US 12,243,316 B2
Method and system of prescreening objects for permission based activities
John F. Jasinski, Jr., Hammonton, NJ (US)
Assigned to The Government of the United States of America, as represented by the Secretary of Homeland Security, Washington, DC (US)
Filed by The Government of the United States of America, as represented by the Secretary of Homeland Security, Washington, DC (US)
Filed on Mar. 19, 2024, as Appl. No. 18/609,209.
Claims priority of provisional application 63/453,576, filed on Mar. 21, 2023.
Prior Publication US 2024/0320979 A1, Sep. 26, 2024
Int. Cl. G06V 20/52 (2022.01)
CPC G06V 20/52 (2022.01) [G06V 2201/07 (2022.01)] 26 Claims
OG exemplary drawing
 
1. A prescreening system comprising:
an image capture device to capture an image of one or more items for a user; and
a memory and a processor configured to:
process digitally the image of the one or more items by image recognition, the processor including (i) an object recognition module to perform object recognition, (ii) a 2D image to 3D model processing module to perform 2D image to 3D model processing, (iii) a size analysis module to perform size analysis, and (iv) an occluded image processing module to perform occluded image processing, of the image of the one or more items;
analyze the image processed by image recognition to determine whether any of the one or more items are listed on a list;
if none of the one or more items in the image is listed on the list, inform the user that none of the one or more items in the image is listed on the list; and
if any of the one or more items in the image is listed on the list as one or more flagged items, identify each item in the image which is listed on the list to the user;
calculate a confidence score representing a level of confidence by statistically analyzing data generated by analyzing the image processed by image recognition and by using weighting factors corresponding to image processes of the object recognition module, the 2D image to 3D model processing module, the size analysis module, and the occluded image processing module, of the image of the one or more items, the weighting factors assigning different weights to contributions of the image processes to the confidence score; and
prompt the user to take action with regard to the one or more flagged items based on the confidence score, the action for the one or more flagged items including at least one of (i) taking one or more additional still photographs of the one or more items from different angles or different distances or both as one or more additional images for additional image processing by image recognition, (ii) taking a video of the one or more items by moving the image capture device around from different angles or different distances or both as one or more additional images for additional image processing by image recognition, or (iii) moving the one or more flagged items to different positions and capturing one or more additional images for additional image processing by image recognition.