Face recognition of color images using artificial neural networks.

机译：使用人工神经网络对彩色图像进行人脸识别。

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Image classification is a quantitative method that can be used to classify or identify objects or patterns on the basis of their multi-spectral values. Artificial Neural Networks offer powerful solutions for pattern recognition. The Image classification can be achieved using neural networks because of its highly nonlinear properties. The objective of this thesis work was to create and train an artificial neural network, which will detect the presence or absence of human face in color images with neural networks using two methods. The networks discussed are based on (1) YIQ color space and (2) XYZ color space. The two networks were trained using the same set of images by using the Levenberg-Marquardt Algorithm. The computed results for the training set images and test set images were presented. The results show that with a success rate of 97.57% (282 out of 289 images) and 97.27% (281 out of 289 images) for XYZ and YIQ approach respectively, the face detection process works well. The results of this thesis work can be used for important applications such as automated security systems, indexing and retrieval of video images, and for face detection in crowded images.

机译：图像分类是一种定量方法，可用于基于对象或图案的多光谱值对其进行分类或识别。人工神经网络为模式识别提供了强大的解决方案。由于其高度非线性的特性，可以使用神经网络来实现图像分类。本文工作的目的是创建和训练一个人工神经网络，该网络将使用两种方法通过神经网络检测彩色图像中人脸的存在与否。讨论的网络基于（1）YIQ颜色空间和（2）XYZ颜色空间。通过使用Levenberg-Marquardt算法，使用相同的图像集训练这两个网络。给出了训练集图像和测试集图像的计算结果。结果表明，人脸检测过程在XYZ和YIQ方法中的成功率分别为97.57％（289张图像中的282张）和97.27％（289张图像中的281张）。本文工作的结果可用于重要的应用，例如自动安全系统，视频图像的索引和检索以及拥挤图像中的人脸检测。

著录项

作者
Kalwakuntla, Rajesh Reddy.;
展开▼
作者单位

Texas A&M University - Kingsville.;

展开▼
授予单位 Texas A&M University - Kingsville.;
学科 Engineering Electronics and Electrical.
学位 M.S.
年度 2005
页码 84 p.
总页数 84
原文格式 PDF
正文语种 eng
中图分类无线电电子学、电信技术;
关键词

相似文献

外文文献
中文文献
专利

1. Human-visual-perception-like intensity recognition for color rust images based on artificial neural network [J] . Shen Heng-Kuang, Chen Po-Han, Chang Luh-Maan Automation in construction . 2018,第JUNa期

机译：基于人工神经网络的彩色锈迹图像人眼感知强度识别
2. Automated multi-level pathology identification techniques for abnormal retinal images using artificial neural networks. [J] . Anitha J, Vijila CK, Selvakumar AI, British journal of ophthalmology . 2012,第2期

机译：使用人工神经网络对异常视网膜图像进行自动化的多级病理学识别技术。
3. Identification of eroded zones with digital images using artificial neural networks. [J] . Trueba Espinosa A, Oropeza Mota J L, Ortiz Solorio C A, Agrociencia . 2004,第6期

机译：使用人工神经网络通过数字图像识别侵蚀区域。
4. Paper currency recognition for color images based on Artificial Neural Network [C] . Ch. Ratna Jyothi, Y. K. SundaraKrishna, V. SrinivasaRao International Conference on Electrical, Electronics, and Optimization Techniques . 2016

机译：基于人工神经网络的彩色图像纸币识别
5. Artificial neural networks and model-based recognition of three-dimensional objects from two-dimensional images. [D] . Chao, Chih-ho. 1994

机译：人工神经网络和基于模型的二维图像中三维对象的识别。
6. Pattern recognition and classification of images of biological macromolecules using artificial neural networks. [O] . R Marabini, J M Carazo 1994

机译：使用人工神经网络对生物大分子图像进行模式识别和分类。
7. Pattern recognition and classification of images of biological macromolecules using artificial neural networks. [O] . Marabini, R, Carazo, J M 1994

机译：使用人工神经网络对生物大分子图像进行模式识别和分类。
8. Isolated Speech Recognition Using Artificial Neural Networks. [R] . Polur, P. D., Zhou, R., Yang, J., 2001

机译：基于人工神经网络的孤立语音识别。

Face recognition of color images using artificial neural networks.

摘要

著录项

相似文献

相关主题

期刊订阅