Identification and verification of medication
In some implementations, a device may receive prescription information associated with a medication in a container. The device may cause a camera to capture first image data associated with the medication while the medication is in the container and the container is positioned on a receptacle. The device may cause an adjusting device to reposition the container on the receptacle. The device may cause the camera to capture second image data associated with the medication while the medication is in the container. The device may process, via a neural network, the first image data and the second image data to identify the medication based on depictions of individual units of the medication included in the first image data and the second image data. The device may verify the medication based on the prescription information and an identifier of the medication provided by the neural network.
1. A method, comprising:
receiving, by a device, prescription information associated with a medication in a container;
causing, by the device, a camera device to capture first image data associated with the medication while the medication is in the container and the container is positioned on a receptacle;
causing, by the device, an adjusting device to reposition the container on the receptacle;
causing, by the device, the camera device to capture second image data associated with the medication while the medication is in the container;
processing, by the device and via a neural network, the first image data and the second image data to identify the medication based on depictions of individual units of the medication included in the first image data and the second image data,
wherein the neural network is configured to:
segment the first image data and the second image data into the depictions of the individual units,
determine one or more classification scores of one or more of the depictions of the individual units, and
provide, based on the one or more classification scores, an identifier of the medication; and
verifying, by the device, the medication based on the prescription information and the identifier of the medication provided by the neural network.
2. The method of claim 1 , wherein the prescription information includes at least one of:
the identifier of the medication;
information identifying a dosage of the medication; or
information identifying an amount of the medication.
3. The method of claim 1 , wherein the adjusting device comprises a vibration mechanism that is configured to move the container on the receptacle.
4. The method of claim 1 , further comprising:
causing a weighing device to obtain weight data associated with the medication while the medication is within the container,
wherein the medication is verified based on the prescription information, the identifier, and the weight data.
5. The method of claim 1 , further comprising:
prior to causing the camera device to capture the second image data, adjusting at least one of:
a polarization of a lens of the camera device;
a light filter of the lens of the camera device;
a zoom setting of the camera device; or
a wavelength of a light emitter associated with the camera device.
6. The method of claim 1 , further comprising:
indicating, via a display, that the medication is verified; or
providing, to a medication management system, a notification that the medication is verified in association with the prescription information.
7. A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
receive prescription information associated with a medication in a container,
wherein the container is positioned on a receptacle of the device;
obtain a plurality of images of the medication by iteratively:
adjusting, via an adjusting device, the container on the receptacle to attempt to reposition individual units of the medication within container, and
capturing, via a camera device, image data associated with the medication while the medication is in the container;
process, via a neural network, the plurality of images to identify the medication based on one or more depictions of a unit of the individual units,
wherein the neural network is configured to:
segment one or more of the plurality of images into the one or more depictions of the unit of the individual units,
determine one or more classification scores of the one or more depictions of the unit of the individual units, and
provide an output based on the one or more classification scores; and
verify the medication based on the prescription information and the output provided by the neural network.
8. The device of claim 7 ,
wherein the output includes an identifier of the medication, and
wherein the prescription information includes at least one of:
the identifier of the medication;
information identifying a dose of the medication; or
information identifying an amount of the medication.
9. The device of claim 7 , wherein the receptacle includes a receptacle window that is configured to support the container while the camera device captures the image data,
wherein the camera device is positioned under the receptacle window and the receptacle window is within a field of view of the camera device.
10. The device of claim 7 , wherein images of the plurality of images are iteratively processed after corresponding image data is captured via the camera device,
wherein the images of the plurality of images are obtained until at least one of:
the medication is identified in an image of the plurality of images, or
a predetermined quantity of the plurality of images are obtained.
11. The device of claim 7 , wherein images of the plurality of images are iteratively obtained until a predetermined quantity of the plurality of images are obtained,
wherein the predetermined quantity is associated with a configuration of the neural network.
12. The device of claim 7 , wherein the one or more processors are further configured to:
indicate, via a display, that the medication is verified; or
provide, to a medication management system, a notification that the medication is verified in association with the prescription information.
13. The device of claim 7 , wherein the neural network comprises a convolutional neural network.
14. The device of claim 7 , wherein the one or more processors are further configured to:
adjust one or more of a polarization of a lens of the camera device to reduce reflected light, a light filter of the lens of the camera device to filter a particular wavelength of light, or a wavelength of a light emitter associated with the camera device to adjust a color of light.
15. A medication analysis system comprising:
a receptacle that is configured to support a container on a receptacle window;
a camera device positioned beneath the receptacle window and configured to have the receptacle window within a field of view of the camera device;
an adjusting device configured to move the receptacle to adjust a position of a medication in the container; and
a control device configured to:
cause the adjusting device to reposition the container on the receptacle,
cause the camera device to capture image data associated with the medication, and
process, via a neural network, the image data to identify the medication,
wherein the neural network is configured to:
segment the image data into one or more depictions of one or more individual units of the medication;
determine one or more classification scores of the one or more depictions of the one or more individual units of the medication; and
provide an output for the medication based on the one or more classification scores, and
verify the medication based on the output provided by the neural network.
16. The medication analysis system of claim 15 , wherein the receptacle window includes one or more adjustable filters.
17. The medication analysis system of claim 15 , wherein the adjusting device comprises a vibration mechanism that is configured to move the container on the receptacle.
18. The medication analysis system of claim 15 , further comprising at least one of:
a polarized lens configured to reduce reflected light depicted in images associated with the image data;
a light filter configured to filter a particular wavelength of light from images associated with the image data;
a lens configured to adjust dimensions of the field of view; or
a light emitter configured to adjust a characteristic of light in images associated with the image data.
19. The medication analysis system of claim 15 , wherein the control device, when verifying the medication, is configured to:
obtain prescription information associated with the medication; and
verify the medication based on the prescription information and the output provided by the neural network.
20. The medication analysis system of claim 19 , further comprising:
a weighing device associated with the receptacle that is configured to obtain weight data associated with the medication,
wherein the control device is further configured to:
cause the weighing device to obtain the weight data associated with the medication while the medication is within the container,
wherein the medication is verified based on the prescription information, the output provided by the neural network, and the weight data.