Using AI to Analyze Chart Images

/ / No Comments
I’ve done a few posts where I’ve asked GenAI services to analyze and summarize data. Most recently, I blogged about Chrome’s built-in AI APIs and summarizing raw data into simple English. In each case where I’ve done work like this, I’ve had access to the raw data of what I want the API to analyze. But what if you don’t? What if all you have is a simple chart image? I did some testing with this and here’s what I found. My Source Data For my source data, I created a set of charts using Highcharts. This isn’t my preferred front-end charting library, but I noticed their demos had (usually) a quick CSV export. That made it easy to get both a sample... more →
Posted in: JavaScript Tagged with: , , ,

Creating Images with Generative AI via Conversation

/ / No Comments
Last week, I blogged about updates to Google’s Gemini APIs in regards to image generation. That post detailed how there are now two models for generating images with the experimental Gemini Flash model having a nice free tier. One of the interesting features of the API is the ability to edit existing images, in other words, pass an image to Gemini and via a prompt, have Gemini update it. I thought it would be kind of fun to see if I could build a ‘chat’ interface for this model, one where you could simply talk to Gemini and have it work on your image along with you. Now to be clear, this is no different than what you can do now at the Gemini website, but I figured it would give... more →
Posted in: JavaScript Tagged with: , , ,

Geolocating a Folder of Images with Python

/ / No Comments
I’m not sure how useful this will be, but as I recently built it in another language (I plan on blogging that soon as well), I thought I’d take a stab at building it in Python. Given a folder of images, can I use Python to grab the Exif information and then using that, figure out where the photos were taken using a reverse geocoding service? Here’s what I built. First – Get the Images Ok, the first step is simple, just get a list of images from a directory: INPUT = "./sources" files = os.listdir(INPUT) for file in files: print(file) Woot! I’m a Python Master! Get the Exif info For the next step, I knew I needed to get the Exif info. For that I used... more →
Posted in: JavaScript Tagged with: , , ,

Easy way to upload, transform and deliver files and images (Sponsored)

/ / No Comments
Managing media is a really difficult task if you try to do all of it yourself, especially if the media comes from other sources. The file can be submitted in any state and size, but what if you need something really specific? You can code it all yourself or you can use an awesome service like Filestack, a utility to upload, transform, and deliver that media in the most optimal style imaginable! The Setup The first step in the Filestack journey is signing up for free. You’ll get at 21 day free trial and can cancel at any time. Once signed up, you’ll have full access to the Filestack libraries of code. You’ll also want to spend time catching up on the Filestack documentation,... more →
Posted in: JavaScript Tagged with: , , , , , ,

Generative Images with Gemini (New Updates)

/ / No Comments
Back in January of this year, I wrote up my experience testing out Google’s Imagen 3 APIs to generate dynamic images. A few days ago, Google updated their support with new experimental support in Flash. I’ve been playing with this the last few days and have some code and samples to share with you, but before that, what exactly changed? Gemini and Imagen 3 There are now two different models, and different APIs, to generate images with Google’s AI platform. The new one is Gemini 2.0 Flash Experimental and the previous one (the one covered in my blog post) is Imagen 3. Of course the next question is, why two, and what do you pick? The docs do a great job of explaining the differences,... more →
Posted in: JavaScript Tagged with: , , ,

Generative AI Images with Gemini and Imagen – an Introduction

/ / No Comments
I’ve been waiting for this to launch for a few days now, and while technically this isn’t quite yet available in Gemini, only Vertex, it should be testable in Gemini in the very short term. You can now use Google’s APIs to generate really high quality images via their Imagen 3 technology. I’ve got a few blog posts planned that will demonstrate these features (and from what I’ve been told, even more powerful stuff is coming), but I thought I’d start off today with a simple short example. To begin, and remember this may not available just yet, take a look at the docs, Imagen 3 in the Gemini API. First, let’s consider the sample code, that I’m going... more →
Posted in: JavaScript Tagged with: , , , ,

The First Images from EUMETSAT MTG-I1

/ / No Comments
The first high quality image from Europe’s newest weather satellite has been released. The European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT) operates a fleet of satellites with which it monitors weather, climate, and the environment from space. EUMETSAT’s newest satellite, Meteosat Third Generation – Imager 1 (Meteosat-12) was launched in December 2022 and is Maps Mania… more →
Posted in: Interactive Maps Tagged with: , , , ,

How to Create a Diff of Two Images

/ / No Comments
When I was a child, I loved looking for Waldo in the “Where’s Waldo?” book series. These days I’m a sucker for TMZ’s “What’s the Big Frigin Difference” images, where TMZ slightly changes an image and you have to spot the differences between the two. That got me to thinking — how easily could I automate diff’ing two images? This StackOverflow post was gold. To create a diff of two similar images, we’ll use ImageMagick’s convert command line utility with a large host of configurations: convert '(' image1.png -flatten -grayscale Rec709Luminance ')' '(' image2.png -flatten -grayscale Rec709Luminance ')' ... more →
Posted in: JavaScript Tagged with: , ,
1 2