Project Naptha

Description

The Naptha project automatically applies the most advanced computer vision algorithms on every image that you see while browsing the Internet. The result is a seamless and intuitive perception in which you can select, copy and paste, and even edit and translate the text previously captured in the image.

Words on the Internet exist in two forms: there is the text of articles, letters, tweets, chats and blogs that can be copied, searched, translated, edited and selected, and then text copied onto images found in comic books, scanning documents, photographs, posters , charts, diagrams, screenshots and memes. Interaction with Naptha with this second type text has always been the second class, the only way to search or copy sentences from an image would be to do what the ancient monks did by manually rewriting the regions of interest.

You can watch how moving the cursor over a block of words changes it to a small ray of light. You can drag a few lines and see how the translucent blue box highlights the text, helping you keep track of where you are and what you read. Press Ctrl + C to copy the text, where you can paste it into the search bar, Word document, email or chat window. Right-click and you can erase the words from the image, edit the words, or even translate them into another language.

Security and privacy: Project Naptha handles OCR and text detection locally on your computer. When text is highlighted, the extension checks the remote server to determine if there is a public, high-quality transcription using the cryptographic hash of the URL (it does not contain cookies, user tokens or any identifying information, and the server cannot store access logs)