원문정보
초록
영어
In this paper, we propose a GRNN(: Generalized Regression Neural Network) algorithms for new eyes and face recognition identification system to solve the points that need corrective action in accordance with the existing problems of facial movements gaze upon it difficult to identify the user and . Using a Kalman filter structural information elements of a face feature to determine the authenticity of the face was estimated future location using the location information of the current head and the treatment time is relatively fast horizontal and vertical elements of the face using a histogram analysis the detected. And the light obtained by configuring the infrared illuminator pupil effects in real-time detection of the pupil, the pupil tracking was - to extract the text print vector. The abstract is to be in fully-justified italicized text as it is here, below the author information.
목차
1. Introduction
2. Features Using Bayesian Statistical Methods Network
2.1. Bayesian Statistical Methods Network Theory
2.2. Face, Eyes with Eye Identification
2.3. Face Tracking Feature
2.4. Artificial Neural Networks for Face Recognition Operation
2.5. Probabilistic Graphical Models
3. Kalman Filter Algorithm Applied
3.1. Kalman Filter and Pupil Tracking Using the Moving Average Algorithm
3.2. Face Identification Preprocessing
3.3. Extraction Parameter
3.4. Gaze Correction
4. Results and Discussion
4.1. Facial Motion Classification Analysis
4.2. Re-identification Recognition Results for Adjacent Areas
5. Conclusion
References