Search - DCT - CodeBus

Search - DCT - List

[AI-NN-PR] face_recognition DL : 0: 基于2D-DCT和模块2DPCA的人脸识别系统的实现（matlab）
Date : 2025-12-23 Size : 1.96mb User : da
[AI-NN-PR] 127 DL : 0: DCT用于掌纹识别的word论文文档，比pdf更容易阅读编辑和引用，供大家学习和交流-The discrete cosine transform is a classical image processing technique, and the discriminant analysis is a commonly used image feature extraction technique. These two techniques are effectively combined in the paper, and a new palmprint feature extraction approach is proposed. After performing discrete cosine transform on the palmprint images, the proposed approach first uses a two-dimensional separability judgment to select the frequency bands with favorable separability. Then from the selected bands, it extracts the discriminant features by using an improved Fisherface method. The experimental results on the public palmprint image database demonstrate the effectiveness of the proposed approach.
Date : 2025-12-23 Size : 48kb User : 小哈
[AI-NN-PR] DCT DL : 0: 本文设计基于DCT的人脸识别系统，首先结合当今人脸识别的背景和发展状况讨论了人脸识别的研究内容及在各方面的应用；然后研究了人脸识别进行预处理，讨论了人脸识别预处理的其他方法，分析各种方法的利弊，最后采用DCT（离散余弦变换）实现人脸图像预处理中的降维处理；接下来对人脸图像的特征提取进行了研究，简单叙述了几何特征提取和代数特征提取，同时深入研究了基于DCT和PCA变换的人脸图像特征提取，从而实现是否对人脸识别系统识别率有所提高的研究；对于分类器的选择，本文对两种分类器进行了探讨，即最近邻分类器和BP神经网络分类器，同时采用BP神经网络分类器作为本次基于DCT的人脸识别系统设计的分类器，并对BP神经网络进行分类的算法进行设计，BP神经网络具有学习功能，只要采用本系统对训练图片进行训练，就可以记下图像的相关信息，对于测试图片，就可以很准确的识别出该图片是属于哪个的。最后，本文对整个人脸识别系统设计实验进行了实验分析，实验结果表明本文采用的方法切实有效。- This is the design of the DCT-based face recognition systems. First of all, the background light of the current face recognition and face recognition to discuss the development of research in all aspects of content and applications And then studied the pretreatment of face recognition to discuss the pre-treatment of other face recognition methods,and analysis of the pros and cons of various methods, finally, the use of DCT (discrete cosine transform) image pre-processing to achieve in the face of the reduced-order processing Next on the face image feature extraction have been studied, A brief description of the feature extraction and algebraic geometry feature extraction, while in-depth study based on the DCT and the PCA Transform face image feature extraction in order to achieve face recognition system to identify whether the rate of increase in the research For the choice of classifier, this paper carried out on two of classifier, that is, nearest neighbor classifier and BP neura
Date : 2025-12-23 Size : 413kb User : 刘文珍
[AI-NN-PR] SoftthresholdingforDCTspeechenhancement DL : 0: Soft thresholding for DCT speechenhancement
Date : 2025-12-23 Size : 236kb User : 金鼎奖大
[AI-NN-PR] digitalwatermarking DL : 0: DCT watermark images
Date : 2025-12-23 Size : 252kb User : Mohamed Ibrahim
[AI-NN-PR] F5steganographic-1.0 DL : 0: 针对F5隐写的检测，包括共生矩阵，不连续性的特征提取，DCT变换，灰度值提取，运用支持向量机SVM -For F5 steganography detection, including the co-occurrence matrix, feature extraction discontinuity, DCT transform, gray value extraction, using support vector machine SVM
Date : 2025-12-23 Size : 4.85mb User : 石杨欣
[AI-NN-PR] dct_bp DL : 0: 结合DCT和BP神经网络进行人脸识别。先利用DCT提取特征，然后利用BP神经网络分类，在ORL人脸库上测试效果不错。-The combination of DCT and BP neural network for face recognition. First DCT Feature Extraction, and then use the BP neural network classifier, a good test results on the ORL face database.
Date : 2025-12-23 Size : 2kb User : 尹贺峰
[AI-NN-PR] dct_pnn DL : 0: 结合DCT和概率神经网络进行人脸识别。先利用DCT提取特征，然后利用PNN分类，在ORL人脸库上测试效果不错。-The combination of DCT and probabilistic neural network for face recognition. First DCT Feature Extraction, and then use a PNN classification, good test results on the ORL face database.
Date : 2025-12-23 Size : 1kb User : 尹贺峰
[AI-NN-PR] CODEdctannprotected DL : 0: DCT-ANN Based Face Recognition
Date : 2025-12-23 Size : 25kb User : sohaa
[AI-NN-PR] batch-omp DL : 0: KSVDBox - Implementation of the K-SVD and K-SVD denoise algorithms.-K-SVD dictionary training. ksvd - K-SVD dictionary training. Signal denoising. ompdenoise - OMP denoising. ompdenoise1 - OMP denoising of 1-D signals. ompdenoise2 - OMP denoising of 2-D signals. ompdenoise3 - OMP denoising of 3-D signals. ksvddenoise - K-SVD denoising. Overcomplete DCT dictionary. odctdict - Overcomplete DCT dictionary. odct2dict - 2-D overcomplete DCT dictionary. odct3dict - 3-D overcomplete DCT dictionary. odctndict - Multi-dimensional overcomplete DCT dictionary. Demonstrations. ksvddemo - K-SVD training demonstration. ksvddenoisedemo- K-SVD denoising demonstration. Miscellaneous. showdict - Display a dictionary of image patches. ksvdver - K-SVD toolbox version information.
Date : 2025-12-23 Size : 847kb User : 时中荣
[AI-NN-PR] v1.9 DL : 0: 程序用vc6.0编写，基于离散余弦变换DCT和bp神经网络的人脸识别。采用ORL人脸库，对图像进行DCT低通滤波，再用BPNN进行训练或识别，样本空间内识别效果好。设计流程参考了本站 yaxuan 的v3.3(http://www.pudn.com/downloads330/sourcecode/math/detail1452162.html)(本程序不包含原作的粒子群修正权值及网络结构调整等功能，但调整了训练样本的排列顺序) 感谢原作者，若有侵权我会删除此上传^ ^-Vc6.0 procedures used to prepare, transform and DCT bp neural network recognition based on discrete cosine. Use ORL face for image DCT lowpass filter, and then BPNN training or recognition, good recognition effect within the sample space. The design process of the reference site yaxuan v3.3 (http://www.pudn.com/downloads330/sourcecode/math/detail1452162.html) (The program does not contain particle swarm correction weights and network features such as the original restructuring but adjusted the order of training samples) thanks to the original, if tort I will remove this upload ^ ^
Date : 2025-12-23 Size : 3.32mb User : 连云
[AI-NN-PR] cdduus426 DL : 0: DCT快速算法64位的C语言实现,乘法次数目前最少,可嵌入解码器使用()
Date : 2025-12-23 Size : 7kb User : LHKPrhjib%2101440