|NORB: the NYU Object Recognition Benchmark|
for more details and for downloading the dataset.
This dataset is intended for experiments in 3D generic object recognition
independently of the pose, illumination, and backgroun clutter.
It contains thousands of images of 50 toys belonging to 5 generic
categories: four-legged animals, human figures, airplanes, trucks, and
cars. The objects were imaged by two cameras under 6 lighting
conditions, 9 elevations (30 to 70 degrees every 5 degrees), and 18
azimuths (0 to 340 every 20 degrees).
The dataset is composed of 12 sets of 29,160 images (10 sets for
training, 2 sets for testing). Each set is generated by randomly
perturbing the size, in-plane rotation, position, contrast, and
brightness of original object images and placing them on random
The training sets contain 5 instances of each category
(instances 4, 6, 7, 8 and 9), and the test sets contain
the remaining 5 instances (instances 0, 1, 2, 3, and 5).
|The MNIST Handwritten Digit Dataset|
Click here for
details, and to download the MNIST dataset.
The MNIST database of handwritten digits has a training set of 60,000
examples, and a test set of 10,000 examples. It is a subset of a
larger set available from NIST. The digits have been size-normalized
and centered in a fixed-size image.
It is a good database for people who want to try learning techniques
and pattern recognition methods on real-world data while spending minimal
efforts on preprocessing and formatting.