Deep Learning for Computer Vision with MATLAB and cuDNN

Shashank Prasanna, product marketing manager at MathWorks, shares how you can use MATLAB to develop an object recognition system using deep convolutional neural networks and GPUs.

Deep Convolutional Neural Networks (CNNs), a specific type of deep learning algorithm, address the gaps in traditional machine learning techniques, changing the way we solve these problems. CNNs not only perform classification, but they can also learn to extract features directly from raw images, eliminating the need for manual feature extraction. For computer vision applications you often need more than just image classification; you need state-of-the-art computer vision techniques for object detection, a bit of domain expertise, and the know-how to set up and use GPUs efficiently. In Shashank’s recent post, he uses an object recognition example to illustrate how easy it is to use MATLAB for deep learning, even if you don’t have extensive knowledge of computer vision or GPU programming.

Pet detection and recognition system
Pet detection and recognition system

In his example, he demonstrates the ability to detect a pet in a video and correctly label the pet as a cat or a dog – for this, he used a Tesla K40 GPU, MATLAB, and MathWorks’ Parallel Computing Toolbox, Computer Vision System Toolbox and Statistics and Machine Learning Toolbox.

Read the entire blog on Parallel Forall >>