Startup Lunarship Software announces version 2019.11 of its photo organizer Phototheca, which is now equipped with deep neural networks to search for people and cats in photographs automatically.
Kyiv, Ukraine, November 19, 2019 --(PR.com)-- Phototheca app users who already benefitted from the product's photo organization features, will now be able to organize and manage photos faster and more accurately. The main feature in the new version of the Phototheca photo organizer is the implementation of Deep Learning algorithms for face detection and recognition of humans and cats.
Having emerged in the late 2000s, Deep Learning is a revolutionary artificial intelligence technology that allows training artificial neural networks on large volumes of data. Many of the most innovative and advanced product features currently available, such as facial recognition on Facebook and Google, as well as Apple's Siri's voice recognition, are all based on Deep Learning.
The face recognition technology in Phototheca provides 4-5 times more accurate recognition of human faces in photos compared to traditional object recognition algorithms based on Viola-Jones cascades of classifiers, HoG, or LBP methods. Deep convolutional neural networks are used as the core of the new technology. Neural networks inside Phototheca were trained to recognize the same face in different poses, light conditions, and environments. These networks can identify a person with more than 90% accuracy and fast enough to process high-resolution photos on consumers' PC without powerful and expensive hardware.
Once installed on a user's computer, Phototheca can import photos and allows the user to organize them via both automatic and semi-automatic modes for sorting and arranging photos. Currently, Phototheca is equipped with facial recognition and pet detection algorithms, as well as the ability to connect to the iPhone, search for duplicates, share photos to Web, and more.
Price and availability
Phototheca is available free of charge for Windows 7/8/8.1/10.
Links
Website: https://lunarship.com