Image processing device and program

Abstract

To obtain a corrected image with a wider dynamic range for both a bright portion and a dark portion in one image.SOLUTION: An image processing apparatus includes a processor. The processor performs illumination component estimation processing in which an illumination component L of an original image 10 is estimated based on a Retinex theory to obtain an illumination image 12, and synthesis processing in which pixel values Il' and Id' of each of a bright portion correction and a dark portion correction obtained based on the original image 10 and the illumination image 12 are weighted and synthesized with a pixel value L of the illumination image 12 to generate a corrected image 14.SELECTED DRAWING: Figure 2

Claims

1. Including the processor, The aforementioned processor, Based on Retinex theory, the illumination component estimation process estimates the illumination component of the original image and obtains an illuminated image. A synthesis process is performed to generate a corrected image by weighting the pixel values ​​of the highlight correction and shadow correction obtained from the original image and the illumination image with the pixel values ​​of the illumination image and combining them. Image processing device.

2. An image processing apparatus according to claim 1, The aforementioned original image is a brightness image in which pixel values ​​represent brightness. Image processing device.

3. An image processing apparatus according to claim 2, The aforementioned processor, The pixel values ​​for the dark area correction are obtained by dividing the pixel values ​​of the original image by the pixel values ​​of the illumination image. The pixel values ​​obtained by dividing the pixel values ​​of the inverted brightness image, which is the original image with inverted brightness, by the pixel values ​​of the inverted illumination image, which is the illumination image with inverted brightness, and then inverting the brightness of the resulting pixel values ​​is obtained to acquire the pixel values ​​for the highlight correction. Image processing device.

4. An image processing apparatus according to any one of claims 1 to 3, The aforementioned processor, The system controls the display unit to superimpose the bright areas, where the pixel values ​​in the illumination image are higher than a threshold, and the dark areas, where the pixel values ​​are below the threshold, onto the original image or the original color image to which color components have been added, and display them on the display unit. Image processing device.

5. An image processing apparatus according to claim 4, The aforementioned processor, The display unit receives an instruction from the user to change the bright area and the dark area displayed on the display unit. Based on the user's instruction to make the change, update the pixel values ​​of the illumination image. Image processing device.

6. An image processing apparatus according to any one of claims 1 to 3, The aforementioned processor, A correction coefficient for correcting the pixel values ​​of the aforementioned illumination image is received from the user. Based on the correction coefficient, the pixel values ​​of the illumination image are updated. Image processing device.

7. An image processing apparatus according to any one of claims 1 to 3, The aforementioned processor, In the illumination component estimation process, a blurred image obtained by smoothing the original image is acquired as the illumination image. Image processing device.

8. An image processing apparatus according to claim 7, The aforementioned processor, The kernel size, kernel sigma value, or both are accepted from the user. In the illumination component estimation process, the illumination image is acquired using a kernel having the kernel size, the sigma value of the kernel, or both, as received from the user. Image processing device.

9. An image processing apparatus according to claim 7, The aforementioned processor, With respect to the object appearing in the original image, information about the distance between the camera and the object at the time of shooting by the camera is obtained. In the illumination component estimation process, when the distance between the camera and the object is long, a kernel with a smaller kernel size is used to acquire the illumination image compared to when the distance is short. Image processing device.

10. An image processing apparatus according to claim 7, The aforementioned processor, With respect to the object appearing in the original image, information on the size of the object relative to the entire original image is obtained. In the illumination component estimation process, when the object is small, a kernel with a smaller kernel size is used to acquire the illumination image compared to when the object is large. Image processing device.

11. An image processing apparatus according to claim 7, The aforementioned processor, The information about the field of view of the original image at the time of shooting by the camera is obtained, In the illumination component estimation process, when the field of view is large, a kernel with a smaller kernel size is used to acquire the illumination image compared to when the field of view is small. Image processing device.

12. Based on Retinex theory, the illumination component estimation process estimates the illumination component of the original image and obtains an illuminated image. A synthesis process is performed to generate a corrected image by weighting the pixel values ​​of the highlight correction and shadow correction obtained from the original image and the illumination image with the pixel values ​​of the illumination image and combining them, A program that causes a computer to execute something.

Images