Pengenalan Citra Wajah Menggunakan Metode Alihragam Gelombang-Singkat dan Metrika Lq  

Oleh:

Wijaya, I Gede Pasek Suta ; Suksmadana, I Made Budi

Jenis: Article from Journal - ilmiah nasional
Dalam koleksi: Jurnal Teknologi Industri vol. 8 no. 3 (Jul. 2004), page 197-206.
Topik: Face Image; Recognition; Metrics; Wavelet Transforms; Library Image; Querv Image

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: JJ83.5 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Image recognition is a mechanism to re-recognize an image that is not recognized by eves, using certain method. This research was ‘Face Image Recognition Using Wavelet Transforms and Lq Metrics Method”. The face recognition algorithm was extracting an image for finding image signature by choosing a little wavelet transforms coefficients that have the biggest magnitude value. Lq metrics be used to select the best match (likeness) to original images in the collection. The test were carried out in three kind of wavelets viz coiflet 6, Dauhechies 8, dan Symlet 8. YJQ color space. and 25 query images and each query image has 30 samples. Query success rates were determined by using one percent threshold value time c si:e of databases. The result shows that the method give good performance, which the average of success role over 90% and need a little lime query The Daubechies-8 can be considered the best waveletfor.face image recognition, which the average of success rate is 98,17%. With respect to the elapsed query lime, of about 0,776 second, the above method is sufficiently efficient for the database size of 5000 records; each additional 500 records the increase in computation time was ± 0.006 second.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali