APPARATUS AND METHOD FOR CLASSIFYING PATTERN IN IMAGE

• US 20170300787A1
• Filed: 04/10/2017
• Published: 10/19/2017
• Est. Priority Date: 04/15/2016
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Chen, Tsewei
• Granted Patent: US 10,402,693 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/2148 characterised by the process organisation or structure, e.g. boosting cascade
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06F 18/253 of extracted features
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/7747 Organisation of the process, e.g. bagging or boosting
• CPC Class Codes: G06V 10/806 of extracted features
• CPC Class Codes: G06V 10/94 Hardware or software architectures specially adapted for image or video understanding

Abstract

An image processing apparatus includes a generation unit that generates feature data based on an image, classification units that classify a predetermined pattern by referring to the feature data, and a control unit that controls operations of the classification units. The classification units include a first classification unit and a second classification unit, processing results of which do not depend on each other, and a third classification unit. The first and the second classification units are operated in parallel. When either of the first and the second classification units determines that a classification condition is not satisfied, the control unit stops operations of all of the classification units. When both the first and the second classification units determine the classification condition is satisfied, the control unit operates the third classification unit by using classification results of the first and the second classification units.

Claims

1. An image processing apparatus comprising:

a generation unit configured to generate feature data based on an image;

a plurality of classification units each configured to classify a predetermined pattern by referring to the feature data; and

a control unit configured to control operations of the plurality of classification units,

wherein the plurality of classification units includes a first classification unit and a second classification unit, processing results of which do not depend on each other, and a third classification unit,

wherein the control unit operates the first and the second classification units in parallel,

wherein, in a case where at least either one of the first and the second classification units determines that a classification condition is not satisfied, the control unit stops operations of all of the plurality of classification units, and

wherein, in a case where both the first and the second classification units determine that the classification condition is satisfied, the control unit operates the third classification unit by using classification results of the first and the second classification units.

2. The image processing apparatus according to claim 1,

wherein the third classification unit refers to feature data common to the first or the second classification unit from the same memory, and

wherein the control unit sequentially operates a plurality of the classification units that refer to the common feature data.

3. The image processing apparatus according to claim 1, wherein either one of the first and the second classification units has a shorter processing time than at least one other classification unit in the plurality of classification units.

4. The image processing apparatus according to claim 1, wherein, based on processing times of the plurality of classification units, the control unit determines an order of operating the plurality of classification units.

5. The image processing apparatus according to claim 1, wherein the control unit determines an order of operating the classification units based on a probability that each of the plurality of classification units has satisfied the classification condition in advance.

6. The image processing apparatus according to claim 1, wherein the feature data generated by the generation unit includes a plurality of feature data stream portions having different characteristics.

7. The image processing apparatus according to claim 6, wherein the generation unit applies different types of filters to an image to generate the plurality of feature data having different characteristics.

8. The image processing apparatus according to claim 1, wherein, in a case where the control unit determines that at least either one of the first and the second classification units does not satisfy the classification condition for a certain image, the control unit stops operations of all of the plurality of classification units and starts operations of the first and the second classification units for a next input image.

9. The image processing apparatus according to claim 1, wherein each of the determination units calculates a score based on the feature data, and compares the score with a threshold value to determine whether the classification condition is satisfied.

10. The image processing apparatus according to claim 1,

wherein the feature data is a feature image, and

wherein each of the classification units calculates a score based on data of a plurality of points of the feature image.

11. The image processing apparatus according to claim 10, wherein each of the classification units calculates the score based on a total of the data of the plurality of points of the feature image.

12. An image processing method comprising:

generating feature data based on an image; and

classifying a predetermined pattern via a plurality of classification units by referring to the feature data,

wherein the plurality of classification units includes a first classification unit and a second classification unit, processing results of which do not depend on each other, and a third classification unit,

wherein, in classification by the plurality of classification units, the first and the second classification units are operated in parallel,

wherein, in a case where at least either one of the first and the second classification units determines that a classification condition is not satisfied, operations of all of the plurality of classification units are stopped, and

wherein, in a case where both the first and the second classification units determine that the classification condition is satisfied, the third classification unit is operated by using classification results of the first and the second classification units.

13. A non-transitory computer-readable storage medium storing a program that when executed by a computer causes the computer to function as:

a generation unit configured to generate feature data based on an image;

a plurality of classification units each configured to classify a predetermined pattern by referring to the feature data; and

a control unit configured to control operations of the plurality of classification units,

wherein the plurality of classification units includes a first classification unit and a second classification unit, processing results of which do not depend on each other, and a third classification unit,

wherein the control unit operates the first and the second classification units in parallel,

wherein, in a case where at least either one of the first and the second classification units determines that a classification condition is not satisfied, the control unit stops operations of all of the plurality of classification units, and

wherein, in a case where both the first and the second classification units determine that the classification condition is satisfied, the control unit operates the third classification unit by using classification results of the first and the second classification units.