发明名称 |
Presenting image subsets based on occurrences of persons satisfying predetermined conditions |
摘要 |
Methods and systems for selecting one or more images from a plurality of captured images are disclosed. One method comprises the steps of: analysing the plurality of captured images to recognise faces in the captured images using a facial recognition process (step 304); updating a count variable relating to a unique face each time the face is recognised in the captured images; selecting one or more unique faces when the related count variable satisfies a predetermined condition (step 308); and selecting a reduced number of the images which together include at least one instance of each of the selected faces (step 310). |
申请公布号 |
US8792685(B2) |
申请公布日期 |
2014.07.29 |
申请号 |
US200912644375 |
申请日期 |
2009.12.22 |
申请人 |
Canon Kabushiki Kaisha |
发明人 |
Sangster Rob |
分类号 |
G06K9/00 |
主分类号 |
G06K9/00 |
代理机构 |
Fitzpatrick, Cella, Harper & Scinto |
代理人 |
Fitzpatrick, Cella, Harper & Scinto |
主权项 |
1. A method for selecting one or more images from a plurality of captured images, the method comprising steps of:
analyzing the plurality of captured images to recognize a plurality of faces in the plurality of captured images using a facial recognition process; updating a count variable associated with each recognized face each time that recognized face is recognized in the plurality of captured images; selecting a set of recognized faces from the plurality of recognized faces by, for each recognized face, comparing a value associated with that recognized face to a predetermined numerical threshold, the value being a ratio of an updated count variable associated with that recognized face relative to a total number of images in the plurality of captured images; and selecting a reduced number of the plurality of captured images, which together include at least one instance of each of the selected recognized faces. |
地址 |
Tokyo JP |