|
|
| Line 1: |
Line 1: |
| '''TSL color space''' is a perceptual [[color space]] which defines color as [[tint]] (the degree to which a stimulus can be described as similar to or different from another stimuli that are described as [[red]], [[green]], [[blue]], [[yellow]], and [[white]], can be thought of as [[hue]] with white added), [[saturation]] (the [[colorfulness]] of a stimulus relative to its own [[brightness]]), and [[lightness]] (the brightness of a stimulus relative to a stimulus that appears white in similar viewing conditions). Proposed by [[Jean-Christophe Terrillon]] and [[Shigeru Akamatsu]],<ref name = terrillon1>{{cite conference |last= Terrillon|first=Jean-Christophe |last2=Akamatsu |first2=Shigeru |year=1998 |title= Automatic Detection of Human Faces in Natural Scene Images by Use of a Skin Color Model and of Invariant Moments |url= |conference=Proc. Of the Third International Conference on Automatic Face and Gesture Recognition|location = Nara, Japan|pages = 130–135| accessdate=December 8, 2013 }}</ref> TSL color space was developed primarily for the purpose of [[face detection]].
| | The author is recognized by the title of Numbers Wunder. Managing people is what I do and the wage has been really satisfying. Puerto Rico is exactly where he and his wife reside. To play baseball is the pastime he will by no means quit doing.<br><br>my weblog - [http://www.sddch.org/?document_srl=345265 std testing at home] |
| | |
| == Conversion between RGB and TSL ==
| |
| The conversion from gamma-corrected [[RGB]] values to TSL is straightforward:<ref name = terrillon1/>
| |
| | |
| <math>T =
| |
| \begin{cases}
| |
| \frac{1}{2\pi} \arctan{\frac{r'}{g'}} + \frac{1}{4}, & \mbox{if}~g'>0 \\
| |
| \frac{1}{2\pi} \arctan{\frac{r'}{g'}} + \frac{3}{4}, & \mbox{if}~g'<0 \\
| |
| 0, & \mbox{if}~g'=0 \\
| |
| \end{cases}
| |
| </math>
| |
| | |
| <math>S = \sqrt{\frac{9}{5}\left( r'^2 + g'^2 \right)}</math>
| |
| | |
| <math>L = 0.299R + 0.587G + 0.114B</math>
| |
| | |
| where:
| |
| | |
| <math>r' = r - \tfrac{1}{3}</math>
| |
| | |
| <math>g' = g - \tfrac{1}{3}</math>
| |
| | |
| <math>r = \tfrac{R}{R+G+B}</math>
| |
| | |
| <math>g = \tfrac{G}{R+G+B}</math>
| |
| | |
| Likewise, the reverse transform is as follows:
| |
| | |
| <math>R = k \cdot r</math>
| |
| | |
| <math>G = k \cdot g</math>
| |
| | |
| <math>B = k \cdot (1-r-g)</math>
| |
| | |
| where:
| |
| | |
| <math>r =
| |
| \begin{cases}
| |
| \frac{\sqrt{5}}{3} S, & \mbox{if}~T=0 \\
| |
| x \cdot g + \frac{1}{3}, & \mbox{if}~T \ne 0 \\
| |
| \end{cases}
| |
| </math>
| |
| | |
| <math>g =
| |
| \begin{cases}
| |
| - \sqrt{\frac{5}{9(x^2+1)}} \cdot S, & \mbox{if}~T>\frac{1}{2} \\
| |
| \sqrt{\frac{5}{9(x^2+1)}} \cdot S, & \mbox{if}~T<\frac{1}{2} \\
| |
| 0, & \mbox{if}~T=0 \\
| |
| \end{cases}
| |
| </math>
| |
| | |
| <math>k = \frac{1}{0.185r + 0.473g + 0.114}</math>
| |
| | |
| <math>x = - \cot ({2\pi \cdot T})</math> | |
| | |
| ==Advantages of TSL==
| |
