Documentos de Académico
Documentos de Profesional
Documentos de Cultura
discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/23400234
CITATIONS READS
3 169
2 authors, including:
Pascal Vallotton
ETH Zurich
82 PUBLICATIONS 1,149 CITATIONS
SEE PROFILE
All content following this page was uploaded by Pascal Vallotton on 22 December 2014.
The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document
and are linked to publications on ResearchGate, letting you access and read them immediately.
Skin Research and Technology 2008; 14: 493–497 r 2008 CSIRO
Printed in Singapore All rights reserved Journal compilation r 2008 Blackwell Munksgaard
doi: 10.1111/j.1600-0846.2008.00322.x Skin Research and Technology
Background/purpose: Hair loss or hair excess is a com- Scanner imaging ensures a sharp image over the whole
mon condition. There is a growing need to quantitatively field. The system analyses on the order of two images per
assess the success of interventions aimed at replenishing minute, making it suitable for large clinical studies. Counts
areas that lack hair or at removing hair from areas such as delivered by a human counter vs. the software were within
the back, the legs, or the arms. Non-invasive methods that 10% of each other (N 5 12).
do not require staining are highly desirable because the Conclusion: Based on our results, we expect that the soft-
staining process itself may affect the efficacy of the treat- ware will be useful to a number of researchers investigating
ment. medical and cosmetic issues involving objective assess-
Methods: We introduce a system based on a flatbed scan- ment of pilosity. The algorithm itself may be of use for other
ner and on novel and sensitive image analysis algorithms to applications.
count the number of hairs and their individual length.
Additionally, a measure of hair visibility is introduced, which Key words: hair – linear feature – hair counting – hair
allows assessing objectively the severity of the condition. length – pilosity
Results: Our system is able to detect even hairs that are
difficult to see to a human observer. It is robust to skin & Blackwell Munksgaard, 2008
impurities or variations in the skin texture and colour. Accepted for publication 30 December 2007
493
Vallotton and Thomas
494
Body hair counting and length measurement
Segment selection
Segments linking neighbouring local intensity
maxima were then tested for their quality, as
measured by the average intensity along their
length. Only segments shorter than 30 pixels
were produced in order to limit the number of
segments to consider. A value of 30 pixels was
found to be large enough such that the immense
majority of segments needed to span the hairs
were generated.
Hairs are very straight locally but they are
flexible. Therefore, rather than calculating the
average intensities only along a straight line,
we let the traces explore a path 1 pixel above
(respectively to the right of) and below (respec-
tively to the left of) the straight path. The optimal
path was not allowed to cross from one side to
the other of the straight line. We found that this
restriction improved discrimination against false
positives. The average intensity on the best such
path had to be higher than the intensity threshold Fig. 1. (a) RGB image of a calf, showing the taped black cardboard
IT in order for the segment to be retained for frame that allows defining the same region of interest before and after
further analysis. the hair removal treatment. (b) Same area as in (a) but with all hair
traces found by the software and longer than 15 pixels shown in red.
Results Fig. 2. Selected local intensity maxima are indicated by black circles
overlaid on the background corrected image. The maxima mostly line
The software exports numerical results in Excelt up along hairs. The density of retained maxima was set self-consis-
tables (Microsoft, Redmont, WA, USA), with each tently to 50 cm 2 on average, in order to speed up the algorithm.
495
Vallotton and Thomas
1 60 59
2 1 7
3 178 175
4 237 222
5 178 175
6 153 158
7 3 28
8 61 48
9 49 57
Fig. 3. Illustration of the hair growing process. Retained local maxima 10 23 29
are the large white disks. All retained candidate segments are shown in 11 11 15
black dotted lines and connect pairs of local maxima within 30 pixels of 12 37 38
each other. The best path in the connected component is the white Total 991 1011
dotted line. Note that the hair on the left was not traced by mistake
because our method deliberately produces only one trace per connected Traces shorter than 15 pixels were not counted. All test subjects were
component. Caucasians.
496
Body hair counting and length measurement
We have purposefully avoided hairs that were 2. Hoffmann R. TrichoScan. A new instrument for digital
crossing each other by limiting the use of the hair analysis. Hautarzt 2002; 53: 798–804.
3. Sun CM, Vallotton P. Fast linear feature detection using
software to short or trimmed hair. Dealing with multiple directional non-maximum suppression. In:
crossing hair will require scheme whereby once a Tang YY, Wang SP, Lorette G, Yeung DS, Yan H, eds.
hair trace has been extracted from a connected Proceedings of the 18th International Conference on
Pattern Recognition, Vol, I. Los Alamitos: IEEE Compu-
component, another trace is initiated from the ter Society, 2006: 288–291.
brightest segment that remains in the component. 4. Menzies SW, Bischof L, Talbot H et al. The performance
Initial attempts have shown that this approach of SolarScan: an automated dermoscopy image analysis
works well; however, it created a significant instrument for the diagnosis of primary melanoma.
Arch Dermatol 2005; 141: 1388–1396.
number of additional false positive that would 5. Cha J, Cofer RH, Kozaitis SP. Extended Hough trans-
need to be filtered out. form for linear feature detection. Patt Recognit 2006; 39:
These extensions will be needed to extend our 1034–1043.
6. Quackenbush LJ. A review of techniques for extracting
framework to other applications, such as tracing linear features from imagery. Photogr Eng Remote Sen-
biological polymers in highly cluttered environ- sing 2004; 70: 1383–1392.
ments, neurites in noisy cell images, or wrinkles. 7. Press WH, Vetterling WT, Teukolski SA, Flannery BP.
Numerical recipes in C11: the art of scientific comput-
ing, Press CU, editor, 2001.
Acknowledgement
Address:
We are grateful to Changming Sun for internally Pascal Vallotton
reviewing this manuscript. Biotech Imaging
CSIRO Mathematical and Information Sciences
Locked Bag 17
North Ryde, NSW 1670
References Australia
1. Leavitt M, Perez-Meza D, Rao NA, Barusco M, Kaufman Tel: 161 2 9325 3208
KD, Ziering C. Effects of finasteride (1 mg) on hair Fax: 161 2 9325 3200
transplant. Dermatol Surg 2005; 31: 1268–1276. e-mail: pascal.vallotton@csiro.au
497
View publication stats