Electronic device and method for removing haze from image
A method for removing haze from an image is provided. The image is converted to S(x) and V(x), the S(X) is saturation component of the image, and the V(x) is value component of the image. The S(x) is filtered to obtain S′(x), and the V(x) is filtered to obtain V′(x). A depth d(x) is estimated by calculating a difference between the S′(x) and V′(x). Once a transmission map t(x) is calculated based on the d(x), haze is removed from the image based on the transmission map t(x).
1. A method for removing hazy from an image applied to an electronic device, the method comprising:
converting the image to S(x) and V(x), wherein the S(x) is a saturation component of the image, and the V(x) is a value component of the image;
filtering the S(x) to obtain S′(x), and filtering V(x) to obtain V′ (x);
estimating a depth d(x) by calculating a difference between the S′(x) and V′(x);
calculating a transmission map t(x) based on the d(x); and
removing haze from the image based on the transmission map t(x) and obtaining a haze-free image J(x).
2. The method according to claim 1 , further comprising:
performing an edge-preserving smoothing process on V(x) to obtain V′(x), and performing the edge-preserving smoothing process on S(x) to obtain S′(x).
3. The method according to claim 1 , wherein the transmission map t(x)=e −β*d(x) , wherein “β” is determined according to a weather information or a concentration of particulate matter of a current position where the image is captured.
4. The method according to claim 3 , wherein the haze is removed from the image based on the transmission map t(x) according to following formulas:
I ( x )= J ( x )* t ( x )+(1− t ( x ))* A;
J ( x )=[ I ( x )−(1− t ( x ))* A ]/ t ( x );
wherein “A” represents an atmospheric light value of the image, “I(x)” represents an intensity of the image, and “J(x)” represents the haze-free image.
5. The method according to claim 1 , wherein the image is a preview image of a camera of the electronic device.
6. An electronic device comprising:
a storage device;
at least one processor; and
the storage device storing one or more programs, which when executed by the at least one processor, cause the at least one processor to:
convert the image to S(x) and V(x), wherein the S(x) is a saturation component of the image, and the V(x) is a value component of the image;
filter the S(x) to obtain S′(x), and filter V(x) to obtain V′(x);
estimate a depth d(x) by calculating a difference between the S′(x) and V′(x);
calculate a transmission map t(x) based on the d(x); and
remove haze from the image based on the transmission map t(x) and obtain a haze-free image J(x).
7. The electronic device according to claim 6 , wherein the at least one processor is further caused to:
perform an edge-preserving smoothing process on V(x) to obtain V′(x), and perform the edge-preserving smoothing process on S(x) to obtain S′(x).
8. The electronic device method according to claim 6 , wherein the transmission map t(x)=e −β * d(x) , wherein “β” is determined according to a weather information or a concentration of particulate matter of a current position where the image is captured.
9. The recognizing method according to claim 8 , wherein the haze is removed from the image based on the transmission map t(x) according to following formulas:
I ( x )= J ( x )* t ( x )+(1− t ( x ))* A;
J ( x )=[ I ( x )−(1− t ( x ))* A ]/ t ( x );
wherein “A” represents an atmospheric light value of the image, “I(x)” represents an intensity of the image, and “J(x)” represents the haze-free image.
10. The recognizing method according to claim 6 , wherein the image is a preview image of a camera of the electronic device.
11. A non-transitory storage medium having instructions stored thereon, when the instructions are executed by a processor of an electronic device, the processor is configured to perform a method of removing haze from an image, wherein the method comprises:
converting the image to S(x) and V(x), wherein the S(x) is a saturation component of the image, and the V(x) is a value component of the image;
filtering the S(x) to obtain S′(x), and filtering V(x) to obtain V′(x);
estimating a depth d(x) by calculating a difference between the S′(x) and V′(x);
calculating a transmission map t(x) based on the d(x); and
removing haze from the image based on the transmission map t(x) and obtaining a haze-free image J(x).
12. The non-transitory storage medium according to claim 11 , wherein the method further comprises:
performing an edge-preserving smoothing process on V(x) to obtain V′(x), and performing the edge-preserving smoothing process on S(x) to obtain S′(x).
13. The non-transitory storage medium according to claim 11 , wherein the transmission map t(x)=e −β*d(x) , wherein “β” is determined according to a weather information or a concentration of particulate matter of a current position where the image is captured.
14. The non-transitory storage medium according to claim 13 , wherein the haze is removed from the image based on the transmission map t(x) according to following formulas:
I ( x )= J ( x )* t ( x )+(1− t ( x ))* A;
J ( x )=[ I ( x )−(1− t ( x ))* A ]/ t ( x );
wherein “A” represents an atmospheric light value of the image, “I(x)” represents an intensity of the image, and “J(x)” represents the haze-free image.
15. The non-transitory storage medium according to claim 11 , wherein the image is a preview image of a camera of the electronic device.