Generating Synthetic Image Data
AssigneeSynapse Technology Corporation
InventorsIan Cinnamon, Bruno Brasil Ferrari Faviero, Simanta Gautam
Life of this patent
Estimating the term…
Abstract
According to an aspect, a method comprises: generating a 2D projection from a 3D representation of an object, wherein the 2D projection comprises an edgemapped projection of the 3D representation, generating, with a generative adversarial neural network (GAN), and based on the edgemapped projection, a simulated image of the object, wherein the simulated image appears as though the object has been scanned by a detection device, combining the simulated image of the object with a background image to form a synthesized image, wherein the background image was captured by a detection device, and outputting the synthesized image.
Claims21
1-20. (canceled)
A method for generating synthesized images for use in a security screening system, the method comprising:
- obtaining, by a processor, an image of a bag that is captured by scanning device of the security system;
- obtaining, by the processor, an image of an object;
- generating, by a first GAN and based on the image of the object, a synthesized image of the object that has image characteristics of images of a type of the object captured by the scanning device;
- overlaying, by the processor, the image of the bag with the synthesized image of the object to form an overlaid image;
- inputting a selected region of the overlaid image into a second GAN;
- refining, by the second GAN, the selected region of the overlaid image to have image characteristics of the image of the bag, thereby forming a refined overlaid image;
- and
- after forming the refined overlaid image:
- training an object detection algorithm with the refined overlaid image.
A system for generating for generating synthesized images for use in a security screening system, the system comprising:
- a memory storing instructions thereon;
- and
- at least one processor, wherein the instructions stored on the memory cause the at least one processor to:
- obtain an image of a bag that is captured by scanning device of the security system;
- obtain an image of an object;
- generate, by a first GAN and based on the image of the object, a synthesized image of the object that has image characteristics of images of a type of the object captured by the scanning device;
- overlay the image of the bag with the synthesized image of the object to form an overlaid image;
- input a selected region of the overlaid image into a second GAN;
- refine, by the second GAN, the selected region of the overlaid image to have image characteristics of the image of the bag, thereby forming a refined overlaid image;
- and
- display the refined synthesized image to a user of the baggage security screening system.
A non-transitory computer-readable storage medium comprising instructions stored thereon for generating synthesized images for use in a baggage security system, wherein the instructions, when executed, cause at least one processor to:
- obtain an image of a bag that is captured by scanning device of the security system;
- obtain an image of an object;
- generate, by a first GAN and based on the image of the object, a synthesized image of the object that has image characteristics of images of a type of the object captured by the scanning device;
- overlay the image of the bag with the synthesized image of the object to form an overlaid image;
- inputting a selected region of the overlaid image into a second GAN;
- refine, by the second GAN, the selected region of the overlaid image to have image characteristics of the image of the bag, thereby forming a refined overlaid image;
- and
- train an object detection algorithm with the refined overlaid image.
Dependencies are inferred from the claim text.