Disclosed are systems and methods for a dispensing cabinet incorporating an image based counting system that includes one or more imaging devices (e.g., one or more color cameras) to capture images of one or more items (e.g., pills, capsules, pharmaceutical units, items for medical use, etc.). Control circuitry of the image based counting system is configured to determine one or more properties of the one or more items based on the images. The dispensing cabinet includes a cabinet housing comprising one or more containers to hold the one or more items, which may employ mounting hardware to releasably secure the image based counting system to the cabinet housing.

A pill identification system identifies a pill type for a pharmaceutical composition from images of the pharmaceutical composition. The system extracts features from images taken of the pill. The features extracted from the pill image include color, size, shape, and surface features of the pill. In particular, the features include rotation-independent surface features of the pill that enable the pill to be identified from a variety of orientations when the images are taken. The feature vectors are applied to a classifier that determines a pill identification for each image. The pill identification for each image is scored to determine identification for the pharmaceutical composition.

A method for providing a singling device of a storage and dispensing container for drug portions is provided. A singling device is adapted to a specific drug portion based on the measurement of the drug portion. The measurement is obtained by generating at least one image of a to-be-measured drug portion by a detection device and using image analysis to process the at least one image. Drug information for the specific drug portion is determined, the drug information including at least the dimensions of the specific drug portion. Based on the determined drug information, a singling device fitting the drug portion to be singularized is identified and provided for use in the storage and dispensing container. A system for identifying a singling device is also provided.

A unit-dose medicament inspection system and method provide for the obtainment of an image of a receptacle after a corresponding filling operation in which a predetermined unit-dose medicament was to have been located in the receptacle. The image may be processed to extract image data that may be compared with stored data corresponding with a predetermined unit-dose medicament. Size, configuration and other features of objects located within a receptacle may be included with the extracted image data and compared with corresponding stored data to determine whether a given receptacle includes the intended medicament and/or whether the medicament located within the receptacle is an acceptable condition. Receptacle attributes may also be inspected for compliance with predetermined configuration parameters.

A system and method for training a system for monitoring administration of medication. The method includes the steps of a method for training a medication administration monitoring apparatus, comprising the steps of defining one or more predetermined medications and then acquiring information from one or more data sources of a user administering medication. A first network is trained to recognize a first step of a medication administration sequence, and then a second network is trained to recognize a second step of a medication administration sequence based upon the training of the first network.

A system classifies materials utilizing a vision system that implements a machine learning system, such as a neural network, in order to identify or classify each of the materials as either a monetary coin or not a monetary coin, which may then be sorted into separate groups based on such an identification or classification. Such a system can sort monetary coins from other forms of scrap, which may have been produced from a shredding of end of life vehicles.

The present disclosure teaches a method of utilizing image “match points” to measure and detect changes in a physical object. In some cases “degradation” or “wear and tear” of the physical object is assessed, while in other applications this disclosure is applicable to measuring intentional changes, such as changes made by additive or subtractive manufacturing processes, which may, for example, involve adding a layer or removing a layer by machining. A system may include a scanner, and a digital fingerprinting process, coupled to an object change computer server. The server is coupled to a datastore that stores class digital fingerprints, selected object digital fingerprints collected over time, match measurements, and deterioration metrics.

System and method for automatic computer aided optical recognition of toys, for example, construction toy elements, recognition of those elements on digital images and associating the elements with existing information is presented. The method and system may recognize toy elements of various sizes invariant of toy element distance from the image acquiring device for example camera, invariant of rotation of the toy element, invariant of angle of the camera, invariant of background, invariant of illumination and without the need of predefined region where a toy element should be placed. The system and method may detect more than one toy element on the image and identify them. The system is configured to learn to recognize and detect any number of various toy elements by training a deep convolutional neural network.

Methods for measuring and verifying drug portions while avoiding the need to teach verification devices is provided. Characteristic key data of a drug type are compiled with a calibrated camera of a measuring device, stored in a storage device, and retrieved from or transmitted to a verification device. Individual key data for a drug portion to be verified are compiled using a calibrated camera of the verification device and compared with the characteristic key data. A digital image of a drug portion to be verified is generated with a calibrated camera and transferred to a control unit. The control unit determines individual key data for the drug portion to be verified using known calibration parameters of the camera and the digital image, compares the individual key data with characteristic key data of the corresponding drug type and verifies or rejects the drug portion based on the results of the comparison. Systems and computer readable medium are also provided.

Provided is a server for determining whether medication has been administered, the server including: a transceiver receiving a video recorded by a wearable device; a memory storing a detection model and a confirmation model, wherein the detection model is trained to output whether each of preset targets appears in an image, and the confirmation model is trained to output whether medication has been administered, wherein the preset targets include an object related to a medicine or a medicine container and a posture related to medication administration; and one or more processors configured to detect the preset targets by inputting image frames of the video to the detection model and to determine whether medication has been administered by inputting confirmation model input data to the confirmation model, the confirmation model input data generated based on a detection result of the detection model.