![]() Obviously, there is a lot of room for improvement in multiple aspects! If you like this project and you feel motivated to contribute, let me know. Inspired by this and motivated by my own idea of personal face recognition, I started to work on this project. The latter provides a nice and clean way for face recognition using the command line but I was looking for a more complete solution from initial training till continous update of my photo database. After some literature research, I found various sources such as dlib, face_recognition or opencv providing state of the art implementations. Google Photos and the recent advances in face detection and recognition inspired me. Obviously, the well working solutions from e.g. Furthermore, I wanted to have something easier to control (privacy, keep my own folder structure, do not modify my photos unless I want it to, etc.) than the various online solutions around. I was looking for a solution to organize my personal photo library and I also wanted to play with face detection algorithms. You can use this to clean your images before tagging them with this (or any other) software. I will change this soon.Īdobe Bridge is a very nice tool to edit metadata. Thus, if you have anything stored there already, it will be lost. This will first extract all metadata to a json file per image, second it will edit the "Keywords" data field and the "ImageDescription" data field, and third it will write the modified metadata to the images.ĪTTENTION: In the current version, the two data fields will be overwritten. In order to export the detected faces to the images' metadata, use export.py -method 1. Obviously, I tried to reduce the manual work to a minimum but if you want to have a clean face database it will be inevitable. However, please be careful and I cannot guarantee for anything :)įurthermore, it is always a good idea to backup your data and images, especially the face database (see below), after and during long manual corrections or annotations. If you use the EXIF data export function you will obviously modify the EXIF data of your images. I wanted to make sure that the initial folder structure etc. ![]() In theory, none of your images will be moved or deleted. If you want to try it, I strongly recommend to play with the provided example first before you use it on your own images. This project builds on modern face detection and recognition algorithms to provide you an easy to use software to organize your personal photo gallery by people without uploading everything to the cloud. Documentation is not up-to-date (wip)! facesįace detection and recognition software to organize your personal photo gallery.ĭRAFT: work in progress, testing in progress, documentation in progress Introduction
0 Comments
Leave a Reply. |