Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Training products of experts by minimizing contrastive divergence
Neural Computation
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Sketched Symbol Recognition using Zernike Moments
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Convolutional Face Finder: A Neural Architecture for Fast and Robust Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Comparing Natural and Synthetic Training Data for Off-Line Cursive Handwriting Recognition
IWFHR '04 Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition
HLT '01 Proceedings of the first international conference on Human language technology research
Data Driven Image Models through Continuous Joint Alignment
IEEE Transactions on Pattern Analysis and Machine Intelligence
One-Shot Learning of Object Categories
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICML '06 Proceedings of the 23rd international conference on Machine learning
A fast learning algorithm for deep belief nets
Neural Computation
A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data
The Journal of Machine Learning Research
On solving the face recognition problem with one training sample per subject
Pattern Recognition
Self-taught learning: transfer learning from unlabeled data
Proceedings of the 24th international conference on Machine learning
POP: Patchwork of Parts Models for Object Recognition
International Journal of Computer Vision
Sketch recognition in interspersed drawings using time-based graphical models
Computers and Graphics
Technical Section: Sketch-based modeling: A survey
Computers and Graphics
Optimization of a training set for more robust face detection
Pattern Recognition
An image-based, trainable symbol recognizer for hand-drawn sketches
Computers and Graphics
Combining geometry and domain knowledge to interpret hand-drawn diagrams
Computers and Graphics
Learning Deep Architectures for AI
Foundations and Trends® in Machine Learning
A visual approach to sketched symbol recognition
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Deep, big, simple neural nets for handwritten digit recognition
Neural Computation
Hi-index | 0.00 |
The recognition of pen-based visual patterns such as sketched symbols is amenable to supervised machine learning models such as neural networks. However, a sizable, labeled training corpus is often required to learn the high variations of freehand sketches. To circumvent the costs associated with creating a large training corpus, improve the recognition accuracy with only a limited amount of training samples and accelerate the development of sketch recognition system for novel sketch domains, we present a neural network training protocol that consists of three steps. First, a large pool of unlabeled, synthetic samples are generated from a small set of existing, labeled training samples. Then, a Deep Belief Network (DBN) is pre-trained with those synthetic, unlabeled samples. Finally, the pre-trained DBN is fine-tuned using the limited amount of labeled samples for classification. The training protocol is evaluated against supervised baseline approaches such as the nearest neighbor classifier and the neural network classifier. The benchmark data sets used are partitioned such that there are only a few labeled samples for training, yet a large number of labeled test cases featuring rich variations. Results suggest that our training protocol leads to a significant error reduction compared to the baseline approaches.