Invention Grant
- Patent Title: Adaptive selection of scale invariant image feature keypoints
-
Application No.: US14955476Application Date: 2015-12-01
-
Publication No.: US09659234B1Publication Date: 2017-05-23
- Inventor: Talat Anand Mohan Kalyanasundaram , Koba Natroshvili
- Applicant: INTEL CORPORATION
- Applicant Address: US CA Santa Clara
- Assignee: Intel Corporation
- Current Assignee: Intel Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Finch & Maloney PLLC
- Main IPC: G06K9/46
- IPC: G06K9/46 ; G06K9/62 ; G06T7/00 ; G06T5/20 ; G06T5/50

Abstract:
Techniques are provided for adaptive selection of feature keypoints of an image. An example system may include a contrast statistics calculation circuit configured to generate contrast measurements of regions of the image associated with each of the feature keypoints, and to calculate a mean and variance of the contrast measurements. The system may also include an edge statistics calculation circuit configured to generate ratios of principal curvatures of regions of the image associated with each of the feature keypoints, and to calculate a mean and variance of the ratios of principal curvatures. The system may further include a threshold calculation circuit configured to calculate thresholds based on the mean and variance of the contrast measurements and on the mean and variance of the ratios of principal curvatures; and a keypoint filter circuit configured to filter the set of feature keypoints based on the those thresholds.
Public/Granted literature
- US20170154243A1 ADAPTIVE SELECTION OF SCALE INVARIANT IMAGE FEATURE KEYPOINTS Public/Granted day:2017-06-01
Information query