Performance Comparison of Several Pre-Processing Methods in a Hand Gesture Recognition System based on Nearest Neighbor for Different Background Conditions
| Main Authors: | Lionnie, Regina; Department of Electronic Engineering, Satya Wacana Christian University, Jalan Diponegoro 52-60, Salatiga, 50711, Indonesia, Timotius, Ivanna K.; Department of Electronic Engineering, Satya Wacana Christian University, Jalan Diponegoro 52-60, Salatiga, 50711, Indonesia, Setyawan, Iwan; Department of Electronic Engineering, Satya Wacana Christian University, Jalan Diponegoro 52-60, Salatiga, 50711, Indonesia |
|---|---|
| Format: | Article info application/pdf eJournal |
| Bahasa: | eng |
| Terbitan: |
ITB Journal Publisher, LPPM ITB
, 2013
|
| Subjects: | |
| Online Access: |
http://journals.itb.ac.id/index.php/jictra/article/view/228 http://journals.itb.ac.id/index.php/jictra/article/view/228/222 |
Daftar Isi:
- This paper presents a performance analysis and comparison of several pre-processing methods used in a hand gesture recognition system. The preprocessing methods are based on the combinations ofseveral image processing operations, namely edge detection, low pass filtering, histogram equalization, thresholding and desaturation. The hand gesture recognition system is designed to classify an input image into one of six possibleclasses. The input images are taken with various background conditions. Our experiments showed that the best result is achieved when the pre-processing method consists of only a desaturation operation, achieving a classification accuracy of up to 83.15%.