Docsumo is a free optical character recognition (OCR) software, also known as text recognition, which can convert text on pictures, videos or PDF files into a state that can be copied and edited. Although it is called free software, it is actually Chrome The browser extension plug-in is also very simple to use, as long as the pictures or videos seen on the webpage can be directly selected, let the artificial intelligence AI and OCR assist users to scan, analyze and capture the information they see, and convert the picture text into Plain text that can be copied or translated into other languages via Google Translate.
Docsumo itself has two grabbing modes: grabbing the selection range and grabbing the visible range. As long as you select the text range in the picture or video, it will be automatically recognized by AI, regardless of Chinese, English, Japanese or other languages. , when encountering a foreign language, it will be translated into a language familiar to the user after grabbing the content.
However, it should be noted that in order to avoid being abused, Docsumo itself has a usage limit of 15 screen captures per day, and this limit is not for profit, so Docsumo developers will not launch a paid premium version to lift this limit.
Identify text in images or videos with Docsumo
STEP 1
Open the Docsumo Free OCR Software extension page, click "Get" to download and install it to the browser.
STEP 2
Click the " Docsumo " button on the toolbar in the upper right corner, and a drop-down menu will appear, corresponding to two functions:
Capture Selected Area : Get the area selected by the user.
Capture Visible Area : Capture the visible range and make screenshots for the screen.
For example, if I first select the first " capture the area selected by the user ", a prompt will pop up on the screen.
STEP 3
Directly select the text on the video or picture with the left button of the mouse, and it will be thrown to Docsumo for text recognition and conversion into text that can be edited and copied.
After completion, the recognition result will pop up in the lower right corner, click " Copy Text " to copy the text to the clipboard and you're done! In addition, there will be a Google Translate button below, which can bring and translate the content into other languages.
STEP 4
If you click the " Capture Visible Range " button, it will take a screenshot of the browser page range, and then convert it into plain text through optical recognition through Docsumo, which is very useful in situations where the recognition range is large and there are many texts.
Three reasons why it's worth a try:
Quickly select text on pictures, videos, and PDF documents, and convert them into copyable and editable formats
Provides two different grabbing modes: Grab Selected Range and Grab Visible Range
After the content, translate it into the language familiar to the user through Google Translate
0 Comments