Have you seen Google Goggles yet? Albeit still a bit of a novelty, it’s a quantum leap in web search and collective intelligence that allows users to scan any object or place (without the stickybit).
Google Goggles is a downloadable image recognition application created by Google Inc. Currently, it is used for searches based on pictures taken by handheld devices. For example taking a picture of a famous landmark would search for information about it, or taking a picture of a product's barcode will search for information on the product.
Google already uses artificial intelligence to interpret cryptic human queries, so a natural step to extend to interpreting cryptic images. As you’d imagine, it works best on books, landmarks, logos, contact info, artwork, businesses, products, barcodes, or text. Typically static elements that don’t change. It can also recognize up to three items at a time and any item you scan automatically linked to associated content. As an example we scanned a Red Strip Beer Can and voila.
The program proposed will be capable of identifying virtually anything. Currently the system is able to identify various labels or landmarks, allowing the user to learn about such items without needing a text-based search. The system can identify barcodes that allow users to search for similar products and prices, as well as save codes for future reference, similar to the failed CueCat of the late '90s, but with more functionality. The system will also recognize printed text and using Optical character recognition (OCR) produce a text snippet, and in some cases even translate the snippet into another language.
Google’s already mapped the streets and stars - so what’s next? They’re currently working to make the system capable of recognizing different plants and leaves, which aids not only the curious person, but also botanists and environmentalists searching for invading or rare plants. Google also plans to turn the app into a full-blown API set that will allow developers to create a number of branded visual search based applications for mobile devices including Augmented Reality (AR). The wonders never cease - check out the video below.