METHOD AND SYSTEM FOR IMAGE CLASSIFICATION AND HALFTONE FREQUENCY DETECTION

Patent №

US 7,424,151

Granted

2008-09-09

Filed 2004

Owner

XEROX CORPORATION

Lab

AI components

1

vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

10861310

A system and method for classifying an image block of a printed image into contone, halftone, or error diffusion classes, includes scanning the printed image; selecting an n by n block of pixels from the scanned image in a luminance channel; calculating an array of DCT coefficients of the pixel block, wherein the calculated DCT coefficients are representative of spatial frequency and spatial orientation of the pixel block; comparing the array of DCT coefficients with an array of predetermined values, wherein the array of predetermined values are indicative of contone, halftone and error diffusion classes; and determining the image classification of the pixel block based on the comparison of the DCT coefficients with the array of predetermined values. If the image is determined to be halftone, then the method further evaluates the DCT coefficients to determine the frequency of the halftone screen.

VisionG06V 30/413H04N 1/40062

AI classification

Vision1.00
Machine learning0.37
Speech0.02
Natural language0.01
AI hardware0.00
Evolutionary computation0.00
Planning0.00
Knowledge representation0.00

Ownership

XEROX CORPORATION

assignment · 154880204

Assignors

LIN, YING-WEI, WANG, SHEN-GE, XU, BEILEI

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC