AI summary

This paper introduces a study on generic object recognition with invariance to pose and lighting, utilizing the NORB dataset, a large stereo image dataset. Nearest Neighbor methods, SVM, and Convolutional Networks were evaluated, achieving a test error rate of 7% using Convolutional Networks.

Abstract

We assess the applicability of several popular learning methods for the problem of recognizing generic visual cat- egories with invariance to pose, lighting, and surrounding clutter. A large dataset comprising stereo image pairs of 50 uniform-colored toys under 36 angles, 9 azimuths, and 6 lighting conditions was collected (for a total of 194,400 in- dividual images). The objects were 10 instances of 5 generic categories: four-legged animals, human figures, airplanes, trucks, and cars. Five instances of each category were used for training, and the other five for testing. Low-resolution grayscale images of the objects with various amounts of variability and surrounding clutter were used for training and testing. Nearest Neighbor methods, Support Vector Ma- chines, and Convolutional Networks, operating on raw pix- els or on PCA-derived features were tested. Test error rates for unseen object instances placed on uniform backgrounds were around 13% for SVM and 7% for Convolutional Nets. On a segmentation/recognition task with highly cluttered images, SVM proved impractical, while Convolutional nets yielded 14% error. A real-time version of the system was implemented that can detect and classify objects in natural scenes at around 10 frames per second.