The method of data presentation "Face Chernova" and their development using asymmetry
Chernoff Faces is a diagram of the visual representation of multivariate data in the form of a human face. Each part of the face: nose, eyes, mouth - is the value of a certain variable assigned to this part (18 total).
The basic idea is that for a person it is very natural to look at faces, because all people do it every day. Therefore, the analysis of the data is obtained by such "naturalistic". Easy to make comparisons and easy to identify deviations. Even blondes can perform multivariate analysis of a significant amount of data.
')
In 1981, Bernard Flury and Hans Riedwil (Bernhard Flury and Hans Riedwyl) improved the concept and added asymmetry to Chernov’s faces. Thus, the number of variables doubled to 36.
So, each face is an array of 18 elements, each of which takes a value from 0 to 1. The value corresponds to the appearance of the corresponding part of the face. The parameters of the studied objects are reduced to these values. The extremes of real data will be taken as 0 and 1. Everything else lies in this interval. On the resulting array is constructed face.
Description of the parameters of the person and examples of their use in my record here
nordisk.pp.ru/design/44
or under the cut
Here are the parameters set by the person:
1. Eye size
2. Pupil size
3. Pupil position
4. Tilt the eyes
5. Horizontal eye position
6. Vertical eye position
7. Eyebrow bend
8. Eyebrow density
9. Horizontal eyebrow position
10. Vertical eyebrow position
11. Upper hairline
12. Lower hairline
13. Circumference
14. Darkness of hair
15. The slope of hair hatching
16. Nose
17. Size of mouth
18. Bend mouth
The difficulty lies in the correct comparison of the studied variables with parts of the face. If an error occurs, important patterns may go unnoticed.
Flury gives an example of a successful analysis with the help of individuals. He analyzed 100 real and 100 counterfeit banknotes on the parameters of the size of borders, indents and diagonals. Here's what happened:
Fake banknotes clearly stand out in a separate group. Thus, the analysis revealed different groups of objects.
Asymmetry allows you to view objects in progress. The second example shows the different parameters in patients to whom treatment was applied. The left side of the face shows the values of the parameters before, and the right after the treatment.
See how the state of the parameters has changed. It is easy to understand who and how much better it has become, even without delving into the essence of the parameters studied.
The article Graphic Representation of Multicariate Faces (by Bernard Flury and Hans Riedwyl) can be read on JSTOR
www.jstor.org/stable/2287565
If you do not have access, I can send it to you in exchange for an interesting link that I don’t know about.
The basic idea is that for a person it is very natural to look at faces, because all people do it every day. Therefore, the analysis of the data is obtained by such "naturalistic". Easy to make comparisons and easy to identify deviations. Even blondes can perform multivariate analysis of a significant amount of data.
')
In 1981, Bernard Flury and Hans Riedwil (Bernhard Flury and Hans Riedwyl) improved the concept and added asymmetry to Chernov’s faces. Thus, the number of variables doubled to 36.
So, each face is an array of 18 elements, each of which takes a value from 0 to 1. The value corresponds to the appearance of the corresponding part of the face. The parameters of the studied objects are reduced to these values. The extremes of real data will be taken as 0 and 1. Everything else lies in this interval. On the resulting array is constructed face.
Description of the parameters of the person and examples of their use in my record here
nordisk.pp.ru/design/44
or under the cut
Here are the parameters set by the person:
1. Eye size
2. Pupil size
3. Pupil position
4. Tilt the eyes
5. Horizontal eye position
6. Vertical eye position
7. Eyebrow bend
8. Eyebrow density
9. Horizontal eyebrow position
10. Vertical eyebrow position
11. Upper hairline
12. Lower hairline
13. Circumference
14. Darkness of hair
15. The slope of hair hatching
16. Nose
17. Size of mouth
18. Bend mouth
The difficulty lies in the correct comparison of the studied variables with parts of the face. If an error occurs, important patterns may go unnoticed.
Flury gives an example of a successful analysis with the help of individuals. He analyzed 100 real and 100 counterfeit banknotes on the parameters of the size of borders, indents and diagonals. Here's what happened:
Fake banknotes clearly stand out in a separate group. Thus, the analysis revealed different groups of objects.
Asymmetry allows you to view objects in progress. The second example shows the different parameters in patients to whom treatment was applied. The left side of the face shows the values of the parameters before, and the right after the treatment.
See how the state of the parameters has changed. It is easy to understand who and how much better it has become, even without delving into the essence of the parameters studied.
The article Graphic Representation of Multicariate Faces (by Bernard Flury and Hans Riedwyl) can be read on JSTOR
www.jstor.org/stable/2287565
If you do not have access, I can send it to you in exchange for an interesting link that I don’t know about.
Source: https://habr.com/ru/post/54316/
All Articles