INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD

• US 20170017859A1
• Filed: 03/24/2015
• Published: 01/19/2017
• Est. Priority Date: 03/27/2014
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: UCHIYAMA, Hiroyuki
• Granted Patent: US 10,255,517 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/2148 characterised by the process organisation or structure, e.g. boosting cascade
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 10/7747 Organisation of the process, e.g. bagging or boosting
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 10/811 the classifiers operating on different input data, e.g. multi-modal recognition
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A feature amount, and context information representing a context regarding an image are obtained from the image. The first likelihood indicating the likelihood at which the image is an image of a specific object is obtained from the feature amount. The second likelihood indicating the likelihood at which the image is an image of the specific object is obtained from the context information. Whether the image is an image of the specific object is identified using the first likelihood and the second likelihood.

Claims

1. An information processing apparatus comprising:

a unit configured to obtain a feature amount from an input image;

a unit configured to obtain context information representing a context regarding the image;

a first identification unit configured to obtain, from the feature amount, a first likelihood indicating a likelihood at which the image is an image of a specific object;

a second identification unit configured to obtain, from the context information, a second likelihood indicating a likelihood at which the image is an image of the specific object; and

a unit configured to identify, by using the first likelihood and the second likelihood, whether the image is an image of the specific object,

wherein the second identification unit includes a discriminator learnt using the first likelihood and the context information.

2. The apparatus according to claim 1, wherein the discriminator of the second identification unit includes a discriminator selected from candidates of the discriminator generated using the first likelihood and the context information.

3. The apparatus according to claim 2, wherein the discriminator of the second identification unit includes a discriminator selected from candidates of a discriminator generated further using a weight set based on the first likelihood for a sample obtained by joining the feature amount and the context information.

4. The apparatus according to claim 1, wherein the context information includes a position and size of the image in an original image from which the image has been extracted.

5. An information processing apparatus comprising:

a unit configured to obtain a feature amount from an input image;

a unit configured to obtain context information representing a context regarding the image;

a first identification unit configured to obtain, from the feature amount, a first likelihood indicating a likelihood at which the image is an image of a specific object; and

a learning unit configured to learn a second identification unit being different from the first identification unit by using the first likelihood and the context information.

6. The apparatus according to claim 5, wherein the learning unit includes:

a unit configured to generate candidates of a discriminator by using the first likelihood and the context information; and

a unit configured to select at least one candidate from the candidates of the discriminator based on an evaluation score obtained for each of the candidates of the discriminator, and constitute the second identification unit by the selected candidate.

7. An information processing method to be performed by an information processing apparatus, comprising:

causing a unit configured to obtain a feature amount of the information processing apparatus, to obtain a feature amount from an input image;

causing a unit configured to obtain context information of the information processing apparatus, to obtain context information representing a context regarding the image;

causing a first identification unit of the information processing apparatus to obtain, from the feature amount, a first likelihood indicating a likelihood at which the image is an image of a specific object;

causing a second identification unit of the information processing apparatus to obtain, from the context information, a second likelihood indicating a likelihood at which the image is an image of the specific object; and

causing an identification unit of the information processing apparatus to identify, by using the first likelihood and the second likelihood, whether the image is an image of the specific object,

wherein the second identification unit includes a discriminator learnt using the first likelihood and the context information.

8. An information processing method to be performed by an information processing apparatus, comprising:

causing a unit configured to obtain a feature amount of the information processing apparatus, to obtain a feature amount from an input image;

causing a unit configured to obtain context information of the information processing apparatus, to obtain context information representing a context regarding the image;

causing a first identification unit of the information processing apparatus to obtain, from the feature amount, a first likelihood indicating a likelihood at which the image is an image of a specific object; and

causing a learning unit of the information processing apparatus to learn a second identification unit being different from the first identification unit by using the first likelihood and the context information.

9. A non-transitory computer-readable storage medium storing a computer program for causing a computer to function as:

a unit configured to obtain a feature amount from an input image;

a unit configured to obtain context information representing a context regarding the image;

a first identification unit configured to obtain, from the feature amount, a first likelihood indicating a likelihood at which the image is an image of a specific object;

a second identification unit configured to obtain, from the context information, a second likelihood indicating a likelihood at which the image is an image of the specific object; and

a unit configured to identify, by using the first likelihood and the second likelihood, whether the image is an image of the specific object,

wherein the second identification unit includes a discriminator learnt using the first likelihood and the context information.