机器学习讲座.pdfVIP

Content • Image classification and data-driven approach • K-nearest neighbor • Linear Classification Content • Image classification and data-driven approach • K-nearest neighbor • Linear Classification Image Classification: a core task omputer Vision What the computer sees in a picture? Images are represented as 3D arrays of numbers, with integers between [0, 255]. E.g. 300 x 100 x 3 (3 for 3 color channels RGB) Challenges in a Computer Vision algorithm • Deformation --Many objects of interest are not rigid bodies and can be deformed in extreme ways. • Occlusion --The objects of interest can be occluded. Sometimes only a small portion of an object (as little as few pixels) could be visible. • Background clutter --The objects of interest may blend into their environment, making them hard to identify. • Intra-class variation --The classes of interest can often be relatively broad, such as chair. There are many different types of these objects, each with their own appearance. Challenges in a Computer Vision algorithm • Viewpoint variation --A single instance of an object can be oriented in many ways with respect to the camera. • Scale variation --Visual classes often exhibit variation in their size (size in the real world, not only in terms of their extent in the image). • Illumination conditions --The effects of illumination are drastic on the pixel level. Data-driven approach 1. Collect a dataset of images and labels 2. Use Machine Learning to train an image classifier 3. Evaluate the classifier on a withheld set of test images Example dataset: CIFAR-10 •10 labels •50,000 training images •10,000 test images •images size : 32*32*3 Example dataset: CIFAR-10 Show the top 10 nearest neighbors in the training set according to pixel-w