|By Le Williams | 2 years ago|
Microsoft announced some major improvements today to its fundamentally biased facial recognition software. The Azure-based Face API was criticized in a research paper earlier this year for its error rate, as high as 20.8 percent when attempting to identify the gender of people of color, particularly women with darker skin tones.
In contrast, the study concluded that Microsoft’s AI was able to identify the gender of photos of “lighter male faces” with an error rate of zero percent.
Reportedly, Microsoft lacked images of darker skinned individuals, as demonstrated in its recognition test results, similar to other companies developing face recognition technology.
Microsoft’s blog post today positions a focus primarily on the data it used when building the facial recognition software, stating that such technologies are “only as good as the data used to train them.” Considering the predicament, the most obvious fix was a new dataset containing more images of individuals with hues of brown, which Microsoft used.
In the blog post, Microsoft senior researcher Hanna Wallach further discussed one of the industry’s broader failings, noting how data generated by a biased society would lead to biased results when it came to training machine learning systems.
“The Face API team made three major changes. They expanded and revised training and benchmark datasets, launched new data collection efforts to further improve the training data by focusing specifically on skin tone, gender, and age, and improved the classifier to produce higher precision results.”
With the latest batch of improvements, Microsoft said it was able to reduce the error rates for men and women with darker skin by up to 20 times. For all women, the company said the error rates were reduced by nine times.