The Application of Modified Least Trimmed Squares with Genetic Algorithms Method in Face Recognition
| Autor: | Hishamuddin Hashim, Nur Azimah Abdul Rahim, Ismail Musirin, Nor Azura Md Ghani, Norazan Mohamed |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Control and Optimization
Pixel Computer Networks and Communications business.industry Computer science Monte Carlo method Pattern recognition Least trimmed squares Context (language use) Salt-and-pepper noise Facial recognition system Hardware and Architecture Face (geometry) Signal Processing Linear regression Genetic algorithm Artificial intelligence Electrical and Electronic Engineering business Information Systems |
| Zdroj: | Indonesian Journal of Electrical Engineering and Computer Science. 8:154 |
| ISSN: | 2502-4760 2502-4752 |
| DOI: | 10.11591/ijeecs.v8.i1.pp154-158 |
| Popis: | Severely occluded face images are the main problem in low performance of face recognition algorithms. In this paper, we apply a new algorithm, a modified version of the least trimmed squares (LTS) with a genetic algorithms introduce by [1]. We focused on the application of modified LTS with genetic algorithm method for face image recognition. This algorithm uses genetic algorithms to construct a basic subset rather than selecting the basic subset randomly. The modification in this method lessens the number of trials to obtain the minimum of the LTS objective function. This method was then applied to two benchmark datasets with clean and occluded query images. The performance of this method was measured by recognition rates. The AT&T dataset and Yale Dataset with different image pixel sizes were used to assess the method in performing face recognition. The query images were contaminated with salt and pepper noise. The modified LTS with GAs method is applied in face recognition framework by using the contaminated images as query image in the context of linear regression. By the end of this study, we can determine this either this method can perform well in dealing with occluded images or vice versa. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|