computer vision
A field of machine learning that enables computers to interpret and extract structured information from images, used here to parse complex historical document layouts
As defined in cwt_melissa-dell
Other definitions
Machine learning methods that interpret images or document layouts, rather than only the text they contain.
Max Simkoff - Redesigning the Home Buying Experience - [Founder’s Field Guide, EP. 47]Techniques that let computers extract information from images or video, such as identifying objects and motion.
Data, Decisions, and Basketball
Where it comes up · 13
- Quant in Private Markets2 claims
- John Deere: Centuries of Farming Innovation2 claims
- Pseudonymous Social Capital and Bottomless Coffee2 claims
- The Future of Artificial Intelligence2 claims
- Will Marshall - Indexing the Earth - [Invest Like the Best, EP. 251]2 claims
- 72 | César Hidalgo on Information in Societies, Economies, and the Universe2 claims
- Palmer Luckey Anduril Presentation Leaves Audience SPEECHLESS2 claims
- Making Decisions with Data1 claim
and 5 more
Most important claims · 10 of 20Search all claims for “computer vision” →
- For a long time sports data was poor because it captured what was easy to record, which describes what happened in the game rather than what best predicts outcomes; player tracking and computer vision now provide data built for prediction.Making Decisions with Data
- Around 2011, neural nets were considered a dead, fringe technology—Russell and Norvig's ~1100-page AI textbook devoted only about 16 pages to them—and AI itself was viewed as a career graveyard with near-zero venture capital, yet AI's missing ingredient was simply computing power.The Man Who Built NVIDIA (with Stephen Witt)
- The Platform 2 craft uses onboard computer vision to build a simple 3D map as it descends, avoiding obstacles like roofs, string lights, clotheslines, power lines, trees, and people, then lowers packages via a winch—and can operate in rain and winds up to about 38 mph.These Delivery Drones Will Beat Amazon To Your Doorstep
- AI systems can be improved to tell the difference between real objects and advertising imagery through better computer vision technology, but there are likely many cases we haven't thought of yet that could fool machines if they don't understand the world the same way humans do; eventually systems might develop such understanding, but it could take longer than 10 years.The Future of Artificial Intelligence
- Deep neural networks achieved human-level or superhuman performance on object recognition tasks by 2017, with error rates dropping below human performance, largely because machines are much better than humans at recognizing dog breeds, but they are also good at recognizing objects in street scenes that self-driving cars might need to recognize.The Future of Artificial Intelligence
- The US military is well behind China's People's Liberation Army in AI implementation, and there is more advanced AI in John Deere tractors than in any US military vehicle, and better computer vision in the Snapchat app than in any system deployed by the Department of Defense.Palmer Luckey Anduril Presentation Leaves Audience SPEECHLESS
- There is better computer vision in the Snapchat app on your phone than in any system the US Department of Defense has deployed.Palmer Luckey Anduril Presentation Leaves Audience SPEECHLESS
- Doma now uses computer vision to classify closing documents by layout and geographic placement of text, such as tables, shading and signature lines, to extract fees, reducing a task that takes a human about 30 minutes to under three seconds.Max Simkoff - Redesigning the Home Buying Experience - [Founder’s Field Guide, EP. 47]
- Using computer vision on about 2,000 to 3,000 snack bar companies and many more products, the team found an inverse correlation between the number of words on the front of the package and revenue growth, though they would never invest on this metric alone.Quant in Private Markets
- Deere's probable endgame is full autonomy across seeding, spraying, and harvesting, whether decisions are made by a centralized computer or distributed across each machine, with the company eventually selling software-in-a-box or optics-in-a-box to make all farms more efficient.John Deere: Centuries of Farming Innovation