Neural network-based symbol recognition using a few labeled samples

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.

Figure optionsDownload high-quality image (140 K)Download as PowerPoint slideHighlights
► A protocol suitable for training neural network-based symbol recognizers in novel sketch domains, where it is difficult to employ other existing training approaches.
► In the scenario we target, the initial number of labeled samples is limited, no labeled sample synthesizer is available and no relevant domain with similar symbols exists for transfer learning.
► Our approach reduces the need for labeled training samples and reduces the time or efforts needed to collect or label such samples.