초록 ▼

Some embodiments of the image editing and organizing application described herein provide an automatic enhancement process that includes a shadow lift adjustment. The process takes an input image and enhances the contrast of darker parts of the image. The process uses a structure histogram to determ

Some embodiments of the image editing and organizing application described herein provide an automatic enhancement process that includes a shadow lift adjustment. The process takes an input image and enhances the contrast of darker parts of the image. The process uses a structure histogram to determine an amount of shadow lift adjustment to apply to the image. The process tempers this adjustment based on an International Organization for Standardization (ISO) value of the image.

대표청구항 ▼

1. A method of automatically adjusting shadow levels of an image, the method comprising: generating a set of histograms that identify different characteristics of the image, wherein the set of histograms comprises a structure histogram comprising values based on relationships between each particular

1. A method of automatically adjusting shadow levels of an image, the method comprising: generating a set of histograms that identify different characteristics of the image, wherein the set of histograms comprises a structure histogram comprising values based on relationships between each particular pixel of a plurality of pixels in the image and the neighboring pixels of the particular pixel;determining a shadow lift setting level based on a set of statistics calculated for the set of histograms; andapplying a shadow lift at the determined shadow lift setting level to the image, wherein the generating, determining and applying are performed by an electronic device. 2. The method of claim 1, wherein the relationships on which the structure histogram values are based comprise differences between luminance values of the particular pixels and the neighboring pixels of the particular pixels. 3. The method of claim 1, wherein a relationship between a particular pixel and a neighboring pixel contributes to a value of the structure histogram only when a luminance value of the particular pixel is different from a luminance value of the neighboring pixel. 4. The method of claim 1, wherein the set of histograms further comprises a luminance histogram. 5. The method of claim 1, wherein the set of histograms further comprises a cumulative luminance histogram. 6. The method of claim 1 further comprising: determining an ISO value of the image; andreducing the applied shadow lift setting level based on the ISO value. 7. The method of claim 6, wherein reducing the applied shadow lift setting level based on the ISO value comprises lowering the shadow lift setting value more for higher ISO values than for lower ISO values. 8. An electronic device comprising: a set of processing units; anda non-transitory machine-readable medium storing a program which when executed by at least one of the processing units enhances an image comprising a plurality of pixels, the program comprising sets of instructions for: identifying a first subset of the plurality of pixels that comprises skin-tone colored pixels; andapplying a variable gamma adjustment to only a second subset of the plurality of pixels that excludes the first subset of pixels, the variable gamma adjustment comprising an adjustment that raises at least one value of each pixel to a power that varies based on characteristics of the pixel. 9. The electronic device of claim 8, wherein the program further comprises a set of instructions for applying the variable gamma adjustment to the first subset of pixels unless a face is identified in the image. 10. The electronic device of claim 8, wherein the variable gamma adjustment is partly based on a user setting level, the program further comprising a set of instructions for applying the variable gamma adjustment to the first subset of pixels when the user setting level is above a preset threshold setting level. 11. The method electronic device of claim 8, wherein when a particular characteristic of the image is detected, a constant gamma adjustment is applied to the first subset of pixels. 12. A method of generating a formula for setting shadow lift levels of new images, the method comprising: receiving data for a plurality of images that indicates a user-specified maximum acceptable shadow lift setting for each of the plurality of images;for each of the images calculating a set of statistics based on a set of histograms generated for the image; andwith an electronic device, performing a mathematical regression to generate the formula for setting shadow lift levels of new images based on the calculated sets of statistics and the user-specified maximum acceptable shadow lift settings for the plurality of images. 13. The method of claim 12, wherein the set of histograms comprises a structure histogram, a luminance histogram, and a cumulative luminance histogram. 14. The method of claim 13, wherein the structure histogram is generated based on both luminance values and an arrangement of pixels in the image. 15. A non-transitory machine readable medium storing a program that when executed by at least one processing unit automatically adjusts shadow levels of an image, the program comprising sets of instructions for: generating a set of histograms that identify different characteristics of the image, wherein the set of histograms comprises a structure histogram comprising values based on relationships between each particular pixel of a plurality of pixels in the image and the neighboring pixels of the particular pixel;determining a shadow lift setting level based on a set of statistics calculated for the set of histograms; andapplying a shadow lift at the determined shadow lift setting level to the image. 16. The non-transitory machine readable medium of claim 15, wherein the relationships on which the structure histogram values are based comprise differences between luminance values of the particular pixels and the neighboring pixels of the particular pixels. 17. The non-transitory machine readable medium of claim 15, wherein the set of histograms further comprises a histogram that measures the luminance values of the pixels in the image. 18. The non-transitory machine readable medium of claim 17, wherein the set of histograms further comprises a cumulative luminance histogram. 19. The non-transitory machine readable medium of claim 15, wherein the set of histograms further comprises a cumulative luminance histogram that measures how many pixels have a given luminance or lower. 20. The non-transitory machine readable medium of claim 15, wherein the program further comprises sets of instructions for: reading an ISO value from metadata of the image to determine an ISO value of the image; andreducing the applied shadow lift setting level based on the ISO value. 21. A non-transitory machine readable medium storing a program which, when executed by at least one processing unit, enhances an image comprising a plurality of pixels, the program comprising sets of instructions for: identifying a first subset of the plurality of pixels that comprises skin-tone colored pixels; andapplying a variable gamma adjustment to only a second subset of the plurality of pixels that excludes the first subset of pixels, the variable gamma adjustment comprising an adjustment that raises at least one value of each pixel to a power that varies based on characteristics of the pixel. 22. The non-transitory machine readable medium of claim 21, wherein the program further comprises a set of instructions for applying the variable gamma adjustment to the first subset of pixels unless a face is identified in the image. 23. The non-transitory machine readable medium of claim 22, wherein the variable gamma adjustment is partly based on a user setting, wherein the program further comprises a set of instructions for applying the variable gamma adjustment to the first subset of pixels when the user setting level is above a preset threshold setting level. 24. The non-transitory machine readable medium of claim 21, wherein the program further comprises a set of instructions for applying a constant gamma adjustment to the first subset of pixels when a particular characteristic of the image is detected. 25. The non-transitory machine readable medium of claim 21, wherein the variable gamma adjustment for a particular pixel is based partly on a luminance value of a corresponding pixel in a blurred version of the image.