The Imaging Whiteboard is done. I’ve added every feature I can think of, fixed every bug I know about. 3.0.5 is the final version.
So, what is the next project?
Obviously, I asked ChatGPT.
“My name is Steve Weavers; my personal web site is http://sound-analysis.com/ . I am responsible for The Musicians Workbench and The Imaging Whiteboard. I have just completed the Imaging Whiteboard. I am looking for ideas for my next project. What do you think I should tackle?”
Here is what it said:
“Hi Steve! It’s great to hear that you’ve completed the Imaging Whiteboard. As for your next project, there are many directions you could go in. Here are a few ideas to consider:
Music notation software: If you enjoy working on music-related projects, creating a software tool that makes it easier for musicians to notate their compositions could be a valuable resource for the community.
Audio editing software: Building an audio editing software could be a complex but rewarding project. You could focus on a specific niche, such as podcast editing, or create a comprehensive tool that covers all aspects of audio editing.
Virtual instrument plugin: If you have experience with music production software, developing a virtual instrument plugin could be a fun challenge. This could involve creating realistic-sounding emulations of real instruments, or coming up with entirely new and unique sounds.
Music recommendation engine: With so much music available online, it can be overwhelming for listeners to discover new artists and albums. Creating a recommendation engine that uses machine learning algorithms to suggest music based on a user’s listening history could be a valuable tool for music lovers.
Audio analysis tool: Given your background in sound analysis, creating a tool that helps users analyze audio files could be a natural fit. This could involve developing algorithms to identify key features of the audio, such as tempo, key, and tonality.
I hope these ideas give you some inspiration for your next project!”
“Those were excellent suggestions. Do you have any ideas for imaging projects?”
“Certainly, here are some ideas for imaging projects you could consider:
Image recognition software: Developing software that uses machine learning algorithms to recognize and identify objects within images could be a valuable tool for a range of industries, from healthcare to security.
Image processing software: Creating software that enhances or alters images could be a fun and creative project. You could focus on specific effects, such as color correction or noise reduction, or create a comprehensive tool that covers a range of editing capabilities.
Virtual reality experiences: With the increasing popularity of virtual reality technology, creating immersive visual experiences could be a rewarding project. This could involve creating 360-degree images or videos, or developing interactive VR games.
Image compression algorithms: Developing algorithms to compress image files without compromising their quality could be a valuable resource for a range of industries, from web development to photography.
Augmented reality applications: Building applications that overlay virtual objects or information onto real-world images could be a fun and innovative project. This could involve creating educational tools or marketing applications for businesses.
I hope these ideas provide some inspiration for your next imaging project!”
That’s brilliant! The Audio analysis tool might be a good challenge. What do you think?
Using the MNIST database of handwritten digits MNIST database – Wikipedia a convolutional neural network was trained to an accuracy of 90%. This took 50 epochs.
The trained model was loaded into the Image Classifier control and used to identify handwritten digits.
The files required to reproduce this demo are available here https://drive.google.com/file/d/1XKSYvJfAW1maNsaiV0iaWZXor0Tbtuat/view?usp=share_link