Image processing device and image processing method to generate image for object recognition
AssigneeSony Semiconductor Solutions Corporation
InventorYoshiaki Tatae
Life of this patent
Estimating the term…
Abstract
An image that enables proper object recognition is generated. An image processing device includes an image processing unit that processes an image. The image processing unit included in this image processing device corrects the level of a pixel constituting the image. That is, the image processing unit corrects the level of a target pixel constituting the image on the basis of a low-frequency component in a peripheral image of a pixel constituting the target image. Here, the peripheral image is made up of a plurality of pixels that includes the target pixel and is located around the target pixel.
Claims12
An image processing device, comprising:
- circuitry configured to:
- not correct a level of a target pixel of an image in a case where the level of the target pixel is smaller than a first threshold value,
- wherein the image includes a first peripheral image around the target pixel with the target pixel as a center;
- and
- correct the level of the target pixel of the image in a case where the level of the target pixel is larger than a second threshold value, wherein
- the second threshold value is larger than the first threshold value, and
- the correction is based on a low-frequency component in the first peripheral image around the target pixel.
An image processing device, comprising:
- circuitry configured to:
- generate a composite image by composition of a first image and a second image, wherein
- the second image is a darker image than the first image,
- the first image and the second image are generated under different conditions,
- the composite image includes a target pixel,
- the first image includes a first pixel and a first peripheral image around the first pixel, and
- the first pixel of the first image corresponds to the target pixel of the composite image;
- and
- correct a level of the target pixel of the composite image, based on a low-frequency component in the first peripheral image around the first pixel corresponding to the target pixel.
An image processing method, comprising:
- generating a composite image by compositing a first image and a second image, wherein
- the second image is a darker image than the first image,
- the first image and the second image are generated under different conditions,
- the composite image includes a target pixel,
- the first image includes a first pixel and a peripheral image around the first pixel, and
- the first pixel of the first image corresponds to the target pixel of the composite image;
- and
- correcting a level of the target pixel of the composite image, based on a low-frequency component in the peripheral image around the first pixel.
Dependencies are inferred from the claim text.