Method for optimal body or face protection with adaptive dewarping based on context segmentation layers
A method for enhancing a wide angle image to improve the perspectives and the visual appeal thereof wide-angle images uses custom adaptive dewarping. The method is based on the scene image content of recognized objects in the image, the position of these objects in the image, the depth of these objects in the scene with respect to other objects and the general context of the image.
1. A method for enhancing an image based on image context and segmentation layers, the method comprising:
a. receiving, by a processor, an original image created by an imager and having a plurality of elements, each element being in one of a foreground or a background of the original image;
b. segmenting, by the processor, the original image into a plurality of segmented layers, each of the segmented layers including at least one of the elements, the segmentation being based on at least one of a shape of one or more of the elements, a position of one or more of the elements in the original image, or a depth of one or more of the elements compared to other elements;
c. processing, by the processor, at least one of the segmented layers, creating at least one processed layer, the creation of the at least one processed layer resulting in at least one zone of missing information; and
d. merging, by the processor, the at least one processed layer with the other segmented layers to form a final image.
2. The method of claim 1 , wherein the original image is captured by the imager, the imager being an optical system comprising at least a camera and a lens.
3. The method of claim 2 wherein the diagonal field of view of the lens is at least over 60°.
4. The method of claim 1 , wherein at least one of the elements is in the foreground of the original image, and the segmentation of the at least one foreground element is based on the relative depth compared to other elements, the relative depth being calculated by an artificial intelligence neural network.
5. The method of claim 1 , wherein the processing step further includes at least one of blurring the at least one processed layer, rotating the at least one processed layer, translating the at least one processed layer, scaling the at least one processed layer, correcting the perspective tilt of the at least one processed layer or stabilizing the at least one processed layer.
6. The method of claim 1 , wherein an inpainting technique is used to complete the at least one zone of missing information.
7. The method of claim 1 , wherein the at least one zone of missing information is hidden by scaling of the at least one processed layer.
8. The method of claim 1 , wherein merging the at least one processed layer with the other layers is done by adjusting either a texture or a display mesh.
9. A device for enhancing an image based on image context and segmentation layers, the device comprising:
a. an imager creating an original image having a plurality of elements, each element being in one of a foreground or a background of the original image; and
b. a processor configured to:
i. segment the original image into a plurality of segmented layers, each of the segmented layers including at least one of the elements, the segmentation being based on at least one of a shape of one or more of the elements, a position of one or more of the elements in the original image, or a depth of one or more of the elements compared to other elements,
ii. process at least one of the segmented layers, creating at least one processed layer, the creation of the at least one processed layer resulting in at least one zone of missing information, and
iii. merge the at least one processed layer with the other segmented layers to form a final image.
10. The device of claim 9 , wherein the imager is an optical system comprising at least a camera and a lens.
11. The device of claim 10 wherein the diagonal field of view of the lens is at least over 60°.
12. The device of claim 9 , wherein at least one of the elements is in the foreground of the original image, and the segmentation of the at least one foreground element is based on the relative depth compared to other elements, the relative depth being configured to be calculated by an artificial intelligence neural network.
13. The device of claim 9 , wherein the processor, in the processing step, is further configured to at least one of blur the at least one processed layer, rotate the at least one processed layer, translate the at least one processed layer, scale the at least one processed layer, correct the perspective tilt of the at least one processed layer or stabilize the at least one processed layer.
14. The device of claim 9 , wherein the processor is configured to use an inpainting technique to complete the at least one zone of missing information.
15. The device of claim 9 , wherein the processor is configured to hide the at least one zone of missing information by scaling of the at least one processed layer.
16. The device of claim 9 , wherein the processor is configured to merge the at least one processed layer with the other layers by adjusting either a texture or a display mesh.