New Photoshop detector shows image alterations

Pretttty sweet, right?! Yup, image forensics researchers at Dartmouth College have created a photo analyzing tool that highlights any Photoshop-style modifications, testing it out on magazine covers and advertisements. Because, we’re bombarded by false images. Everyone uses them, and not even in the media. With new programs and Apps available, it’s not uncommon for a percentage of the general public to be airbrushing and enhancing their own digital photos (for Facebook or any other use – social and non-social). I don’t know about you, but I’m longing to see raw and unedited images. Or at least, realistic ones. Considering the state of culture and how superficial things have become, I don’t think that will happen anytime soon. So, I’m glad a tool like this has been created because I think it could assist people struggling with their perceptions of reality, instead of being a tool to merely satisfy curiosity. This new tool is able to show changes to photos, scaling changes from minor to massive overhauls on a 1 to 5 scale. “Publishers have legitimate reasons to alter photographs to create fantasy and sell products, but they’ve gone a little too far. You can’t ignore the body of literature showing negative consequences to being inundated with these images,” Image Forensics Specialist Hany Farid of Dartmouth University told Wired. Farid told the New York Times this may discourage retouching altogether. “Models, for example, might well say, ‘I don’t want to be a 5. I want to be a 1.” The tool’s algorithm statistically measures how much the image of a person’s face and body has been altered. Many of the before-and-after photos for their research were plucked from the Web sites of professional photo retouchers, promoting their skills. The algorithm is meant to mimic human perceptions. To do that, hundreds of people were recruited online to compare before-and-after images and to determine the 1 to 5 scale, from minimally altered to starkly changed. The human rankings were used to train the software. I’m curious to see how accurate this really is, but I still think it’s useful. Hopefully, the Dartmouth researchers will turn their mathematical tool into an App that will be available for consumers. If the general public is able to get their hands on something like this, it could be the beginning of a much more honest dialogue between companies, advertisers and consumers. For example, women will be able to see how much eyelashes have been retouched in a beauty ad for mascara. They’ll be able to see if what they’re being shown is even attainable. Or if certain jeans actually do make a model’s butt look great, versus some sculpting via Photoshop. If this tool is accurate, it could be something great for people who struggle with body image and comparing themselves to celebrities and models. I’m hoping that programs like this will discourage photo editing and lead to more realistic bodies being used in the media, therefore shifting our perception of what is “ideal” into a more normal and healthier range (because unfortunately, I don’t think we know how to advertise without an “ideal” to sell). I think it’ll be a process, then again most worthwhile things are.

About The Author

Patricia Colli, Editor of Beutiful Magazine, is a human rights activist, equality advocate, and promoter of health, acceptance and wellbeing. Having experienced disordered eating, unhealthy exercise patterns and poor body image, she is especially passionate about shedding light on eating disorders and the power of body acceptance.