Name
Abstract | ||
|---|---|---|
We propose a discriminatively-trained convolutional neural network for gender classification of pedestrians. Convolutional neural networks are hierarchical, multilayered neural networks which integrate feature extraction and classification in a single framework. Using a relatively straightforward architecture and minimal preprocessing of the images, we achieved 80.4% accuracy on a dataset containing full body images of pedestrians in both front and rear views. The performance is comparable to the state-of-the-art obtained by previous methods without relying on using hand-engineered feature extractors. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1007/978-3-642-39065-4_67 | ISNN (1) |
Keywords | Field | DocType |
gender classification,convolutional neural network,rear view,feature extraction,multilayered neural network,minimal preprocessing,full body image,previous method,pedestrian gender recognition,hand-engineered feature extractor,discriminatively-trained convolutional neural network | Neocognitron,Pedestrian,Convolutional neural network,Computer science,Time delay neural network,Artificial intelligence,Deep learning,Artificial neural network,Pattern recognition,Speech recognition,Feature extraction,Preprocessor,Machine learning | Conference |
Citations | PageRank | References |
4 | 0.42 | 14 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Choon Boon Ng | 1 | 79 | 3.64 |
| Yong Haur Tay | 2 | 225 | 20.14 |
| Bok-Min Goi | 3 | 498 | 62.02 |