Generating graphical representation of scanned objects
According to an aspect, a system comprises at least one processor, a memory, and a non-transitory computer-readable storage medium storing instructions. The stored instructions are executable to cause the at least one processor to: receive a digital image that represents an object scanned by a security scanning device, receive, from a neural network, information indicating an item identified within the image, receive, from a database, item data for the identified item, and generate, for output at a display, a graphical representation corresponding to the identified item based on the received item data, wherein the graphical representation indicates a location of the identified item by a neural network, and wherein the generated graphical representation comprises at least a portion of the digital image corresponding to the identified item, and output, for display, the graphical representation.
1. A method comprising:
receiving a digital image that represents an object scanned by a detection device of a given security system;
determining that the digital image comprises a first item of a first classification of interest utilizing at least one neural network that is configured to perform object detection on the digital image to localize a target within the digital image followed by performing a classification task based on the localized target;
determining that the digital image comprises a second item of a second classification of interest that differs from the first classification of interest utilizing a classification technique that differs from utilizing the at least one neural network;
based on determining that (i) the first item of the first classification of interest and (ii) the second item of the second classification of interest are deemed to be a security threat for the given security system, generating, for output at a display, a visualization for the object scanned by the detection device that comprises (i) at least a portion of the digital image, (ii) a first indicator indicating a location of the first item within the digital image, wherein the first indicator comprises a first visualization characteristic corresponding to the first classification of interest, and (iii) a second indicator indicating a location of the second item within the digital image, wherein the second indicator comprises a second visualization characteristic corresponding to the second classification of interest, wherein the first visualization characteristic and the second visualization characteristic differ; and
causing the display to output the visualization for the object scanned by the detection device.
2. The method of claim 1 , wherein determining that the digital image comprises the first item of the first classification of interest comprises
determining that the first item comprises at least one component of a plurality of components that combine to form a particular item; and
wherein generating the visualization for the object scanned by the detection device further comprises generating a graphical representation of the at least one component.
3. The method of claim 2 ,
wherein generating the graphical representation of the at least one component comprises at least one of: generating a graphical representation of a component that is similar to the at least one component, or generating a three-dimensional (3D) model of the particular item to which the at least one component belongs.
4. The method of claim 3 , further comprising:
determining at least one additional component that is associated with the at least one component; and
wherein generating the graphical representation of the at least one component comprises generating a graphical representation of the at least one additional component.
5. The method of claim 1 , further comprising:
determining a first threat level associated with the first classification of interest; and
wherein the first visualization characteristic corresponding to the first classification of interest is defined at least in part on the first threat level.
6. The method of claim 5 , further comprising:
determining a second threat level associated with the second classification of interest; and
wherein the second visualization characteristic corresponding to the second classification of interest is defined at least in part on the second threat level.
7. The method of claim 5 ,
wherein the first visualization characteristic corresponding to the first classification of interest comprises at least one of:
a heat map corresponding to the first threat level, a bounding-polygon characteristic corresponding to the first threat level, or a color coding corresponding to the first threat level.
8. A system comprising:
at least one processor; and
a non-transitory computer-readable storage medium comprising instructions that are executable by the at least one processor to cause the system to:
receive a digital image that represents an object scanned by a detection device of a given security system;
determine that the digital image comprises a first item of a first classification of interest utilizing at least one neural network, that is configured to perform object detection on the digital image to localize a target within the digital image followed by performing a classification task based on the localized target;
determine that the digital image comprises a second item of a second classification of interest that differs from the first classification of interest utilizing a classification technique that differs from utilizing the at least one neural network;
based on determining that (i) the first item of the first classification of interest and (ii) the second item of the second classification of interest are deemed to be a security threat for the given security system, generate, for output at a display, a visualization for the object scanned by the detection device that comprises (i) at least a portion of the digital image, (ii) a first indicator indicating a location of the first item within the digital image, wherein the first indicator comprises a first visualization characteristic corresponding to the first classification of interest, and (iii) a second indicator indicating a location of the second item within the digital image, wherein the second indicator comprises a second visualization characteristic corresponding to the second classification of interest, wherein the first visualization characteristic and the second portion visualization characteristic differ; and
cause the display to output the visualization for the object scanned by the detection device.
