We're coming up on a year since Google CEO Sundar Pichai showed off a nifty obstruction-removal feature in Google Photos at I/O 2017 — you know, the one where a chain-link fence is magically removed from a photo of a girl at bat. Some Pollyannas were hoping Google would offer an update on the now-mythical feature at this year's developer conference. While the company announced some cool enhancements to Google Photos at I/O 2018, there was no official follow-up on the fate of the buzzworthy feature showed off last year. But now there's word that it has been deprioritized and may not be anywhere close to a rollout. Read More
It may seem unthinkable that the much maligned 'selfie,' a photo of oneself taken by oneself, could be used in any meaningful, useful way. That's exactly what is being proposed by researchers from the University of Washington. They've developed an app called BiliScreen which could utilize selfies, as well as computer vision algorithms and machine learning tools, as a method of screening for pancreatic cancer. Read More
Google I/O is underway and one of the first topics covered was the great strides the company has made in image recognition software. Further improvements in computer vision are enabling Google products to see the attributes behind the picture and break them down into constituent parts. This is powered by machine learning and capable of some incredible image editing feats. Read More
In the spirit of Amazon's Free App Of The Day promotion, Packt Publishing has been unleashing a free eBook from its massive library of content each day for the last month. There have been a couple of notable development books in the lineup including the Android NDK Game Development Cookbook and Android Database Programming. Today brings another nice surprise with Android Application Programming With OpenCV by Joseph Howse.
If you've never heard of OpenCV, it's a popular open source "computer vision" library designed for efficient, real-time processing. This is a great platform for live object tracking, photo capture, image manipulation, and more. Read More
In an effort to help advance computer vision on mobile devices, Qualcomm has released the first mobile-optimized CV library, aptly named FastCV. While this news may not be groundbreaking for end-users, it's a pretty big deal for developers, as this library can be used in mobile development to help improve things like face detection and recognition, text tracking and recognition, gesture recognition, as well as open a whole new world for augmented reality applications.
The initial release of FastCV supports Android development, with "expanded platform support" coming soon. So, if you're a dev looking to incorporate some CV into your next app, hit this link to download. Read More