Start here if...
you’re new to computer vision. This project is the perfect introduction to techniques like neural networks using a classic dataset including pre-extracted features.
MNIST ("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.
In this TensorFlow project, our goal is to correctly identify digits from a dataset of tens of thousands of handwritten images. We encourage you to experiment with different algorithms to learn first-hand what works well and how techniques compare.
Computer vision fundamentals including simple neural networks
Each image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between 0 and 255, inclusive.
The training data set, (train.csv), has 785 columns. The first column, called "label", is the digit that was drawn by the user. The rest of the columns contain the pixel-values of the associated image.
Each pixel column in the training set has a name like pixelx, where x is an integer between 0 and 783, inclusive. To locate this pixel on the image, suppose that we have decomposed as , where and are integers between 0 and 27, inclusive. Then pixelx is located on row i and column j of a 28 x 28 matrix, (indexing by zero).
More details about the dataset, including algorithms that have been tried on it and their levels of success, can be found at http://yann.lecun.com/exdb/mnist/index.html. The dataset is made available under a Creative Commons Attribution-Share Alike 3.0 license.