Genetic algorithm based defect identification system

Face Identification System using a fast genetic algorithm computation (FGA) is presented. FGA is used to compute and search the face in a database. The objective of the work is to make a face identification system which can recognize face from a given image or any other image streaming system like webcam. The system also has to detect the face from a system accurately in order to identify the face accurately. The image can be captured either from a proposed webcam or a captured JPEG or PNG image or any other data source. The system needs training with adequate sample images to perform this operation. Training the generic system plays a vital role in identifying the face in an image. A tolerance is identified as a limit to the genetic algorithm which acts as a terminal condition to the evolution. A unique encoding is used which stores the facial features of a human face into numeric string which can be stored and searched with much ease thereby decreasing the search and computational time. Template matching technique is applied to identify the face in a big picture. Generation of an Eigen face is obtained by the stage a mathematical practice called PCA. Eigen Features is also computed such that the measurement of facial metrics is done using nodal point measurement.

Download Full-text

Optimization of Bayesian Filters and Hammerstein-Wiener Models for EMG-Force Signals Using Genetic Algorithm

ASME 2009 Dynamic Systems and Control Conference, Volume 1 ◽

10.1115/dscc2009-2658 ◽

2009 ◽

Cited By ~ 1

Author(s):

Anish Sebastian ◽

Parmod Kumar ◽

Madhavi Anugolu ◽

Marco P. Schoen ◽

Alex Urfer ◽

...

Keyword(s):

Genetic Algorithm ◽

System Identification ◽

Optimal Parameter ◽

Nonlinear Models ◽

Human Hand ◽

Identification System ◽

Force Estimation ◽

Emg Signal ◽

Wiener Models ◽

Bayesian Filters

Processing electromyographic (EMG) signals for force estimation has many unknown variables that can influence the outcome or interpretation of the recorded EMG signal significantly. An array of filtering methods have been proposed over the past few years with the objective to classify motion for use in prosthetic hands. In this paper, we explore the optimal parameter settings of a set of Bayesian based EMG filters with the objective to use the filtered EMG data for system identification. System identification is utilized to establish a relationship between the measured EMG data and the generated force developed by fingers in a human hand. The proposed system identification is based on nonlinear Hammerstein-Wiener models. Optimization is also applied to find the optimal parameter settings for these nonlinear models. Genetic Algorithm (GA) is used to conduct the optimization for both, the optimal parameter settings for the Bayesian filters as well as the Hammerstein-Wiener model. The experimental results and optimization analysis indicate that the optimization can yield significant improvement in data accuracy and interpretation.

Download Full-text

Genetic Programming for Letters Identification Based on Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.734.642 ◽

2015 ◽

Vol 734 ◽

pp. 642-645

Author(s):

Yan Hui Liu ◽

Zhi Peng Wang

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Neural Networks ◽

Genetic Programming ◽

Network Structure ◽

High Accuracy ◽

Identification System ◽

Neural Network Structure ◽

Hidden Layer

According to the problem that the letters identification is not high accuracy using neural networks, in this paper, an optimal neural network structure is designed based on genetic algorithm to optimize the number of hidden layer. The English letters can be identified by optimal neural network. The results obtained in the genetic programming optimizations are very satisfactory. Experiments show that the identification system has higher accuracy and achieved good ideal letters identification effect.

Download Full-text