 |
Technical Program
Paper Detail
| Paper: | WA-P8.7 |
| Session: | Image/Video Processing Applications: Object Detection and Recognition |
| Time: | Wednesday, October 11, 09:40 - 12:20 |
| Presentation: |
Poster
|
| Title: |
RECOGNITION USING RAPID CLASSIFICATION TREE |
| Authors: |
Keith Haynes; United States Military Academy | | | | | Xiuwen Liu; Florida State University | | | | | Washington Mio; Florida State University | | |
| Abstract: |
This paper proposes a method to achieve object classification with high throughput and accuracy using a rapid classifcation tree by decoupling the training and test stages. During the training stage, we learn optimal discriminatory features from the training set and then train a classifier with high accuracy. Then we create a classifcation tree, where each node uses a lookup table to store the solutions, resulting high throughput at the test stage. To make the lookup tables feasible for applications, we learn a projection matrix through stochastic optimization. We illustrate the effectiveness of the proposed method using several datasets; our results show the proposed method achieves often several orders of magnitudes of improvement in throughput while maintaining a similar accuracy. |
|
