Face or other object detection including template matching
First Claim
Patent Images
1. A digital image acquisition device, comprising:
- an optoelectronic system for acquiring a digital image;
a processor;
a plurality of object detection templates, wherein each object detection template of the plurality of object detection templates is;
tuned for high detection, low rejection ratios, andtrained to detect a corresponding object that has certain characteristics that are reflected in the template;
a plurality of high-quality object detection templates tuned for low detection, high rejection ratios; and
a template matching module configured to;
apply the plurality of object detection templates in parallel to data of the digital image to determine one or more particular characteristics of either the digital image or an object in the digital image;
wherein the one or more particular characteristics of the digital image comprise one or more of;
an object type,a configuration,an orientation,a pose,a blur,an exposure, oran illumination condition;
based on the one or more particular characteristics, select one or more high-quality object detection templates from the plurality of high-quality object detection templates;
wherein the one or more high-quality object detection templates are different from the plurality of object detection templates;
a filtering module configured to;
use the one or more high-quality object detection templates to determine whether any of the one or more particular characteristics has been falsely identified; and
filter out, from the one or more particular characteristics, any characteristics that were determined to have been falsely identified.
2 Assignments
0 Petitions
Accused Products
Abstract
A template matching module is configured to program a processor to apply multiple differently-tuned object detection classifier sets in parallel to a digital image to determine one or more of an object type, configuration, orientation, pose or illumination condition, and to dynamically switch between object detection templates to match a determined object type, configuration, orientation, pose, blur, exposure and/or directional illumination condition.
-
Citations
19 Claims
-
1. A digital image acquisition device, comprising:
-
an optoelectronic system for acquiring a digital image; a processor; a plurality of object detection templates, wherein each object detection template of the plurality of object detection templates is; tuned for high detection, low rejection ratios, and trained to detect a corresponding object that has certain characteristics that are reflected in the template; a plurality of high-quality object detection templates tuned for low detection, high rejection ratios; and a template matching module configured to; apply the plurality of object detection templates in parallel to data of the digital image to determine one or more particular characteristics of either the digital image or an object in the digital image; wherein the one or more particular characteristics of the digital image comprise one or more of; an object type, a configuration, an orientation, a pose, a blur, an exposure, or an illumination condition; based on the one or more particular characteristics, select one or more high-quality object detection templates from the plurality of high-quality object detection templates; wherein the one or more high-quality object detection templates are different from the plurality of object detection templates; a filtering module configured to; use the one or more high-quality object detection templates to determine whether any of the one or more particular characteristics has been falsely identified; and filter out, from the one or more particular characteristics, any characteristics that were determined to have been falsely identified. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An object detection system, comprising:
-
an optoelectronic system for acquiring a digital image; a processor; a plurality of object detection templates, wherein each object detection template of the plurality of object detection templates is; tuned for high detection, low rejection ratios, and trained to detect a corresponding object that has certain characteristics that are reflected in the template; a plurality of high-quality object detection templates tuned for low detection, high rejection ratios; a template matching module configured to; apply the plurality of object detection templates in parallel to data of the digital image to determine one or more particular characteristics of either the digital image or an object in the digital image; wherein the one or more particular characteristics of the digital image comprise one or more of; an object type, a configuration, an orientation, a pose, a blur, an exposure, or an illumination condition; based on the one or more particular characteristics, select one or more high-quality object detection templates from the plurality of high-quality object detection templates; wherein the one or more high-quality object detection templates are different from the plurality of object detection templates; and a filtering module configured to; use the one or more high-quality object detection templates to determine whether any of the one or more particular characteristics has been falsely identified; and filter out, from the one or more particular characteristics, any characteristics that were determined to have been falsely identified. - View Dependent Claims (10, 11)
-
-
12. A method of object detection in an acquired digital image, comprising:
-
acquiring a digital image; applying a plurality of object detection templates in parallel to data of the digital image to identify one or more particular characteristics of either the digital image or an object in the digital image; wherein each object detection template of the plurality of object detection templates is; tuned for high detection, low rejection ratios, and trained to detect a corresponding object that has certain characteristics that are reflected in the template; wherein the one or more particular characteristics of the digital image comprise one or more of an object type, a configuration, an orientation, a pose, a blur, an exposure, or an illumination condition; based on the one or more particular characteristics, select one or more high-quality object detection templates from a plurality of high-quality object detection templates; wherein the plurality of high-quality object detection templates are tuned for low detection, high rejection ratios; wherein the one or more high-quality object detection templates are different from the plurality of object detection templates; use the one or more high-quality object detection templates to determine whether any of the one or more particular characteristics has been falsely identified; and filtering out, from the one or more particular characteristics, any characteristics that were determined to have been falsely identified; and wherein the method is performed by one or more computing devices. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19)
-
Specification