From my previous post (http://dangminhthang.com/computer-vision/character-recognition-using-alexnet/) some wonder what we can do with the model after we train it. In this post I will share how we can use the pre-trained model in a case study. Specifically we will use image processing and deep learning techniques for characters segmentation and recognition in vehicle license plate. Given… Read More »
When AlexNet (paper) won the ImageNet Large Scale Visual Recognition Challenge in 2012, it sent a shock wave across the computer vision research community. Even though the concept of neural network has been available for many decades, it is AlexNet that made deep convolutional neural network (CNN) a highly recognised solution that solves many computer… Read More »
You Only Look Once (YOLO) model is one of the most efficient and fastest object detection algorithms. There are currently three state-of-the-art models for detecting objects: You Only Look Once – YOLO (paper) R-CNN and its variants Fast R-CNN, Faster R-CNN, etc. (paper) Single Shot Detector – SSD (paper) This post will show you how… Read More »
This is the final article in a series of experiments with deep learning for image recognition. In the first one, it is a simple deep learning model with two hidden layers and an output layer. In the second one, it uses a convolutional neural network which follows LeNet-5 architecture. And in this one another convolutional… Read More »
This is a follow up of my previous post, Deep learning for sign language recoginition. This is another exercise resulted from Coursera’s Convolutional Neural Networks. This model differs from the previous one in that this one uses Convolutional Neural Network. The Dataset The dataset is obtained from Kaggle (https://www.kaggle.com/datamunge/sign-language-mnist). The training data has 27,455 examples… Read More »
I’m taking Coursera’s Deep Learning Specialization (https://www.coursera.org/specializations/deep-learning) to solidify my deep learning knowledge. I strongly believe the best way to learn something is to put it into practice. So after the course Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization, I did my own exercise to sharpen my skills. In the course, the programming… Read More »