From the course: Generative AI Tools for Productivity and Research
Unlock the full course today
Join today to access over 23,200 courses taught by industry experts.
Extract text from an image with Google Gemini
From the course: Generative AI Tools for Productivity and Research
Extract text from an image with Google Gemini
- [Instructor] Gemini is truly multimodal. It can work with different data types. For example, it can extract text data from images, upload image_4 from the provided images. This image is a process flow from one of my projects. Now, let's write a prompt, "extract the text component from this image." Okay, so Gemini was successfully able to extract the text component from these images. The first part is ideation. It has sub topics like Topic Selection, Topic Level, Target Audience, Vocabulary Development, and Scripting. That aligns with exactly what's in the image. And the same for production, you can see Video Recording, Video Editing, and Subtitling. Well, subtitling is originally under production in the original image. Let's see if all the drafts got it right. So this is Draft 2, okay, and also Draft 3. In this particular instance though, Gemini made an attempt to extract as much as possible as it can see. Subtitling was placed under production in the original image. In this…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
Working with Google Gemini4m 19s
-
(Locked)
Writing with Google Gemini8m 10s
-
(Locked)
Data exploration with Google Gemini3m 40s
-
(Locked)
Image description with Google Gemini3m 49s
-
(Locked)
Extract text from an image with Google Gemini3m 11s
-
(Locked)
Working with Microsoft Copilot in Edge1m 21s
-
(Locked)
Image generation with Microsoft Copilot Designer3m 59s
-
(Locked)
Design creation with Microsoft Copilot Designer3m 20s
-
(Locked)
Create a simple brand kit with Microsoft Copilot Designer6m 53s
-
-