Image processing method, image processing apparatus, and recording medium

Patent metadata

Field	Value
Publication number	US-9911204-B2
Application number	US-201615238416-A
Country	US
Kind code	B2
Filing date	Aug 16, 2016
Priority date	Aug 21, 2015
Publication date	Mar 6, 2018
Grant date	Mar 6, 2018

Abstract

A processor performs pattern matching on a search target image using a reference image. The processor uses the reference image to calculate a model pyramid, which has model edges and different layers, and uses the search target image to calculate the search target pyramid, which has search target edges and layers having size reduction factors which are the same as those of the model pyramid. The processor performs pattern matching on the search target pyramid using the model pyramid. Calculation of the model pyramid includes (i) extracting and calculating sizes of edges from the reference image, (ii) obtaining maximum size reduction factors of the individual edges, and (iii) setting an edge (a) which has a size reduction factor equal to or larger than a target layer size reduction factor and (b) which has been subjected to size reduction as a model edge of the target layer.

First claim

What is claimed is:

1. An image processing method to cause a processor to perform pattern matching on a search target image using a reference image, the image processing method comprising:
causing the processor to calculate a model pyramid which has different layers having different size reduction factors and which includes model edges in individual layers of the model pyramid using the reference image;
causing the processor to calculate a search target pyramid which has layers having size reduction factors which are the same as those in the layers of the model pyramid and which includes search target edges in individual layers of the search target pyramid using the search target image; and
causing the processor to perform pattern matching on the search target pyramid using the model pyramid,
wherein the calculation of the model pyramid includes
causing the processor to extract a plurality of edges from, the reference image,
causing the processor to calculate sizes of extracted individual edges,
causing the processor to obtain maximum size reduction factors of the individual edges in accordance with the calculated sizes of the extracted individual edges, and
causing the processor to set, when a target layer which is a target one of the plurality of layers of the model pyramid is to be generated, an edge which has a maximum size reduction factor equal to or larger than a size reduction factor of the target layer and which has been subjected to size reduction by the size reduction factor of the target layer as a model edge of the target layer, an edge which has a maximum size reduction factor smaller than the size reduction factor of the target layer being excluded from the edge to be set as the model edge.

2. The image processing method according to claim 1 , wherein extracting the plurality of edges includes causing the processor to set an edge extraction region in the reference image and to extract the plurality of edges from the edge extraction region.

3. The image processing method according to claim 1 , wherein setting the model edge of the target layer includes (i) causing the processor to extract edges, from among the plurality of edges, having size reduction factors equal to or larger than the size reduction factor of the target layer, (ii) causing the processor to perform size reduction on the extracted edges by the size reduction factor of the target layer, and (iii) causing the processor to set the extracted edges as model edges in the target layer.

4. The image processing method according to claim 1 ,
wherein setting the model edge of the target layer includes
(i) causing the processor to perform size reduction on the reference image while the largest one of the maximum size reduction factors of the plurality of edges is set as an upper limit so as to obtain a size-reduced image having the size reduction factor of the target layer,
(ii) causing the processor to set, in the size-reduced image, a size reduction edge extraction region having a size reduction factor that is the same as that of the size-reduced image in a region other than a region including edges having maximum size reduction factors smaller than the size reduction factor of the size-reduced image, and
(iii) causing the processor to set edges extracted from the size reduction edge extraction region as the model edges in the target layer.

5. The image processing method according to claim 1 , wherein, in a case where the target layer corresponds to a layer of a size reduction factor of 1, setting the model edge includes causing the processor to set the plurality of edges as the model edges of the target layer.

6. The image processing method according to claim 1 , wherein calculating the search target pyramid includes causing the processor to obtain a search target edge by performing size reduction on an edge extracted from the search target image.

7. A non-transitory computer readable recording medium on which a program is recorded to cause a computer to perform the image processing method according to claim 1 .

8. An image processing apparatus comprising:
a processor which performs pattern matching on a search target image using a reference image, wherein the processor is configured to execute
a process of calculating a model pyramid which has different layers having different size reduction factors and which includes model edges in individual layers of the model pyramid using the reference image;
a process of calculating a search target pyramid which has layers having size reduction factors which are the same as those in the layers of the model pyramid and which includes search target edges in individual layers of the search target pyramid using the search target image; and
a process of performing pattern matching on the search target pyramid using the model pyramid,
wherein the process of calculating the model pyramid includes
a process of extracting a plurality of edges from the reference image,
a process of calculating sizes of extracted individual edges,
a process of obtaining maximum size reduction factors of the individual edges in accordance with the calculated sizes of the extracted individual edges, and
a process of setting, when a target layer which is a target one of the plurality of layers of the model pyramid is to be generated, an edge which has a maximum size reduction factor equal to or larger than a size reduction factor of the target layer and which has been subjected to size reduction by the size reduction factor of the target layer as a model edge of the target layer, an edge which has a maximum size reduction factor smaller than the size reduction factor of the target layer being excluded from the edge to be set as the model edge.

9. The image processing apparatus according to claim 8 , wherein the process of extracting the plurality of edges includes a process of setting an edge extraction region in the reference image and extracting the plurality of edges from the edge extraction region.

10. The image processing apparatus according to claim 8 , wherein the process of setting the model edge of the target layer includes (i) a process of extracting edges, from among the plurality of edges, having size reduction factors equal to or larger than the size reduction factor of the target layer, (ii) a process of performing size reduction on the extracted edges by the size reduction factor of the target layer, and (iii) a process of setting the extracted edges as model edges in the target layer.

11. The image processing apparatus according to claim 8 ,
wherein the process of setting the model edge of the target layer includes
(i) a process of performing size reduction on the reference image while the largest one of the maximum, size reduction factors of the plurality of edges is set as an upper limit so as to obtain a size-reduced image having the size reduction factor of the target layer,
(ii) a process of setting, in the size-reduced image, a size reduction edge extraction region having a size reduction factor that is the same as that of the size-reduced image in a region other than a region including edges having maximum size reduction factors smaller than the size reduction factor of the size-reduced image, and
(iii) a process of setting edges extracted from the size reduction edge extraction region as the model edges in the target layer.

12. The image processing apparatus according to claim 8 , wherein, in a case where the target layer corresponds to a layer of a size reduction factor of 1, the process of setting the model edge includes a process of setting the plurality of edges as the model edges of the target layer.

13. The image processi

Assignees

• Canon Kk

Inventors

• Odagiri Jun

Classifications

• G06T2207/20016

  Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform · CPC title

• G06T7/74 Primary

  involving reference images or patches · CPC title