Report 5: Computational Aesthetics, Generative Art

Post Reply
glegrady
Posts: 203
Joined: Wed Sep 22, 2010 12:26 pm

Report 5: Computational Aesthetics, Generative Art

Post by glegrady » Tue Mar 29, 2022 2:22 pm

Report 5: Computational Aesthetics, Generative Art

MAT 255 Techniques, History & Aesthetics of the Computational Photographic Image
https://www.mat.ucsb.edu/~g.legrady/aca ... s255b.html

Please provide a response to any of the material covered in this week's two presentations by clicking on "Post Reply". Consider this to be a journal to be viewed by class members. The idea is to share thoughts, other information through links, anything that may be of interest to you and the topic at hand.

Topic: Computational Aesthetics, Generative Art

Report for this topic is due by May 13, 2022 but each of your submissions can be updated throughout the length of the course.
George Legrady
legrady@mat.ucsb.edu

siennahelena
Posts: 8
Joined: Tue Mar 29, 2022 3:33 pm

Re: Report 5: Computational Aesthetics, Generative Art

Post by siennahelena » Sat May 07, 2022 12:06 pm

After our conversation about computational aesthetics, something I kept thinking about that we didn’t discuss in much detail is the appraisal of human beauty. From several articles for the week, a common theme was how researchers, scientists, and artists grapple with how to measure aesthetics. However, a challenge is that aesthetics, what is deemed beautiful, its inherent subjectivity. While there are certain rules for what makes images aesthetic, like the golden ratio and rule of thirds, ultimately what is beautiful relies on the viewer. As described by Hoenig in his article about the definition of computational aesthetics, “Aesthetics is assumed always to be subjective, but aesthetics choices can reflect the opinion of either (a) one person, (b) a group of persons or (c), a normalized observer that represents some kind of universal aesthetic opinion” (Hoenig, p. 16). Moreover, the difficulties (and dangers) of how to measure aesthetics are further amplified in the discussion of human beauty.

Thus, I thought I would share two examples of the consequences of computational aesthetics of human beauty.

[1] First, around a year ago, I came across this website: https://www.hownormalami.eu/. It’s described as an “interactive documentary” that teaches about different face analysis software and AI while simultaneously using your face to demonstrate how the software/AI works. While they go through several different AI metrics like predicted BMI and gender, the first one they present is about how “hot” you are on a scale of 1-10. For this beauty rating, they discuss how most of these algorithms are trained based on amassed ratings typically collected from university students. However, depending on where the ratings were collected, the AI may only be trained on the beauty norms from a specific culture. This can have a significant impact because companies will use beauty ratings as a part of their services. For example, Tinder will present matches of individuals with similar beauty ratings.


[2] In a similar vein, my second example is about augmented reality face filters on social media websites like Instagram and TikTok. For context, these social media sites have a suite of AR filters that allow individuals to change their appearance. However, there’s been a surge of negative reactions about how filters, especially ones that enhance beauty, can be especially damaging to a person’s self-perception. In fact, Forbes coined the term “Snapchat Dysmorphia” in relation to how constant usage of beauty filters causes individuals to become dissatisfied with their actual faces https://www.forbes.com/sites/annahaines ... 6187a14eff. Furthermore, a recent empirical study shows that a primary reason people use these filters is to present their ideal, aspirational selves. However, using beauty filters for this reason also decreases self-acceptance and positive affect (Javornik et al., 2022).

Image
Example of different beauty filters. Retrieved from https://www.refinery29.com/en-gb/instag ... dysmorphia


Sources:
  • Hoenig, F. (2005). Defining Computational Aesthetics (L. Neumann, M. Sbert, B. Gooch, & W. Purgathofer (editors, Eds.)
  • Javornik, A., Marder, B., Barhorst, J. B., McLean, G., Rogers, Y., Marshall, P., & Warlop, L. (2022). ‘What lies behind the filter?’ Uncovering the motivations for using augmented reality (AR) face filters on social media and their effect on well-being. Computers in Human Behavior, 128, 107126

