Preprocessing Images For Recognition

We have previously through the process of recognizing numbers utilizing our artificial neural network (ANN). If you haven’t gone through that post on, you can do so now. However, we ran the recognition task on images from the MNIST dataset. Even though we used the test data, it’s still cannot be considered real-world. It’s clean, well-labeled, and structured, with a lot of the noise and ambiguity removed.

Continue reading “Preprocessing Images For Recognition”

Creating A Basic Artificial Neural Network

Artificial Neural Networks (ANN) can be complex but it has become much easier to implement, thanks to frameworks and libraries, the past few years. In this post, we’ll walk through the process of creating a basic ANN. We’ll be using Python, TensorFlow, and Keras to create an ANN for recognizing handwritten digits. This is kind of the “Hello World” of AI.

Continue reading “Creating A Basic Artificial Neural Network”

Making An AI-Powered Business Card Reader

Writing a business card reader can be tedious. I first tried using Tesseract, an open-source Optical Character Recognition (OCR) engine. But besides OCR, you still need to segment the images, do optical character recognition (OCR) then identify text patterns for names, title, phones, emails, etc and extract them. Quite a lot of work if you have a big stack of business cards to go through.

But thankfully, technology and especially AI has come a long way and we can use widely available AI engines such as OpenAI’s to make the job easier… unbelievably easier. In this post, we’ll go through the whole thing from start to finish.

Continue reading “Making An AI-Powered Business Card Reader”