Object detection with false positive filtering
View Patent ↗Embodiments of this invention relate to detecting and blurring images. In an embodiment, a system detects objects in a photographic image. The system includes an object detector module configured to detect regions of the photographic image that include objects of a particular type at least based on the content of the photographic image. The system further includes a false positive detector module configured to determine whether each region detected by the object detector module includes an object of the particular type at least based on information about the context in which the photographic image was taken.
1. A method for detecting regions in an image, the method comprising:
detecting, by one or more computing devices, a set of regions of the image that include features that appear to correspond to objects of a particular type; and
identifying, by the one or more computing devices, a given region of the set of regions as not including features that correspond to objects of the particular type based on at least information describing a ratio including a size of the given region and a dimension of a feature included within the given region, wherein the information describing the ratio includes a dimension corresponding to a height of a camera that captured the image.
2. The method of claim 1 , wherein the dimension includes a bottom edge of an object corresponding to the feature included in the given region.
3. The method of claim 1 , wherein the dimension includes a height of an object corresponding to the feature included in the given region.
4. The method of claim 1 , wherein the dimension includes a height of a plane of a bottom edge of an object corresponding to the feature included in the given region.
5. The method of claim 4 , wherein the objects of the particular type are faces of humans and the height of the plane of the bottom edge of the object is estimated based on an average human height value.
6. The method of claim 4 , wherein the objects of the particular type are license plates of vehicles and the height of the plane of the bottom edge of the object is estimated based on an average height of a license plate.
7. A system for detecting regions in an image, the system comprising:
one or more computing devices configured to:
detect a set of regions of the image that include features that appear to correspond to objects of a particular type; and
identify a given region of the set of regions as not including features that correspond to objects of the particular type based on at least information describing a ratio including a size of the given region and a dimension of a feature included within the given region, wherein the information describing the ratio includes a dimension corresponding to a height of a camera that captured the image.
8. The system of claim 7 , wherein the dimension includes a bottom edge of an object corresponding to the feature included in the given region.
9. The system of claim 7 , wherein the dimension includes a height of an object corresponding to the feature included in the given region.
10. The system of claim 7 , wherein the dimension includes a height of a plane of a bottom edge of an object corresponding to the feature included in the given region.
11. The system of claim 10 , wherein the objects of the particular type are faces of humans and the height of the plane of the bottom edge of the object is estimated based on an average human height value.
12. The system of claim 10 , wherein the objects of the particular type are license plates of vehicles and the height of the plane of the bottom edge of the object is estimated based on an average height of a license plate.
13. A non-transitory, tangible computer-readable storage medium on which computer readable instructions of a program are stored, the instructions, when executed by a processor, cause the processor to perform a method for detecting regions in an image, the system comprising:
one or more computing devices configured to:
detecting a set of regions of the image that include features that appear to correspond to objects of a particular type; and
identifying a given region of the set of regions as not including features that correspond to objects of the particular type based on at least information describing a ratio including a size of the given region and a dimension of a feature included within the given region, wherein the objects of the particular type are license plates of vehicles and the height of the plane of the bottom edge of the object is estimated based on an average height of a license plate.
14. The medium of claim 13 , wherein the dimension includes a height of an object corresponding to the feature included in the given region.
15. The medium of claim 13 , wherein the dimension includes a height of a camera that captured the image.
16. The medium of claim 13 , wherein the dimension includes a height of a plane of a bottom edge of an object corresponding to the feature included in the given region.
17. The medium of claim 16 , wherein the objects of the particular type are faces of humans and the height of the plane of the bottom edge of the object is estimated based on an average human height value.