Learning methods for generic object recognition with invariance to pose and lighting
Yann LeCun, Fu Jie Huang, Léon Bottou · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2004
We assess the applicability of several popular learning methods for the problem of recognizing generic visual categories with invariance to pose, lighting, and surrounding clutter. A large dataset comprising stereo image pairs of 50 uniform-colored toys under 36 azimuths, 9 elevations, and 6 lighting conditions was collected (for a total of 194,400 individual 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 machines, and convolutional networks, operating on raw pixels 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 16/7% 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.
Cited by 1,299 works. doi:10.1109/cvpr.2004.1315150
Authors
References
- Gradient-based learning applied to document recognition
- Rapid object detection using a boosted cascade of simple features
- Neural network-based face detection
- Training support vector machines: an application to face detection
- Local grayvalue invariants for image retrieval
- Visual learning and recognition of 3-d objects from appearance
- A statistical method for 3D object detection applied to faces and cars
- Original approach for the localisation of objects in images
- Probabilistic visual learning for object detection
- GradientBased Learning Applied to Document Recognition