Main Content

Deep Learning, Semantic Segmentation, and Detection

Deep learning and convolutional networks, semantic image segmentation, object detection, recognition, ground truth labeling, bag of features, template matching, and background estimation

Computer Vision Toolbox™ supports several approaches for image classification, object detection, and recognition, including:

  • Deep learning and Convolutional neural networks (CNNs)

  • Bag of features

  • Template matching

  • Blob analysis

  • Viola-Jones algorithm

  • Interactive apps for ground truth labeling

A CNN is a popular deep learning architecture that automatically learns useful feature representations directly from image data. Bag of features encodes image features into a compact representation suitable for image classification and image retrieval. Template matching uses a small image, or template, to find matching regions in a larger image. Blob analysis uses segmentation and blob properties to identify objects of interest. The Viola-Jones algorithm uses Haar-like features and a cascade of classifiers to identify objects, including faces, noses, and eyes. You can train this classifier to recognize other objects.

Featured Examples