I have a vastly updated version of my Image Description Toolkit (IDT) available. The 3.0 release builds on the command line workflow tools I released earlier with a guided workflow creation system, analysis tools for combining descriptions, a range of performance statistics on your descriptions and tools to review content from various AI models and prompts. The IDT also includes several other tools for working with image descriptions. A results viewer allows you to browse…
15 CommentsCategory: Accessibility
I’ve been dabbling further with AI-driven development and have another app for exploration. This time it is a basic RSS Reader for Windows I’m calling RSS Quick. Get the full details and program from Release RSS Quick 1.0 – Initial Release · kellylford/rssquick or my alternative download location. The name RSS Quick reflects the intent of the app to be a simple and fast way to quickly browse RSS feeds. The program does not handle…
Leave a CommentI’ve gone back to the AI workbench, much like I did with my Image Description Toolkit, to create another app. This time it is to address the goal to make sports scores and play-by-play information easier to read and avoid some of the long-standing accessibility challenges on leading sports web sites. I’m calling this app a preview release because not everything is working yet but I have enough functionality available that I wanted to share…
Leave a CommentI’ve made another series of updates to what I’m calling the Image Description Toolkit since my last announcement. As a recap, the goal of this toolkit is to take collections of images and videos and create descriptions you can save and do this all with local AI models. Dozens of tools provide descriptions, but it is still difficult to save those descriptions for future review. With the Image Description Toolkit, you get nicely formatted HTML…
Leave a CommentSeveral months ago I announced a highly experimental set of Python scripts I called The Image Description Toolkit. Consider it a fancy name for solving my goal of wanting a way to get thousands of pictures taken from my iPhone and also for the past several decades from whatever phone I was using described and having a permanent description of the photos. I’ve made some key updates, although I’d still say this is categorized as…
Leave a Comment“I Just Want to Be Included”: How a Simple Plea Sparked an unintentional AI Accessibility Experiment
The work of editorial cartoonists and their ability to capture the essence of an idea in a picture or two must be quite the talent to have and job to hold. That phrase “a picture is worth a thousand words,” certainly can ring true. A recent experience verifying an issue in Microsoft’s Copilot app I was told had been fixed, led to that all-too-common situation in accessibility of taking one step forward and a couple…
Leave a CommentIt is good to know that AI doesn’t pull any punches. I took the latest Word Online conformance report available from aka.ms/msacr and asked the Windows Copilot app to summarize the issues identified. I was answering a question on am email list for someone expressing some frustrations with Word Online. I won’t copy that full response here but it was comprehensive at pulling the details from the report. I will share the summary. As AI…
Leave a CommentI’ve noticed a growing trend to try and make the content from some popups or tooltips directly keyboard accessible on web pages with buttons that reveal the content. This is good but what’s not so good is the naming of these buttons. In pretty much every situation where I’ve encountered this, the name starts with the phrase “tooltip.” For example on a financial web site I use when obtaining a ticker quote, the button in…
2 CommentsWhile the digital world offers an abundance of online news sources, accessibility is still a work-in-progress far too often. It is commonplace to spend more time navigating to content than reading that content when using screen reading technology. Poor heading structure, Ads lacking accessibility that are mixed in with the news story, multimedia that plays silently and grabs focus and much more take away from the reading experience. A public library card and a resource…
Leave a CommentAs a matter of choice, not necessity, I try from time to time to use the various speech and voice input systems in operating systems. My ideal scenario is still to be able to use the computer by voice entirely as well as running a screen meter. I’ve not found a reliable solution as of yet that meets my needs completely. I know there are combinations of solutions that have made great strides in this…
Leave a Comment