This attractiveness test is completely free. No registration is needed, you just need to upload a picture.
More than 7000 hand-labeled faces were used to train the Deep Learning model behind this online tool. The results are accurate if you follow our recommendations. .
Despite heavy Operationans that are performed by our attractiveness prediction model, based on Neural Networks, the result are shown within seconds.
Test it now by uploading a picture of you!Start the test
How should the picture look like? here are Examples that work for calculation your hotness.
We recommend you to stick to these suggestions so that our AI-Model can predict an accurate score. Besides these tips, we also recommend avoiding accessories like sunglasses and nothing should cover parts of your face. Note that hair doesn't have a big impact on the beauty test, much more important is your face. Furthermore we suggest not using black and white pictures and no Instagram filters that drastically change the colors.
The follow photos were all rated by out beauty calculator. The photos of the faces were all created by Artificceal Intelligence (Generative Adversial Neural Network to be precies). You can find more information here. The beauty/attractiveness of each portrait photo is rated with a value on a scale from 1 to 10. The pictures are sorted from less attractive to very attractive.
We use a complex Artificial Neural Network (ANN), based on a pre-trained ResNet-50 architecture which is finetuned with a dataset of hand-labeled photos.
We use a second Neural Network that locates the faces, crops it, and transforms a bit, to make the input images consistent with our training dataset. We also use the Open-CV moduleto preprocess the images.
We plan to publish a more detailed technical description at a later time and are also thinking about releasing the code on Github.
Studies show that people consider attractive people to be more successful and competent, but not more righteous or concerned about other people. Other studies show that even infants pay more attention to attractive faces and that adults implicitly associate attractive faces with positive qualities.
In experiments, attractive faces are often created on the computer. For this purpose, a series of photographs of real people is morphed into an average face. Such average faces are considered attractive by many viewers. According to some authors, however, the attractiveness of average faces could be due more to the side effect that the morphing process makes their skin look particularly flawless, smooth, fine and thus of reproductive age, than to the actual mediocrity of the faces.
The perceived attractiveness can be increased by artificially created symmetry between the face halves. Infants also pay more attention to these artificially created faces. In addition, faces with more feminine features seem to be perceived as more attractive, for example if they have higher cheekbones. Daily experience shows that smiling people are spontaneously perceived as more attractive than others.
In the animal kingdom, there is evidence that external features and their symmetry determine sexual attractiveness, for example the peacock's wheel, the flaring or whistling of birds, or, among higher mammals, the stature of the oldest gorilla or the antlers of male deer.
In a study carried out in 2011, researchers investigated the relationship between the (facial) attractiveness of infants (aged 24 months and under) and the same individuals in young adulthood (16-18 years) by evaluating attractiveness using photographs. In fact, no correlation was found between attractiveness in babyhood and adulthood (no correlation): some pretty babies, for example, became unattractive adults, while some unattractive babies remained unattractive. This was true for both men and women, but at the age of five years or ten years, future attractiveness can already be partially predicted.