Tutorials

In this tutorial, you will learn how to OCR video streams. This lesson is part 3 of a 4-part series on Optical Character Recognition with Python: Multi-Column Table OCR OpenCV Fast Fourier Transform (FFT) for Blur Detection in Images and…

In this tutorial, you will: Discover a technique for associating rows and columns together Learn how to detect tables of text/data in an image Extract the detected table from an image OCR the text in the table Apply hierarchical agglomerative…

In this tutorial, you will learn how to create U-Net, an image segmentation model in TensorFlow 2 / Keras. We will first present a brief introduction on image segmentation, U-Net architecture, and then walk through the code implementation with a…

In this tutorial, you will learn to use image super resolution. This lesson is part of a 3-part series on Super Resolution: OpenCV Super Resolution with Deep Learning Image Super Resolution (this tutorial) Pixel Shuffle Super Resolution with TensorFlow, Keras,…

In this post, we implement two GAN variants: Wasserstein GAN (WGAN) and Wasserstein GAN with Gradient Penalty (WGAN-GP), to address the training instability discussed in my previous post, GAN Training Challenges: DCGAN for Color Images. We will train the WGAN…

An essential component of any OCR system is image preprocessing — the higher the quality input image you present to the OCR engine, the better your OCR output will be. To be successful in OCR, you need to review arguably…

In this tutorial, you will learn the concept behind Fully Convolutional Networks (FCNs) for segmentation. In addition, we will see how we can use Torch Hub to import a pre-trained FCN model and use it in our projects to get…

In the previous part of this series, we discussed some state-of-the-art object detection models; YOLOv5 and SSD. In today’s tutorial, we will discuss MiDaS, an ingenious attempt to aid the depth estimation of images. With this tutorial, we will create…

In this tutorial, you will learn the architectural details of Progressive GAN, which enable it to generate high-resolution images. In addition, we will see how we can use Torch Hub to import a pre-trained PGAN model and use it in…