Patent №
US 7,081,972
Granted
2006-07-25
Filed 2001
Owner
CANON KABUSHIKI KAISHA
Lab
—
AI components
2
vision · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
09953953
In order to acquire a good binary image at all levels of gray scale, an image processing apparatus for quantizing input multivalued image data by a multivalued error diffusion method, selecting a predetermined dot pattern based on the quantized image data and outputting a binary image is configured to have an error calculation division for calculating corrected value from a pixel value and a processed pixel diffusion error of an input image, and calculating a quantization error from an output density level corresponding to the corrected value, an image generation division for first acquiring a diffusion coefficient corresponding to a pixel value of the input image, and distributing the quantization error to surrounding pixels according to a weight assignment by the diffusion coefficient to generate the binary image, a diffusion coefficient generation division for generating a plurality of candidate diffusion coefficients, a computing division for acquiring an evaluation value for the binary image generated by the image generation division, and a selection division for selecting the diffusion coefficient corresponding to the pixel value of the input image from the plurality of candidate diffusion coefficients based on the above evaluation value.
AI classification
Ownership
CANON KABUSHIKI KAISHA
assignment · 121800384
Assignors
FUKAO, SUZUKO
On an employer assignment, the assignors are typically the inventors.