Process and device for detecting faces in a colour image

1. Process for use in a device for detecting faces in an image, the image being composed of a plurality of pixels, comprising the steps of:

using a processor, to perform the steps of:

detecting the flesh coloured pixels in the image,

segmenting the image into regions of homogeneous colour,

selecting, among the regions of homogeneous colour, of the regions comprising a number of flesh coloured pixels greater than a first predetermined threshold, the regions selected being said to be flesh coloured regions,

merging of the neighbouring flesh coloured regions until the merge cost attains a second predetermined threshold, the merge cost linearly weighting a merge cost relating to the shape of the regions and a merge cost relating to the colour of the regions, and

excluding false positives,

wherein the merge step comprises the substeps of

calculating the merge cost relating to the colour of the regions by calculating the mean difference in colour between neighbouring regions, and

calculating the merge cost relating to the shape by calculating the overlap between the area of the region and the area of an ellipse having the same centre of gravity as the said region and overlapping it best,

the elliptic nature of each region by calculation of the ratio of the sum of the number of pixels of the region outside the ellipse and of the number of pixels of the ellipse outside the region to the number of pixels of the ellipse, and

the difference between the minimum of the measures of elliptic nature of the two neighbouring regions and the measure of elliptic nature of the merged region.

2. Process according to claim 1 wherein the step of detection of the flesh coloured pixels consists in defining a face colour model in the form of a two-dimensional Gaussian probability law in a chrominance plane.

3. Process according to claim 1 wherein the step of excluding false positives consists in comparing the properties of the merged regions with certain properties of a face and in excluding the regions whose properties are too far from those of a face.

4. Process according to claim 3 wherein the properties are chosen among

the size of the region,

the shape of the region,

the average colour,

the variance of the luminance along the major axis and any combination of these properties.

5. Process according to claim 1 wherein the step of excluding false positives includes the substeps of

calculating at least one visual descriptor with regard to the merged regions,

determining an optimal hyperplane in the space of descriptors between example images comprising a face and example images not comprising any face,

excluding the regions whose descriptor does not lie on the correct side of the hyperplane.

6. Process according to claim 5 wherein the descriptor is calculated by the steps of:

performing a wavelet transformation of a minimal rectangle encompassing the merged regions, and

calculating the descriptor as the variance of the wavelet coefficients in twelve detail images obtained by hierarchical decomposition of the image.

7. Device for detecting faces in an image, the image being composed of a plurality of pixels, wherein it comprises:

means for detection of the flesh coloured pixels in the image,

means for segmentation of the image into regions of homogeneous colour,

means for selection, among the regions of homogeneous colour, of the regions comprising a number of flesh coloured pixels greater than a first predetermined threshold, the regions selected being said to be flesh coloured regions,

means for merging of the neighbouring flesh coloured regions until the merge cost attains a second predetermined threshold, the merge cost linearly weighting a merge cost relating to the shape of the regions and a merge cost relating to the colour of the regions,

means for excluding false positives,

wherein the means for merging

calculates the merge cost relating to the colour of the regions by calculating the mean difference in colour between neighbouring regions, and

calculates the merge cost relating to the shape by calculating

the overlap between the area of the region and the area of an ellipse having the same centre of gravity as the said region and overlapping it best,

the elliptic nature of each region by calculation of the ratio of the sum of the number of pixels of the region outside the ellipse and of the number of pixels of the ellipse outside the region to the number of pixels of the ellipse, and

the difference between the minimum of the measures of elliptic nature of the two neighbouring regions and the measure of elliptic nature of the merged region.

8. A computer readable medium encoded with a computer program for detecting faces in an image, the image being composed of a plurality of pixels, the computer program comprising the steps of:

detecting the flesh coloured pixels in the image,

segmenting the image into regions of homogeneous colour,

selecting, among the regions of homogeneous colour, of the regions comprising a number of flesh coloured pixels greater than a first predetermined threshold, the regions selected being said to be flesh coloured regions,

merging of the neighbouring flesh coloured regions until the merge cost attains a second predetermined threshold, the merge cost linearly weighting a merge cost relating to the shape of the regions and a merge cost relating to the colour of the regions, and

excluding false positives,

wherein the merge step comprises the substeps of

calculating the merge cost relating to the colour of the regions by calculating the mean difference in colour between neighbouring regions,

calculating the merge cost relating to the shape by calculating

the overlap between the area of the region and the area of an ellipse having the same centre of gravity as the said region and overlapping it best,

the elliptic nature of each region by calculation of the ratio of the sum of the number of pixels of the region outside the ellipse and of the number of pixels of the ellipse outside the region to the number of pixels of the ellipse, and

the difference between the minimum of the measures of elliptic nature of the two neighbouring regions and the measure of elliptic nature of the merged region.