Method of speeding up image detection

Patent metadata

Field	Value
Publication number	US-2018365511-A1
Application number	US-201715628111-A
Country	US
Kind code	A1
Filing date	Jun 20, 2017
Priority date	Jun 20, 2017
Publication date	Dec 20, 2018
Grant date	—

Abstract

A method of speeding up image detection, adapted to increase a speed of detecting a target image and enhance efficiency of image detection, comprises the steps of capturing an image; retrieving a plurality of characteristic points of the image; creating a region of interest (ROI) centered at the characteristic points each; creating a plurality of search point scan windows corresponding to the ROIs, respectively; calculating target hit scores of the characteristic points and the search point scan windows; comparing the target hit scores of the characteristic points and the search point scan windows to obtain an ROI most likely to have a target image; calculating centroid coordinates of the ROI by a centroid shift weight equation; and narrowing a scope of ROI search according to a location of the centroid coordinates and reducing a displacement between the search points.

First claim

What is claimed is:

1 . A method of speeding up image detection, adapted to increase a speed of detecting a target image, comprising the steps of:
(1) capturing an image; (2) retrieving a plurality of characteristic points of the image; (3) creating a region of interest (ROI) centered at the characteristic points each; (4) creating a plurality of search point scan windows corresponding to the ROIs, respectively; (5) calculating target hit scores of the characteristic points and the search point scan windows; (6) comparing the target hit scores of the characteristic points and the search point scan windows to obtain an ROI which has a target image; (7) calculating centroid coordinates of the ROI by a centroid shift weight equation; and (8) narrowing a scope of ROI search according to a location of the centroid coordinates and reducing a displacement between the search points.

2 . The method of speeding up image detection in accordance with claim 1 , wherein the step (2) of retrieving a plurality of characteristic points of the image is performed by a speeded up robust features (SURF) algorithm.

3 . The method of speeding up image detection in accordance with claim 1 , wherein the step (5) of calculating the target hit scores of the characteristic points and the search point scan windows is performed by a support vector machine (SVM) algorithm.

4 . The method of speeding up image detection in accordance with claim 1 , wherein the step (7) of calculating centroid coordinates of the ROI by the centroid shift weight equation is performed in accordance with the target hit scores of the characteristic points and the search point scan windows and center coordinates of the characteristic points and the search point scan windows, so as to calculate the centroid coordinates by the centroid shift weight equation.

Assignees

• Nat Chung Shan Inst Science & Tech

Inventors

• Hsieh Chun-Wei
• Chien Shih-Che
• Chang Feng-Chia
• Hsiao Chien-Hao

Classifications

• G06V10/771

  Feature selection, e.g. selecting representative features from a multi-dimensional feature space · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/2115

  by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination · CPC title

• G06V10/255 Primary

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06F18/2113

  by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation · CPC title