Media handling system
First Claim
Patent Images
1. A media handling system in which candidate video sequences are displayed on a display screen in schematic form for selection by a user, the system comprising:
- user control means for defining a set of one or more of the video sequences;
detecting means for detecting human faces in the candidate video sequences, for detecting a probability of a human face being present in each field or frame of the video sequences, and for weighting at least some of the detected probability levels depending on the size of the detected face, each one of the weighted probability levels corresponds with a respective face size stored in a look-up table; and
a display screen configured to display at least one representation of the candidate video sequences for selection by the user, each representation of the candidate video sequence including one or more images representing human faces derived from the respective video sequences and having the highest weighted probability levels amongst the respective video sequences, whereinthe detector means weights the probability levels based on the correspondence between each one of the weighted probability levels and the respective face sizes as defined by the look-up table, such that detected faces closer in size to a preferred representation size are presented to the user for selection thereof as the displayed representation of the candidate video sequence.
1 Assignment
0 Petitions
Accused Products
Abstract
A media handling system in which candidate video sequences are displayed on a display screen in schematic form for selection by a user comprises means for detecting human faces in the candidate video sequences; a display screen for displaying representations of the candidate video sequences for selection by a user, each representation including one or more images representing human faces derived from the respective video sequences; and a user control for defining a set of one or more of the video sequences.
50 Citations
14 Claims
-
1. A media handling system in which candidate video sequences are displayed on a display screen in schematic form for selection by a user, the system comprising:
-
user control means for defining a set of one or more of the video sequences; detecting means for detecting human faces in the candidate video sequences, for detecting a probability of a human face being present in each field or frame of the video sequences, and for weighting at least some of the detected probability levels depending on the size of the detected face, each one of the weighted probability levels corresponds with a respective face size stored in a look-up table; and a display screen configured to display at least one representation of the candidate video sequences for selection by the user, each representation of the candidate video sequence including one or more images representing human faces derived from the respective video sequences and having the highest weighted probability levels amongst the respective video sequences, wherein the detector means weights the probability levels based on the correspondence between each one of the weighted probability levels and the respective face sizes as defined by the look-up table, such that detected faces closer in size to a preferred representation size are presented to the user for selection thereof as the displayed representation of the candidate video sequence. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method of media handling in which candidate video sequences are displayed on a display screen in schematic form for selection by a user, the method comprising:
-
detecting human faces in the candidate video sequences; detecting a probability of a human face being present in each field or frame of the video sequences; weighting at least some of the detected probability levels depending on the size of the detected face, each one of the weighted probability levels corresponds with a respective face size stored in a look-up table; displaying on a display screen at least one representation of the candidate video sequences for selection by the user, each representation of the candidate video sequences including one or more images representing human faces derived from the respective video sequences and having the highest weighted probability levels amongst the respective video sequences; defining a set of one or more of the video sequences; and weighting the probability levels based on the correspondence between each one of the weighted probability levels and the respective face sizes as defined by the look-up table, such that detected faces closer in size to a preferred representation size are presented to the user for selection thereof as the displayed representation of the of the candidate video sequences. - View Dependent Claims (13)
-
-
14. A media handling system in which candidate video sequences are displayed on a display screen in schematic form for selection by a user, the system comprising:
-
a user control configured to define a set of one or more of the video sequences; a detector configured to detect human faces in the candidate video sequences, to detect a probability of a human face being present in each field or frame of the video sequences, and to weight at least some of the detected probability levels depending on the size of the detected face, each one of the weighted probability levels corresponds with a respective face size stored in a look-up; and a display screen configured to display at least one representation of the candidate video sequences for selection by the user, each representation of the candidate video sequence including one or more images representing human faces derived from the respective video sequences and having the highest weighted probability levels amongst the respective video sequences, wherein the detector weights the probability levels based on the correspondence between each one of the weighted probability levels and the respective face sizes as defined by the look-up table, such that detected faces closer in size to a preferred representation size are presented to the user for selection thereof as the displayed representation of the of the candidate video sequences.
-
Specification