Photo processing method and apparatus

Patent metadata

Field	Value
Publication number	US-2017364750-A1
Application number	US-201715694162-A
Country	US
Kind code	A1
Filing date	Sep 1, 2017
Priority date	Nov 25, 2015
Publication date	Dec 21, 2017
Grant date	—

Abstract

The present disclosure discloses a photo processing method and an apparatus for grouping photos into photo albums based on facial recognition results. The method includes: performing face detection on multiple photos, to obtain a face image feature set, each face image feature in the face image feature set corresponding to one of the multiple photos; determining a face-level similarity for each pair of face image features in the face image feature set; determining a photo-level similarity between each pair of photos in the multiple photos in accordance with their associated face-level similarities; generating a photo set for each target photo in the multiple photos, wherein any photo-level similarity between the target photo and another photo in the photo set exceeds a predefined photo-level threshold; and generating a label for each photo set using photographing location and photographing time information associated with the photos in the photo set.

First claim

What is claimed is:

1 . A photo processing method performed at a computing device having one or more processors and memory storing one or more programs to be executed by the one or more processors, the method comprising:
performing face detection on multiple photos, to obtain a face image feature set, each face image feature in the face image feature set corresponding to one of the multiple photos; determining a face-level similarity for each pair of face image features in the face image feature set; determining a photo-level similarity between each pair of photos in the multiple photos in accordance with their associated face-level similarities; generating a photo set for each target photo in the multiple photos, wherein any photo-level similarity between the target photo and another photo in the photo set exceeds a predefined photo-level threshold; and generating a label for each photo set using photographing location and photographing time information associated with the photos in the photo set.

2 . The method according to claim 1 , further comprising:
determining a photo set-level similarity between each pair of photo sets associated with the multiple photos; and combining two or more photo sets into a photo album, wherein any photo set-level similarities of the two or more photo sets exceed a predefined photo set-level threshold.

3 . The method according to claim 2 , further comprising:
combining two photo sets in which photos that correspond to a pair of face image features whose face-level similarity is greater than a preset face-level similarity threshold; determining, according to the face-level similarity that corresponds to each pair of face image features, a photo set-level similarity between the combined photo set and another photo set; and when the photo set-level similarity between the combined photo set and the another photo set exceeds the predefined photo set-level similarity threshold, combining them into the photo album.

4 . The method according to claim 3 , further comprising:
combining the labels of the two or more photo sets into one label for the photo album.

5 . The method according to claim 2 , wherein the photo set-level similarity between two photo sets is defined in the following expression:

s
_

=

{

1

n
i



n
j



∑



s
ij



(

f
i

∈

A
i

,

f
j

∈

A
j

)

}

,

s representing the photo set-level similarity, A i represents one of the two photo sets, A j represents the other of the two photo sets, f i represents a face image feature that corresponds to a photo in the photo set A i , f j , represents a face image feature that corresponds to a photo in the photo set A j , s ij represents a similarity that corresponds to a pair of face image features formed by the face image feature f i and the face image feature f j , n i represents a quantity of photos in the photo set A i , and n j represents a quantity of photos in the photo set A j , i and j being two unequal natural numbers.

6 . The method according to claim 1 , wherein the photo-level similarity between a pair of photos is a summation of the face-level similarities between the face image features in the two photos.

7 . The method according to claim 1 , further comprising:
displaying the label for the photo set to a user; and prompting the user to update the label for the photo set.

8 . The method according to claim 1 , further comprising:
sorting photos in each output photo set according to an order of photographing time of the photos.

9 . The method according to claim 8 , further comprising:
dividing photos in each output photo set into different photo subsets according to the order of photographing time of the photos; and generating a sub-label for each photo subset according to the photographing time of the photos in the photo subset.

10 . A photo processing apparatus, comprising:
at least one processor; memory; and a plurality of program instructions stored in the memory that, when executed by the at least processor, cause the photo processing apparatus to perform a plurality of operations including:
performing face detection on multiple photos, to obtain a face image feature set, each face image feature in the face image feature set corresponding to one of the multiple photos;
determining a face-level similarity for each pair of face image features in the face image feature set;
determining a photo-level similarity between each pair of photos in the multiple photos in accordance with their associated face-level similarities;
generating a photo set for each target photo in the multiple photos, wherein any photo-level similarity between the target photo and another photo in the photo set exceeds a predefined photo-level threshold; and
generating a label for each photo set using photographing location and photographing time information associated with the photos in the photo set.

11 . The photo processing apparatus according to claim 10 , wherein the plurality of operations further comprise:
determining a photo set-level similarity between each pair of photo sets associated with the multiple photos; and combining two or more photo sets into a photo album, wherein any photo set-level similarities of the two or more photo sets exceed a predefined photo set-level threshold.

12 . The photo processing apparatus according to claim 11 , wherein the plurality of operations further comprise:
combining two photo sets in which photos that correspond to a pair of face image features whose face-level similarity is greater than a preset face-level similarity threshold; determining, according to the face-level similarity that corresponds to each pair of face image features, a photo set-level similar

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Tan Guofu

Classifications

• G06V10/763

  Non-hierarchical techniques, e.g. based on statistics of modelling distributions · CPC title

• G06V20/35

  Categorising the entire scene, e.g. birthday party or wedding scene · CPC title

• G06F16/51 Primary

  Indexing; Data structures therefor; Storage structures · CPC title

• H04N1/00196

  Creation of a photo-montage, e.g. photoalbum (H04N1/0019 takes precedence) · CPC title

• G06F16/5838

  using colour · CPC title