Image data processing device and system

Patent metadata

Field	Value
Publication number	US-12437578-B2
Application number	US-202218062585-A
Country	US
Kind code	B2
Filing date	Dec 7, 2022
Priority date	Jul 1, 2020
Publication date	Oct 7, 2025
Grant date	Oct 7, 2025

Abstract

An image data processing device and a system capable of efficiently detecting a face from an image including a plurality of faces are provided. A processor executes at least following processes including detecting a face of a person from an image represented by image data by using a first discrimination model and discriminating an attribute of the detected face, clustering an area where the face is detected in the image represented by the image data according to a type of the attribute of the face, selecting a second discrimination model to be applied to the area based on information on the type of the attribute of the face in the clustered area, and detecting a face of a person from an image of each area by using the second discrimination model applied to the area and discriminating an attribute of the detected face.

First claim

What is claimed is:

1. An image data processing device that processes image data, the device comprising:
a memory; and
a processor,
wherein the processor executes
a first discrimination process of detecting a face of a person from an image represented by the image data by using a first discrimination model and discriminating an attribute of the detected face,
a clustering process of clustering an area where the face is detected in the image represented by the image data according to a type of the attribute of the face,
a selection process of selecting a second discrimination model to be applied to the area based on information on the type of the attribute of the face in the clustered area, and
a second discrimination process of detecting a face of a person from an image of the area by using the second discrimination model applied to the area and discriminating an attribute of the detected face.

2. The image data processing device according to claim 1 ,
wherein the second discrimination model is prepared for each type of attributes of a plurality of faces, and
in the clustering process, the clustering is performed according to the type of the attribute of the face for which the second discrimination model is prepared.

3. The image data processing device according to claim 2 ,
wherein the second discrimination model is prepared according to a type of the attribute of the face discriminated by the first discrimination model.

4. The image data processing device according to claim 2 ,
wherein the second discrimination model detects the face of a corresponding type of the attribute with a higher accuracy than the first discrimination model.

5. The image data processing device according to claim 1 ,
wherein the second discrimination model classifies the types in more detail within a range of a corresponding type of the attribute to discriminate the attribute of the face.

6. The image data processing device according to claim 1 ,
wherein the second discrimination model classifies whether or not the face has a corresponding type of the attribute to discriminate the attribute of the face.

7. The image data processing device according to claim 1 ,
wherein the processor executes processes once in order of the first discrimination process, the clustering process, the selection process, and the second discrimination process.

8. The image data processing device according to claim 1 ,
wherein the processor executes processes once in order of the first discrimination process, the clustering process, the selection process, and the second discrimination process, and then repeatedly executes the clustering process, the selection process, and the second discrimination process based on a result of the second discrimination process.

9. The image data processing device according to claim 1 ,
wherein the first discrimination model and the second discrimination model discriminates at least an expression as the attribute of the face.

10. The image data processing device according to claim 9 ,
wherein the first discrimination model and/or the second discrimination model further discriminates an orientation of the face as the attribute of the face.

11. The image data processing device according to claim 1 ,
wherein the processor
further executes an extraction process of extracting an area where a person exists from the image represented by the image data as a processing target area, and
executes the clustering process, the selection process, and the second discrimination process to the extracted processing target area.

12. The image data processing device according to claim 11 ,
wherein, in the extraction process, a passage is detected from the image, and an area divided by the passage is extracted as the processing target area.

13. The image data processing device according to claim 1 ,
wherein the processor further executes a map data generation process of generating map data in which the face detected from the image represented by the image data is recorded by associating a position of the face in the image with the attribute.

14. The image data processing device according to claim 13 ,
wherein the processor further executes a heat map generation process of generating a heat map based on the map data.

15. The image data processing device according to claim 14 ,
wherein the processor further executes a display control process of displaying the generated heat map on a display.

16. The image data processing device according to claim 14 ,
wherein the processor further executes an output control process of outputting the generated heat map to an outside.

17. The image data processing device according to claim 1 ,
wherein the first discrimination model and the second discrimination model are stored in the memory.

18. An image data processing system comprising:
an imaging device; and
the image data processing device according to claim 1 , which inputs and processes image data captured by the imaging device.

Assignees

• Fujifilm Corp

Inventors

• Hayashi Daisuke
• Ego Shunta
• Terada Masahiro
• Makino Kenji

Classifications

• G06T2207/30201

  Face · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06V10/762

  using clustering, e.g. of similar faces in social networks · CPC title

• G06V40/174

  Facial expression recognition · CPC title

• G06T7/70 Primary

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title