ashleybruce
Posts: 11
Joined: Thu Jan 07, 2021 2:59 pm

Re: Report 5: Computational Aesthetics, Generative Art

Post by ashleybruce » Mon May 09, 2022 9:28 pm

One of the things I am most interested in exploring through this class is the increased availability of filters in social media. Similar to what Sienna was saying in her post, beauty is subjective, especially the idea of self beauty. But this idea of self beauty can be warped when constantly comparing to others as presented on social media. This comparison with others is almost intrinsic, but it is greatly swayed when the people being compared to are editing their images in such a way and then presenting them as the truth.
Edited.png
In these pictures, we see a good looking girl as is commonly presented on social media. We can see some makeup and maybe some slight editing? But this woman has an even skin tone, no pores, good hair, and bright eyes. When these images are posted on social media under the guise of no editing, it makes women (and people in general for that matter) believe that women can look like this naturally. But the truth is far from that.
Natural.png
Here are the same pictures, but the non-edited version. And the difference is drastic. When comparing side by side, we can see the obvious editing, but without it, the edited pictures being presented push this view of beauty that does not exist. For example, in the edited pictures, the woman has completely eliminated any pores and evened out here skin tone. It is reported that 40 to 50 million people struggle with acne in the US alone [1]. The skincare industry in the US makes around 17 billion dollars a year [2]. There are many people, young women especially, who are self-conscious about the way they look. The images that are put out by "influencers" on social media only serve to promote unattainable look standards.

This is only one part of the problem though. What I just mentioned was the use of editing that is meant to go unsuspecting to the audience. But the easy access of filters can also have negative affects even when the viewer knows a filter is being used. Sienna brought up a good point in her post about how beauty is very difficult to measure because it is subjective. But these ideas can be drastically influenced by what we see online and what we believe to be attainable.
orig.JPG
butterfly.JPG
sparkle.JPG
Here is a picture of Margot Robbie I found on the internet. I then used two filters that were easily accessible on snapchat just over her face. As you can see, even though the main purpose of the butterfly filter and the sparkle filter is to have fun butterflies and sparkles over the image, that's not all the filter does. The filter brings the jawline slightly in for a smaller jaw, makes the nose smaller, and widens the eyes a bit. The difference is so subtle, but it makes the person applying the filters believe that if they could only fix these things about themselves, they could look like the images presented by all the women on social media.

This brings up a few interesting questions. What is it that decides this standard of beauty? As mentioned in lecture this week, there are certain themes in photographs that make it more aesthetically pleasing. This consists of things such as the golden ratio, the rule of thirds, color combinations, etc. But these same rules cannot be applied to human beauty.


References
[1] https://jamanetwork.com/journals/jamade ... 25%20years.
[2] https://www.statista.com/topics/4517/us ... %20dollars.

nataliadubon
Posts: 15
Joined: Tue Mar 29, 2022 3:30 pm

Re: Report 5: Computational Aesthetics, Generative Art

Post by nataliadubon » Tue May 17, 2022 12:44 pm

Personally, I feel that it is difficult to speak about generative art in 2022 without acknowledging the sudden rise of NFTs, which stand for "Non-Fungible Tokens". A clearer definition from Forbes describes NFTS as such:
An NFT is a digital asset that represents real-world objects like art, music, in-game items and videos. They are bought and sold online, frequently with cryptocurrency, and they are generally encoded with the same underlying software as many cryptos.
Essentially, NFTs have become a way for art enthusiasts to collect digital illustrations in a similar mannerism to traditional art. Just as there are multiple copies and prints of the Mona Lisa, only the original piece is worth millions. NFTs are attempting to create that similar effect in the digital community by allowing individuals to purchase the ownership of an artist's illustration, fully acknowledging that though there may be many prints and screenshots, only the original holds the most value. This idea overall has brought some controversy on its own.

However, it's important to realize how generative art comes into play when discussing NFTs. In order to further add to the prestige and originality of elevated digital art, generative art has been used with individual parameters to create truly unique art. Therefore, if another artwork looks similar, in theory they don't contain the same parameters and is therefore different. This entire process is often calling "minting":
Minting a generative art NFT adds a level of uniqueness that could not have been reached before. This is achieved by including inputs to the piece of art such as wallet address, transaction ID or gas price. These parameters are then used to mint the NFT
Here is one example of generative art with unique parameters that is now being sold for thousands of dollars by artist Tyler Hobbs:
Image

Overall, the immense progression towards generating, selling, and owning NFTs has challenged the idea of what necessarily gives art its worth.


References
https://www.forbes.com/advisor/investin ... ble-token/
https://medium.com/@datash/an-introduct ... e650a0f281
https://tylerxhobbs.com/essays/2021/the ... rative-art

Post Reply