visit image result and on the planogram reference data.

Methods and systems for determining characteristic(s) of patterns of interest (POIs) are provided. One system is configured to acquire output of an inspection system generated at the POI instances without detecting defects at the POI instances. The output is then used to generate a selection of the POI instances. The system then acquires output from an output acquisition subsystem for the selected POI instances. The system also determines characteristic(s) of the POI using the output acquired from the output acquisition subsystem.

An information processing system includes circuitry configured to store, in a memory, one or more feature value patterns associated with appearance attribute of one or more groups of persons calculated from a plurality of acquired image data using machine learning, in which each one of the groups assumed to have a unique group value being different for each one of the groups, receive image data of a target person input as analysis target data, analyze an appearance attribute of the target person in the image data using the one or more feature value patterns associated with the appearance attribute of the one or more groups stored in the memory, and output a response corresponding to an analysis result of the appearance attribute of the target person.

The present invention, belonging to a field of fingerprint detecting technology, relates to a fingerprint detecting circuit including: a first conductive layer; a second conductive layer; an inverting amplifier, comprising a single input terminal coupled to the first conductive layer; and an output terminal coupled to the second conductive layer; and a switch, configured for establishing a DC operating point of the inverting amplifier, wherein a terminal of the switch is coupled to the input terminal, and another terminal of the switch is coupled to the output terminal. The present invention utilizes the inverting amplifier with single input single output and the switch to quickly and correctly establish the DC biasing point of the inverting amplifier, and convert the sensing capacitance into the output signal. No need for another biasing circuit. The circuit structure thereof is simple and the accuracy is high.

An augmented reality (AR) client terminal identifies initial location information for a location of a user. A scene picture associated with the location of the user is captured. Image matching is performed between the captured scene picture and scene pictures in a scene picture set. The scene picture set is generated based on the initial location information. Each scene picture in the scene picture set is associated with detailed location information. In response to the captured scene picture matching a particular scene picture in the scene picture set, refined location information for the location of the user is determined based on the detailed location information of the particular scene picture.

A smart phone user captures video and still images of a motor and makes a sound recording of his observations. The images and recordings are tagged with a date/time stamp, a serial number, bar code, matrix code, RFID code, or geolocation and sent wirelessly to an infrared camera. The infrared camera has a collocation application that reads the tag and creates a folder which holds the infrared image and the auxiliary information from the smartphone related to an asset. The collocation program also adds icons to the infrared image. By operating the user interface (not shown) of the infrared camera, the user may select an icon to view the images and listen to the sound recording.

An image processing method includes the steps of performing processing of selecting a learning model from a plurality of learning models that have learned a reference used to record an image generated by an image sensor; performing, using the selected learning model, determination processing of determining whether the image generated by the image sensor satisfies the reference; and recording the image in a case in which it is determined that the image generated by the image sensor satisfies the reference, wherein the processing of selecting the learning model is performed based on at least one of an image capturing instruction by a user, an evaluation result of the image by the user, an environment when the image is generated, and a score of each of the learning models for the image generated by the image sensor.

Technology for matching images (for example, video images, still images) of an identical infrastructure object (for example, a tower component of a tower supporting power lines) for purposes of comparing the infrastructure object to itself at different points in time to detect a potential anomaly and the potential need for maintenance of the infrastructure object. In some embodiments, this matching of images is done using creation of a three dimensional (#D) computer model of the infrastructure object and by tagging captured images with location on the 3D model across multiple videos taken at different points in time.