A method of face classification and recognition based on dct and svm is proposed . the features are extracted by dct and a small set of dct coefficients are inputted to svm . the experiments show that the performance is satisfactory 提出了一种基于dct和支持向量机的人脸分类和识别方法，首先对人脸图像作二维离散余弦变换，取离散余弦变换系数作为特征输入支持向量机，然后用支持向量机进行性别分类及人脸识别。
Except h . 264 , almost all of the standards use mc - dpcm / dct technologies . motion compensation and dct ( discrete cosine transform ) are used to decorrelate spatio - temporal correlation of video signal and quantization is used to exploit perceptual redundancy of nature video 除最新的h . 264外，这些标准都是基于联合mc - dpcm dct的视频压缩框架，即采用运动补偿预测和离散余弦变换分别消除视频信号的时域和空域冗余。
4 ) at the same time , this dissertation studies the probability that wavelet transform is used to substitute for the dct transform in the mpeg - 2 standard . some consideration to use the wavelet transform to process the video signal in the mpeg - 2 has been given ( 4 )对小波变换在mpeg - 2中的应用做了研究，并讨论了用小波变换替换mpeg - 2标准中的离散余弦变换的可能性，最后提出了结合小波变换在视频处理中应用的一些设想。
In this paper the visually recognizable binary image is selected as watermark information , which is embedded in the transform domain through transforming the original audio signal ( discrete cosine transform and discrete wavelet transform ) 本文选用二值图像作为水印信息，通过对原始音频信号做变换，在变换域内嵌入水印，采用的是离散余弦变换( discretecosinetransform ? dct )和离散小波变换( discretewavelettransform ? dwt ) 。
Combining the principles of pipelining and parallelism of dsp with idct theory , we concentrate on the use of multiply - accumulate unit of mcf5272 by merging the operations of addition and multiplication , and realize two dimension of idct with one dimension of idct efficiently . testing shows the software meets the requirement of real - time decoder 重点结合mcf5272的流水线操作和并行操作特征和反离散余弦变换算法原理，将的二维反离散余弦变换转换成8点的一维反离散余弦变换，利用乘法累加器合并加法运算和乘法运算高效快速地实现了反离散余弦变换算法。
Scalable video coding ( such as mpeg - 4 fgs and jvt svc ) and streaming is one of the most promising technologies . in this thesis , we investigate the key problem of scalable video coding and streaming : rate - distortion analysis and approximation , with which we also design some simple and effective smooth quality reconstruction algorithms of video streaming 本文主要的内容和创新点包括:由于广义高斯分布ggd ( generalizedgaussiandistribution )的高度灵活性,理论上和实际中它都可以非常好地描述离散余弦变换( dct )和小波变换( wavelettransform )的编码系数( transformcoefficients ) 。
By comparing the experimental results of these algorithms , the differences between the features of pictures and paintings are analyzed ， based on which , the characteristics of face painting recognition algorithms should have are given . the experimental results indicate that those algorithms that do not require a strict justification of the face images and do not depend on the gray scale value itself will achieve a relatively high recognition performance . among these algorithms is the method based on discrete cosine transform 首先，深入研究了人脸的检测与定位方法，建立了一个人脸自动检测系统，为后续的人脸识别提供了精确的器官位置；其次，针对人脸画像的特点，提出了一种基于离散余弦变换（ dct ）的画像识别方法，以及一种适用于画像的几何归一化方法；最后，研究了现有的几种人脸识别方法在画像识别中的应用，通过对包括本文提出的基于dct方法在内的几种识别方法作对比实验，分析了画像和照片在特征上的差别，并总结出用于画像识别的方法所应具有的基本特点。
In this dissertation , lots of exploratory research work has been done around some key techniques of image retrieval based on compressed - domain , which include based on discrete cosine transform ( dct ) , based on vector quantization ( vq ) combine with low - level feature extraction , similarity measure and so on 本论文围绕压缩域图象检索中的一些关键方法，包括基于离散余弦变换和基于矢量量化等方法联合提取图象低层特征、图象间相似性度的度量等技术，进行了一些探索性的研究。
A method of face detection based on support vector machine ( svm ) is put forward . the features are extracted by applying the discrete cosine transform ( dct ) to the preprocessing image . the dct coefficients are inputted to the svm and the svm are trained using the cropped face samples and the " bootstrapping non - face " samples 对预处理后的图像进行离散余弦变换提取特征，取dct系数作为支持向量机的输入，将经过裁剪的“人脸”样本与“自举”方法得到的“非人脸”样本一起用来训练支持向量机。
This dissertation presents the study of several issues in video coding and its hardware implementation . a novel hardware - based video coding system is proposed based on the itu - t h . 263 recommendation . some key techniques such as discrete cosine transform ( dct ) and its inverse ( jdct ) and motion estimation are studied in detail 本文介绍了作者在视频压缩编码及其硬件实现方面的研究，研究了itu - th . 263建议的视频编码标准，并在该建议的基础上提出了一种基于硬件实现的视频编码器结构，对于离散余弦变换( dct )反变换( idct ) 、运动估值等关键技术做了深入研究，并在此基础上提出了dct idct和运动估值的硬件实现方案。
