Device, System and Method for Skin Detection

Patent metadata

Field	Value
Publication number	US-2016171684-A1
Application number	US-201514956429-A
Country	US
Kind code	A1
Filing date	Dec 2, 2015
Priority date	Dec 15, 2014
Publication date	Jun 16, 2016
Grant date	—

Abstract

The present invention relates to a device, system and method for skin detection. To enable a reliable, accurate and fast skin detection the proposed device comprises an input unit ( 20 ) for obtaining a sequence of image frames acquired over time, a segmentation unit ( 22 ) for segmenting an image frame of said sequence of image frames, a tracking unit ( 24 ) for tracking segments of the segmented image frame over time in said sequence of image frames, and a clustering unit ( 26 ) for clustering the tracked segments to obtain clusters representing skin of a subject by use of one or more image features of said tracked segments.

First claim

1 . Device for skin detection comprising:
an input unit for obtaining a sequence of image frames acquired over time, a segmentation unit for segmenting an image frame of said sequence of image frames, a tracking unit for tracking segments of the segmented image frame over time in said sequence of image frames, a clustering unit for clustering the tracked segments to obtain clusters representing skin of a subject by use of one or more image features of said tracked segments.

2 . Device as claimed in claim 1 ,
wherein said segmentation unit is configured to over-segment the image frame that is used for segmentation.

3 . Device as claimed in claim 1 ,
wherein said clustering unit is configured to use temporal color variations of the tracked segments as feature for clustering the tracked segments.

4 . Device as claimed in claim 3 ,
wherein said clustering unit is configured to perform a Fourier transformation of the spatially combined color value of at least part of the pixels in a tracked segment and to cluster two tracked segments into a single cluster if their amplitude peak frequency has substantially the same value and phase.

5 . Device as claimed in claim 1 ,
wherein said clustering unit is configured to compute the inner product between normalized time signals of different tracked segments and to cluster said tracked segments into a single cluster if said inner product exceeds a predetermined threshold.

6 . Device as claimed in claim 1 ,
wherein said clustering unit is configured to use the hue of pixels of the tracked segments as feature for clustering the tracked segments.

7 . Device as claimed in claim 1 ,
wherein said segmentation unit, tracking unit and clustering unit are configured to repeatedly perform segmentation, tracking and clustering, wherein the sequence of acquired image frames used for subsequent repetitions overlap in time.

8 . Device as claimed in claim 1 ,
wherein said segmentation unit is configured to perform a feature point detection, in particular a Harris corner detection.

9 . Device as claimed in claim 1 ,
wherein said segmentation unit is configured to perform a triangulation, in particular a Delaunay triangulation.

10 . Device as claimed in claim 2 ,
wherein said segmentation unit is configured to over-segment the image frame that is used for segmentation based on color, position and/or texture properties.

11 . Device as claimed in claim 1 ,
wherein said tracking unit is configured to track the segments of the segmented image frame using motion estimation.

12 . Device as claimed in claim 1 ,
further comprising a vital signs detector for detecting vital signs of a subject based on image information from detected skin areas within said sequence of image frames.

13 . System for skin detection comprising:
an imaging unit for acquiring a sequence of image frames over time and a device for skin detection as claimed in claim 1 based on the acquired sequence of image frames.

14 . Method for skin detection comprising:
obtaining a sequence of image frames acquired over time, segmenting an image frame of said sequence of image frames, tracking segments of the segmented image frame over time in said sequence of image frames, clustering the tracked segments to obtain clusters representing skin of a subject by use of one or more image features of said tracked segments.

15 . Computer program comprising program code means for causing a computer to carry out the steps of the method as claimed in claim 14 when said computer program is carried out on the computer.

Assignees

• Koninkl Philips Nv

Inventors

• De Haan Gerard

Classifications

• G06V40/15

  Biometric patterns based on physiological signals, e.g. heartbeat, blood flow · CPC title

• G06V10/7635

  based on graphs, e.g. graph cuts or spectral clustering · CPC title

• G06F2218/00

  Aspects of pattern recognition specially adapted for signal processing · CPC title

• G06V10/56 Primary

  relating to colour · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title