9. The system of claim 8 , wherein the instructions that are executable by the at least one processor to cause the system to determine that the digital image comprises the first item of the first classification of interest comprise instructions that are executable by the at least one processor to cause the system to determine that the first item comprises at least one component of a plurality of components that combine to form a particular item; and
wherein the instructions that are executable by the at least one processor to cause the system to generate the visualization for the object scanned by the detection device comprise instruction that are executable by the at least one processor to cause the system to generate a graphical representation of the at least one component.
10. The system of claim 9 , wherein the instructions that are executable by the at least one processor to cause the system to generate the graphical representation of the at least one component comprise instructions that are executable by the at least one processor to cause the system to at least one of: generate a graphical representation of a component that is similar to the at least one component, or generating a three-dimensional (3D) model of the particular item to which the at least one component belongs.
11. The system of claim 10 , wherein the instructions are further executable by the at least one processor to cause the system to determine at least one additional component that is associated with the at least one component; and
wherein the instructions that are executable by the at least one processor to cause the system to generate the graphical representation of the at least one component comprise instructions that are executable by the at least one processor to cause the system to generate a graphical representation of the at least one additional component.
12. The system of claim 8 , wherein the instructions are further executable by the at least one processor to cause the system to determine a first threat level associated with the first classification of interest; and
wherein the first visualization characteristic corresponding to the first classification of interest is defined at least in part on the first threat level.
13. The system of claim 12 , wherein the instructions are further executable by the at least one processor to cause the system to determine a second threat level associated with the second classification of interest; and
wherein the second visualization characteristic corresponding to the second classification of interest is defined at least in part on the second threat level.
14. The system of claim 12 ,
wherein the first visualization characteristic corresponding to the first classification of interest comprises at least one of:
a heat map corresponding to the first threat level, a bounding-polygon characteristic corresponding to the first threat level, or a color coding corresponding to the first threat level.
15. A non-transitory computer-readable storage medium comprising instructions that are executable by at least one processor to cause a computing system to:
receive a digital image that represents an object scanned by a detection device of a given security system;
determine that the digital image comprises a first item of a first classification of interest utilizing at least one neural network that is configured to perform object detection on the digital image to localize a target within the digital image followed by performing a classification task based on the localized target;
determine that the digital image comprises a second item of a second classification of interest that differs from the first classification of interest utilizing a classification technique that differs from utilizing the at least one neural network;
based on determining that (i) the first item of the first classification of interest and (ii) the second item of the second classification of interest are deemed to be a security threat for the given security system, generate, for output at a display, a visualization for the object scanned by the detection device that comprises (i) at least a portion of the digital image, (ii) a first indicator indicating a location of the first item within the digital image, wherein the first indicator comprises a first visualization characteristic corresponding to the first classification of interest, and (iii) a second indicator indicating a location of the second item within the digital image, wherein the second indicator comprises a second visualization characteristic corresponding to the second classification of interest, wherein the first visualization characteristic and the second visualization characteristic differ; and
cause the display to output the visualization for the object scanned by the detection device.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions that are executable by the at least one processor to cause the computing system to determine that the digital image comprises the first item of the first classification of interest comprise instructions that are executable by the at least one processor to cause the computing system to determine that the first item comprises at least one component of a plurality of components that combine to form a particular item; and
wherein the instructions that are executable by the at least one processor to cause the computing system to generate the visualization for the object scanned by the detection device comprise instruction that are executable by the at least one processor to cause the computing system to generate a graphical representation of the at least one component.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions are further executable by the at least one processor to cause the computing system to determine a first threat level associated with the first classification of interest; and
wherein the first visualization characteristic corresponding to the first classification of interest is defined at least in part on the first threat level.
18. The non-transitory computer-readable storage medium of claim 17 ,
wherein the first visualization characteristic corresponding to the first classification of interest comprises at least one of:
a heat map corresponding to the first threat level, a bounding-polygon characteristic corresponding to the first threat level, or a color coding corresponding to the first threat level.
19. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions are further executable by the at least one processor to cause the computing system to determine a second threat level associated with the second classification of interest; and
wherein the second visualization characteristic corresponding to the second classification of interest is defined at least in part on the second threat level.
20. The non-transitory computer-readable storage medium of claim 15 , wherein the at least one neural network is a first neural network, and wherein the instructions that are executable by the at least one processor to cause the computing system to determine that the digital image comprises the second item of the second classification of interest that differs from the first classification of interest comprise instructions that are executable by the at least one processor to cause the computing system to determine that the digital image comprises the second item of the second classification of interest that differs from the first classification of interest utilizing a second neural network that differs from the first neural network.