GEODESIC SUPERPIXEL SEGMENTATION

Patent №

US 8,923,646

Granted

2014-12-30

Filed 2012

Owner

CANON KABUSHIKI KAISHA

Lab

AI components

1

vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

13717373

An aspect of the present invention provides a method of segmenting an input image into a plurality of segments. The method comprises the steps of: deriving an image representative of boundary strength of each of a plurality of pixels in the input image; adding a random noise pattern to at least a portion of the derived image; determining a plurality of local minima in the derived image with the random noise pattern added, each of the plurality of local minima comprising a point with a lowest measure of boundary strength within a pre-defined region in the derived image; and associating each of the plurality of pixels in the input image with one of the determined local minima to segment the image based on a geodesic distance transform of the measure between the determined local minima and the pixels.

VisionG06T 7/155G06T 7/12G06T 2207/20041

AI classification

Vision1.00
Evolutionary computation0.04
Machine learning0.00
Speech0.00
AI hardware0.00
Knowledge representation0.00
Natural language0.00
Planning0.00

Ownership

CANON KABUSHIKI KAISHA

assignment · 301160876

Assignors

PHAM, TUAN QUANG

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

From the same owner

© 2026 NYSGPT2525 LLC