{"id":89839,"date":"2020-07-26T19:42:07","date_gmt":"2020-07-26T17:42:07","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-programmy-dlya-upravleniya-fotografiyami-digikam-7-0"},"modified":"2020-07-26T19:42:07","modified_gmt":"2020-07-26T17:42:07","slug":"vypusk-programmy-dlya-upravleniya-fotografiyami-digikam-7-0","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/vypusk-programmy-dlya-upravleniya-fotografiyami-digikam-7-0","title":{"rendered":"Release of the photo management software digiKam 7.0","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

After a year of development the<\/a><\/noindex> Photo collection management program release digiKam 7.0.0<\/a><\/noindex>, developed as part of the KDE project. The program provides a comprehensive set of tools for importing, managing, editing, and publishing photos, as well as images from digital cameras in raw format. The code is written in C++ using Qt and KDE libraries, and is distributed<\/a><\/noindex> is licensed under GPLv2. Installation packages are prepared<\/a><\/noindex> are available for Linux (AppImage, FlatPak), Windows, and macOS.<\/p>\n

\"Release<\/a><\/noindex><\/center><\/p>\n

A key improvement in digiKam 7.0 is a newly completely redesigned system for classifying faces in photos, enabling the identification and recognition of faces in images, and automatically assigning appropriate tags. Instead of the previously used cascade classifier<\/a><\/noindex> from OpenCV, the new version employs a deep neural network-based algorithm , which improved identification accuracy from 80% to 97%, increased processing speed (supporting parallel computation on multiple CPU cores), and fully automated the tagging process, relieving the user from the need to confirm the accuracy of matches.<\/a><\/noindex>The package includes a pre-trained model for identifying and matching faces that does not require additional training \u2014 just tag one face in several photos and the system will subsequently be able to detect and mark that face itself. In addition to human faces, the system can classify animals and also determine distorted, blurred, upside-down, and partially obscured faces. Furthermore, significant work has been done to optimize tag management, enhance the matching interface, and add new sorting and grouping modes for faces. <\/p>\n

The package includes a pre-trained model for recognizing and matching faces that does not require additional training \u2014 simply tag one face in several photographs, and the system will automatically identify and tag that face in the future. In addition to human faces, the system can classify animals and also identifies distorted, blurred, inverted, and partially obscured faces. Furthermore, considerable work has been done to optimize tag management, expand the matching interface, and introduce new sorting and grouping modes for faces.<\/p>\n

\"Release<\/a><\/noindex><\/center><\/p>\n

. Support for the HEIF image format, used by Apple and employed for distributing HDR images, has also been improved. Support for the updated XCF format, used in the GIMP 2.10 branch, has been added. 1100<\/a><\/noindex>Among other improvements:<\/p>\n

\"Release<\/a><\/noindex><\/center><\/p>\n

Among other improvements:<\/p>\n