| The advantages of TSL color space lie within the normalization within the RGB-TSL transform. Utilizing normalized r and g allows for chrominance spaces TSL to be more efficient for skin color segmentation. Additionally with this normalization, the sensitivity of the chrominance distributions to the variability of skin color is significantly reduced, allowing for an easier detection of different skin tones.<ref name = terrillon2>{{cite journal |last= Terrillon|first=Jean-Christophe |last2=Akamatsu |first2=Shigeru |year=1999 |title= Comparative Performance of Different Chrominance Spaces for Color Segmentation and Detection of Human Faces in Complex Scene Images |url= http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=840612 |journal=Vision Interface |publisher= |volume=99 |issue= |pages= |doi= |accessdate=8 December 2013}}</ref>
| |
| | |
| === Comparison of TSL to other color spaces ===
| |
| Terrillon investigated the efficiency of facial detection for several different color spaces. Testing consisted of using the same algorithm with 10 different color spaces to detect faces in 90 images with 133 faces and 59 subjects - 27 Asian, 31 Caucasian, and 1 African). TSL showed superior performance to the other spaces, with 90.8% correct detection and 84.9% correct rejection. A full comparison can be seen in the table below.<ref name = terrillon2/>
| |
| {| class="wikitable"
| |
| |-
| |
| ! Color Space !! # of Elements !! CD (%) !! CR (%)
| |
| |-
| |
| | TSL || 258 || 90.8 || 84.9
| |
| |-
| |
| | r-g || 328 || 74.6 || 80.3
| |
| |-
| |
| | CIE-xy || 388 || 56.6 || 83.5
| |
| |-
| |
| | CIE-DSH || 318 || 60.9 || 75.0
| |
| |-
| |
| | [[HSL and HSV|HSV]] || 408 || 55.7 || 84.7
| |
| |-
| |
| | YIQ || 471 || 47.3 || 79.8
| |
| |-
| |
| | YES || 494 || 41.6 || 80.3
| |
| |-
| |
| | [[CIELUV]] || 418 || 24.1 || 79.0
| |
| |-
| |
| | [[CIELAB]] || 399 || 38.4 || 83.6
| |
| |}
| |
| | |
| == Disadvantages of TSL ==
| |
| TSL space could be made more efficient and robust. There currently exists no color correction algorithms for different camera systems. Additionally, despite a better accuracy of skin tone detection, detecting dark skin color still proves to be a challenge.<ref name = terrillon1/>
| |
| | |
| == Applications ==
| |
| Being a relatively new color space and having very specific uses, TSL hasn’t been widely implemented. Again, it is only very useful in skin detection algorithms. Skin detection itself can be used for a variety of applications – face detection, person tracking (for [[surveillance]] and [[Match Moving|cinematographic purposes]]), and [[pornography]] filtering are a few examples. A [[Self-Organizing Map]] (SOM) was implemented in skin detection using TSL and achieved comparable results to older methods of [[histograms]] and Gaussian [[mixture models]].<ref name = brown>{{cite conference |last= Brown|first=D. |last2=Craw |first2=I. | last3 = Lewthwaite |first3=J. |year=2001 |title= A SOM Based Approach to Skin Detection with Application in Real Time Systems |url= |conference=British Machine Vision Conference|location = Manchester, United Kingdom|accessdate=December 8, 2013 }}</ref>
| |
| | |
| ==See also==
| |
| * [[HSL and HSV]]
| |
| * [[Face detection]]
| |
| * [[List of color spaces and their uses]]
| |
| | |
| == References ==
| |
| {{reflist}}
| |
| | |
| {{DEFAULTSORT:Tsl Color Space}}
| |
| [[Category:Color space]]
| |
The author is recognized by the title of Numbers Wunder. Managing people is what I do and the wage has been really satisfying. Puerto Rico is exactly where he and his wife reside. To play baseball is the pastime he will by no means quit doing.
my weblog - std testing at home