Tag: graphics

Pixel Perfect

the uncanny valley comes full circle

Pascal Dangin is the premier retoucher of fashion photographs. Art directors and admen call him when they want someone who looks less than great to look great, someone who looks great to look amazing, or someone who looks amazing already—whether by dint of DNA or M·A·C—to look, as is the mode, superhuman. (Christy Turlington, for the record, needs the least help.) In the March issue of Vogue Dangin tweaked 144 images: 107 advertisements (Estée Lauder, Gucci, Dior, etc.), 36 fashion pictures, and the cover, featuring Drew Barrymore. To keep track of his clients, he assigns 3-letter rubrics, like airport codes. Click on the current-jobs menu on his computer: AFR (Air France), AMX (American Express), BAL (Balenciaga), DSN (Disney), LUV (Louis Vuitton), TFY (Tiffany & Co.), VIC (Victoria’s Secret).

Street View OCR

In addition to street scenes, indexing can be applied to other image sets. In one implementation, a store (e.g., a grocery store or hardware store) is indexed. Images of items within the store are captured, for example, using a small motorized vehicle or robot. The aisles of the store are traversed and images of products are captured in a similar manner as discussed above. Additionally, as discussed above, location information is associated with each image. Text is extracted from the product images. In particular, extracted text can be filtered using a product name database in order to focus character recognition results on product names.

now you won’t lose your keys again, ever.

Seam Carving Demo

you can use your own images in this flash implementation of seam carving

Seam carving (or liquid rescaling) is an algorithm for content-aware image resizing. It functions by establishing a number of seams (paths of least importance) in an image and automatically removes seams to reduce image size or inserts seams to extend it. Seam carving also allows manually defining areas in which pixels may not be modified, and features the ability to remove whole objects from photographs.

Nervous About Resizing

The idea is to not just squeeze or crop the image as it is resized to fit (say) a browser window, but to remove less informative parts so that important objects and people remain. the browser compresses the image and the designer has made Y a preferred seam. We will tend to see X and Z, and likely never think of Y. This is a form of manipulation more subtle than just removing Y, since the designer can now truthfully say that the photo is authentic

Compound-Eye Camera

He looked at biological imaging systems–in particular, the compound eyes of insects–for the design blueprint. The technology, called TOMBO (Thin Observation Module by Bound Optics), is actually a collection of 9 small lenses and software that analyzes the scene by mimicking the process that insects use to recognize the position, shape, and color of objects. The researchers have crammed TOMBO’s hardware into a tiny box the size of a shirt button. And in the age of increasingly smaller and thinner mobile gadgets, such a compound-eye camera could provide powerful image-taking and image-recognizing functions in, for example, a cell phone.

camera the size of a shirt button can extract 3D information from scenes and recognize objects.