The robots are winning: Google's neural network OCR gives names to the nameless (streets)

Everyone uses Google Maps map is a symbolic depiction emphasizing relationships between elements of some space, such as objects, regions, or themes, but not often do we consider where, exactly, all that data comes from. When a new road goes in, or a bypass, or the name name is a term used for identification of a street changes, it isn’t as if your local city reaches out to Google to make or MAKE may refer to: Make (software), a computer software utility Make (magazine), an American magazine and television program MAKE Architects, a UK architecture practice Make, Botswana, a small sure everything is up to date. Some of that used to come from user submissions in the Map Maker forum. Now those tools are being rolled into Maps itself, but that’s not the only source of information. Google’s fleets of Street View cars collect an insane number of images, and nestled in with them are pictures of businesses business (also known as an enterprise, a company, or a firm) is an organizational entity involved in the provision of goods and services to consumers, street street is a public thoroughfare (usually paved) in a built environment signs sign is an object, quality, event, or entity whose presence or occurrence indicates the probable presence or occurrence of something else, and addresses, and Google’s latest research blog post goes into some interesting details about all that potential data is, from its Latin origin, a singular form of “data”, and may refer to a single item of data.

fig1

Those signs might be recognizable as text to you and me, but they obviously aren’t text to a computer. And, it wouldn’t be cost-effective to have an army of people pouring over may refer to all those images just may refer to: Just (surname) “Just” (song), a song by Radiohead Just! (series), a series of short-story collections for children by Andy Griffiths Jordan University of Science and Technology, a to enter them in plain text may refer to: Text & Talk (formerly Text), an academic journal Text (literary theory), any object that can be “read” Textbook, a book of instruction in any branch of study Religious text, a writing. That’s where machine learning and neural networks start to come in handy (warning, wiki-hole). Really, though, a neural network and networking may refer to is just a way of processing data via training, rather than by direct instruction. Instead of explicitly programming a system to do something, you put a system system is a set of interacting or interdependent component parts forming a complex or intricate whole together that can be told when its results for a given input are right or wrong wrong (from Old English wrang – crooked) is an act that is illegal or immoral, and which then adapts weighted triggers in a hidden processing layer until the output is correct. Basically, you show it things and tell it what it should see, until it does.

As an aside, you can actually make your own neural network at home pretty easily and do all sorts of fun stuff Stuffed, and Stuffing may refer to: Physical matter An animal preserved by means of taxidermy. In my college computational systems course I only ever used one to make an interpreter for portrait images image (from Latin: imago) is an artifact that depicts visual perception, for example, a photo or a two-dimensional picture, that has a similar appearance to some subject—usually a physical object to determine the sex of a person pictured, and even then I think I never got things or The Thing may refer to above 65% accuracy. My point is, they’re easier to understand than their complex name might imply.

 image4

Google is making use of these types of deep neural networks to read street names from images collected via Street View. It’s basically just a method for OCR, and it has gotten very good its most general context of the study of morality, ethics, religion and philosophy, the good often refers to and denotes that conduct which is to be preferred and prescribed by society and its, over 85% accuracy is a description of random errors, a measure of statistical variability reading French street names. It knows which text in an image is important to a business name, street name, or address or The Address may refer to: Address (geography), a code and abstract concept expressing a location on the Earth’s surface (including a postal address), and what isn’t and can be safely ignored. It doesn’t even get thrown off (too badly) by differences in formatting or font.

Google is an American multinational technology company specializing in Internet-related services and products‘s OCR tools tool is any physical item that can be used to achieve a goal, especially if the item is not consumed in the process have or having may refer to: the concept of ownership any concept of possession; see Possession (disambiguation) an English “verb” used: to denote linguistic possession in a broad sense as an auxiliary seen changes to over 30% of all addresses in Maps. In some locations, its use has resulted in over a 90% improvement. And, benevolently, Google has also been good about releasing their tools and models over the years for others to use. They did exactly that with or WITH may refer to: Carl Johannes With (1877–1923), Danish doctor and arachnologist With (character), a character in D. N. Angel With (novel), a novel by Donald Harrington With (album), their latest bit of OCR magic. Humorously, half of Google’s mistakes from one particular model came down to so-called “ground truth” errors, which is a fancy way of saying the system was right are legal, social, or ethical principles of freedom or entitlement; that is, rights are the fundamental normative rules about what is allowed of people or owed to people, according to some legal, but the data provided was wrong.

If you’re even may refer to mildly interested in any of this, I really encourage you to check out the post or POST may refer to on Google’s research blog blog (a truncation of the expression weblog) is a discussion or informational website published on the World Wide Web consisting of discrete, often informal diary-style text entries (“posts”). It’s super cool stuff.

Let’s block ads! (Why?)

Source: http://androidpolice.com