Performance Comparison of Several Pre-Processing Methods in a Hand Gesture Recognition System based on Nearest Neighbor for Different Background Conditions  

Oleh:

Lionnie, Regina ; Timotius, Ivanna K. ; Setyawan, Iwan

Jenis: Article from Journal - ilmiah nasional - terakreditasi DIKTI
Dalam koleksi: Journal of ICT Research and Applications vol. 6C no. 3 (2012), page 183-194.
Topik: binary image processing; desaturation; edge detection; hand gesture recognition; histogram equalization; low-pass filtering; nearest neighbor.
Fulltext: C11175.pdf (168.16KB)

Isi artikel

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 of several 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 possible classes. 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%.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali