SYSTEMS, METHODS, AND MEDIA FOR CREATING MULTIPLE LAYERS FROM AN IMAGE

• US 20120063680A1
• Filed: 09/15/2011
• Published: 03/15/2012
• Est. Priority Date: 09/15/2010
• Status: Active Grant

• Current Assignee: Kyran Daisy
• Original Assignee: Kyran Daisy
• Inventors: DAISY, Kyran
• Granted Patent: US 8,467,601 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 15/205 Image-based rendering
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 3/14 Transformations for image registration, e.g. adjusting or mapping for alignment of images
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06T 7/50 Depth or shape recovery

Abstract

A method for creating a plurality of layer images from an input image is provided. The method includes analyzing an input image for color content to detect at least one dominant color in the image and for shape recognition to detect at least one object in the image. The method also includes generating a concentric grid for the input image based on the color content analysis and the shape recognition for a depth calculation of the input image. The concentric grid includes a center point, a plurality of lines that radiate from the center point, and a plurality of concentric circles that expand at a spatial distance in the input image. The concentric circles divide the input image into a plurality of sections, each of which represents an equal spatial depth. The method further includes generating a plurality of layer images using at least two of the plurality of sections.

Claims

1. A method for creating a plurality of layer images from an input image, the method comprising:

analyzing an input image for color content to detect at least one dominant color in the input image;

analyzing the input image for shape recognition to detect at least one object in the input image;

generating a concentric grid for the input image based on the color content analysis and the shape recognition for a depth calculation of the input image, the concentric grid including a center point, a plurality of lines that radiate from the center point, and a plurality of concentric circles that expand at a spatial distance in the input image, the concentric circles dividing the input image into a plurality of sections, each of the plurality of sections representing an equal spatial depth; and

generating a plurality of layer images using at least two of the plurality of sections.

2. The method of claim 1, wherein the depth calculation includes using ratios of spatial dimensions of an outermost section of the plurality of sections to spatial dimensions of inner sections of the plurality of sections that are closer to the center point.

3. The method of claim 1, further comprising analyzing the input image to determine at least one of a horizontal horizon line and a vertical horizon line in the input image based on at least one of the color content analysis and the shape recognition.

4. The method of claim 3, wherein the horizontal horizon line and the vertical horizon line are used to determine the center point of the concentric grid.

5. The method of claim 1, wherein an order of the plurality of layer images is determined by a direction of perceived depth based on the depth calculation.

6. The method of claim 1, wherein the shape recognition is performed using a shape library, the shape library including a series of geometric shapes and patterns, a series of combinations of shapes, and a series of letters and text.

7. The method of claim 1, wherein the color content analysis is performed using a color library, the color library including a spectrum of colors, a color saturation scale, and a color intensity scale.

8. The method of claim 1, wherein analyzing the input image for the shape recognition to detect the at least one object in the input image includes correlating a detected shape to at least one already recognized object within the input image to determine if the detected shape matches near objects.

9. The method of claim 1, wherein the input image includes a monochromatic image and wherein, if the at least one dominant color in the monochromatic image is detected throughout more than a predetermined percentage of the monochromatic image, analyzing the monochromatic image for shape recognition includes:

desaturating the monochromatic image to detect shapes based on shape outlines; and

resaturating the monochromatic image.

10. The method of claim 1, further comprising calculating a degree of shadow on each of the at least one object in the input image detected through the shape recognition by analyzing pixel data of each of the detected at least one object and comparing a percentage of color change of each detected object to its neighboring objects.

11. The method of claim 1, further comprising determining a light source direction and a light source angle of the input image by comparing and analyzing shadow color gradient of the at least one object detected through the shape recognition.

12. A system for creating a plurality of layer images from an input image, the system comprising:

a memory capable of storing data; and

a processor coupled to the memory and configured to use the data such that the system can;

analyze an input image for color content to detect at least one dominant color in the input image;

analyze the input image for shape recognition to detect at least one object in the input image;

generate a concentric grid for the input image based on the color content analysis and the shape recognition for a depth calculation of the input image, the concentric grid including a center point, a plurality of lines that radiate from the center point, and a plurality of concentric circles that expand at a spatial distance in the input image, the concentric circles dividing the input image into a plurality of sections, each of the plurality of sections representing an equal spatial depth; and

generate a plurality of layer images using at least two of the plurality of sections.

13. The system of claim 12, wherein the depth calculation includes using ratios of spatial dimensions of an outermost section of the plurality of sections to spatial dimensions of inner sections of the plurality of sections that are closer to the center point.

14. The system of claim 13, wherein the horizontal horizon line and the vertical horizon line are used to determine the center point of the concentric grid.

15. The system of claim 12, wherein the data includes a shape library having a series of geometric shapes and patterns, a series of combinations of shapes, and a series of letters and text and wherein the shape recognition is performed using the shape library.

16. The system of claim 12, wherein the data includes a color library having a spectrum of colors, a color saturation scale, and a color intensity scale and wherein the color content analysis is performed using the color library.

17. The system of claim 12, wherein analyzing the input image for the shape recognition to detect the at least one object in the input image includes correlating a detected shape to at least one already recognized object within the input image to determine if the detected shape matches near objects.

18. The system of claim 12, wherein the system is further configured to use the data such that the system can calculate a degree of shadow on each of the at least one object in the input image detected through the shape recognition by analyzing pixel data of each of the detected at least one object and comparing a percentage of color change of each detected object to its neighboring objects.

19. The system of claim 12, wherein the system is further configured to use the data such that the system can determine a light source direction and a light source angle of the input image by comparing and analyzing shadow color gradient of the at least one object detected through the shape recognition.

20. A non-transitory computer readable storage medium storing computer executable instructions that, when executed on a processor, cause the processor to perform a method for creating a plurality of layer images from an input image, the method comprising:

analyzing an input image for color content to detect at least one dominant color in the input image;

analyzing the input image for shape recognition to detect at least one object in the input image;

analyzing the input image to determine a horizontal horizon line and a vertical horizon line in the input image based on the color content analysis and the shape recognition, wherein the horizontal horizon line and the vertical horizon line are used to determine a furthest point in the input image;

generating a concentric grid for the input image using the furthest point for a depth calculation of the input image, the concentric grid including a center point, a plurality of lines that radiate from the center point, and a plurality of concentric circles that expand at a spatial distance in the input image, the concentric circles dividing the input image into a plurality of sections, each of the plurality of sections representing an equal spatial depth, wherein the center point is determined based on the furthest point and wherein the depth calculation includes using ratios of spatial dimensions of an outermost section of the plurality of sections to spatial dimensions of inner sections of the plurality of sections that are closer to the center point; and

generating a plurality of layer images using at least two of the plurality of sections, wherein an order of the plurality of layer images is determined by a direction of perceived depth based on the depth calculation.