IP Library › Granted Patent US 12,014,447
Granted Patent B2
US 12,014,447 · App. 17/674,495 · Granted Jun 18, 2024

Method and system for dynamic cropping of full body pose images

Inventor: Thiyagarajan Manihatty Bojan (Espoo, FI)
Assignee: Revieve Oy
G06T11/00G06T3/10G06T7/11G06T7/73G06V10/225G06V40/161G06T2207/20021G06T2207/20132G06T2207/30201G06T2210/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,014,447
App. No.
17/674,495
Granted
Jun 18, 2024
Kind
B2
Abstract

Disclosed is method for dynamic cropping of full body pose (FBP) image, method comprising: receiving in computing device FBP image from image resource, wherein FBP image comprises face; detecting in received FBP image area of face by bounding box; detecting coordinates of corner points of bounding box; performing distance approximation of detected area of face in received FBP image; cropping distance approximated area of face of FBP image; performing coordinates mapping transformation of cropped FBP image by mapping coordinates of cropped FBP image to received FBP image; segmenting region of hair of cropped FBP image; masking region of hair of cropped FBP image for obtaining hair polymask; and applying masked FBP image to received FBP image according to performed coordinates mapping for obtaining the dynamically cropped FBP image.

Claims (22)

1. A method for dynamic cropping of a full body pose image, the method comprises:

receiving in a computing device a full body pose image from an image resource, wherein the full body pose image comprises a face;

detecting in the received full body pose image an area of the face by a bounding box;

detecting coordinates of corner points of the bounding box of the area of the face;

performing distance approximation of the detected area of the face in the received full body pose image;

cropping the distance approximated area of the face of the full body pose image;

performing coordinates mapping transformation of the cropped full body pose image by mapping coordinates of the cropped full body pose image in relation to the received full body pose image;

segmenting a region of the hair of the cropped full body pose image;

masking the region of the hair of the cropped full body pose image for obtaining a hair polymask of the region of the hair; and

applying the masked full body pose image to the received full body pose image according to the performed coordinates mapping for obtaining the dynamically cropped full body pose image.

2. The method according to claim 1 , wherein the distance approximation of the detected area of the face comprises:

computing a difference C of a width of the bounding box by calculating absolute value of a difference of a second coordinate of the detected area of the face and a first coordinate of the detected area of the face;

performing normalization of the computed difference C; and

comparing the normalized differences with a pre-determined minimal difference C threshold and a pre-determined maximal difference C threshold.

3. The method according to claim 1 , wherein performing coordinates mapping transformation comprises:

transforming the coordinates of corner points of the rectangle of the cropping area to pixel coordinates of the corner points of the rectangle of the cropping area in the received full body pose image;

remapping the transformed coordinates of corner points of the rectangle of the cropping area to the pixel coordinates in the cropped full body pose image;

determining location coordinates of a crop pixel in the rectangle of the cropping area; and

based on the determined location coordinates of the crop pixel and the pixel coordinates of the corner points of the rectangle of the cropping area in the received full body pose image, determining location coordinates of an original pixel in the received full body pose image.

4. The method according to claim 3 , wherein remapping comprises defining the pixel coordinates in the cropped full body pose image according to coordinates of the top left, top right, bottom left and bottom right pixels of the cropped area.

5. A system for dynamic cropping of a full body pose image, the system comprises a computing device and an image resource, wherein the computing device is configured to carry out the steps of the method according to claim 1 .

6. A computer program for dynamic cropping of a full body pose image comprising instructions adapted to perform the method according to claim 1 , when the computer program is executed by a system comprising a computing device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 17, 2022
From: BOJAN, THIYAGARAJAN MANIHATTY
To: REVIEVE OY
Reel/Frame 059038/0750 →
Continuity (1)
Related Publication 20230260166A1 · Aug 17, 2023