But how did a glossy magazine photograph become the benchmark for —the algorithms that compress, stream, and recognize images on every modern website?
This is the story of how a single image defined the engineering constraints of the early internet and continues to haunt the ethics of dataset curation. At the University of Southern California’s Signal and Image Processing Institute (SIPI), assistant professor Alexander Sawchuk needed a high-contrast, high-detail image to scan for a colleague’s conference paper. The lab’s flatbed scanner (one of the first) was crude: 100 lines per inch, 6 bits per pixel.
Before deploying a new image codec to Chrome or Safari, engineers still run Lena through it. Why? Because if you can't compress Lena well, you can't compress any face well.
"We need a standardized, high-quality, public-domain image to compare results across 50 years of literature. Changing the benchmark invalidates historical progress."
The engineers were tired of the standard test images—stock photos of mandrills and peppers. According to lore, a graduate student named William Pratt walked in with a copy of the November 1972 issue of Playboy he had just bought. They tore out the centerfold, wrapped it around the drum scanner, and digitized a 5.12 x 5.12 cm crop of Lena Forsén’s face and hat.
"Using a soft-core porn image as the default test for serious engineering normalizes the exclusion of women. It signals that the lab is a frat house, not a professional environment."
"Lena is actually a bad test image. It’s over-smoothed, has limited dynamic range, and its popularity leads to overfitting. Natural images (BSDS500, ImageNet) are superior."