搜索资源列表
DCT
- 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B
xiaoshutuxiang
- 深入研究对基于零树的小波图像压缩算法，利用多分辨分析对图像进行了小波分解，并利用零树编码算法对图像进行压缩。 -In-depth study of the zero-tree wavelet-based image compression algorithm using multi-resolution analysis of wavelet image decomposition, and using zero-tree coding algorithm for image compres
Depth_image
- Algorithm to find Depth of Image
pingjunqulv
- 深度图像遮挡边缘检测，平均曲率法，Matlab 7.0开发-Depth of the image edge detection block, the average curvature, Matlab 7.0 development
yuzhifa
- 深度图像遮挡边缘检测，阈值法，MATLAB源码-Depth of the image edge detection block, threshold method, MATLAB source
shendutuhuizhi
- 基于深度图的图像绘制技术研究 介绍并探讨研究了图像绘制的关键技术-Based on the depth chart image rendering technology research describes and discusses the key technologies of images drawn
FaceRecognitionBased-OnDeepLearning
- 本文运用深度神经网络的方法克服姿态变量和图像分辨率的影响,提出了一种多姿态的人脸超分辨识别算法并在实验数据集上获得了良好的性能表现。另外本文利用深度信念网络探索正面人脸图像和侧面人脸图像的映射,方法放松了深度信念网络的输入也输出之间绝对相等,而只是保证其高层含义上的相等。实验表明了使用深度信念网络可以学习到侧面人脸图像到正面人脸图像的一个全局映射,但是丢失了个体细节差异。本文还提出了基于深度网络保持姿态邻域进行姿态分类的方法,在学习过程中,我们保证了同一个姿态下的人脸图像应该与同一姿态下的多张图
kinect-for-image-achieve
- 同时采集Kinect的深度图像和彩色图像，并且可实时将同一时刻采集的两种图像保存到相应目录.-Simultaneous acquisition Kinect depth images and color images, and save the two kinds of image to the appropriate directory.
rgbd_kinect
- 结合kinect景深图像对视频目标进行跟踪，在vs2010+opencv平台上测试通过。-Combined with kinect depth of field image of the video object tracking on vs2010+ opencv test platform.
DeepLearningApp
- 深度学习在语音识别，图像识别方面的应用介绍余凯老师-In depth study of speech recognition, application of image recognition is introduced the aspects of teacher Yu Kai
CUDA-convnet
- HINTON的学生alex写的有关深度学习的图像分类上在cuda上的实现-Image classification HINTON alex students wrote about the depth of learning implemented on cuda' s
Depth-of-field-calculator-based-on-2D-digital-ima
- Depth of field calculator based on 2D digital image correlation data , Depth of field calculator based on 2D digital image correlation data-Depth of field calculator based on 2D digital image correlation data , Depth of field calculator based on 2D
DMM
- DMMs提取Kinect人体深度动作图像的方法，是一种将深度图像映射到三个正交直角平面的有效方法。-DMMs extraction depth Kinect body movement image method, the depth of the image is an effective way to map three orthogonal Cartesian plane.
OpenCode_luzhenbo
- [原创]混沌分析,聚类分析,支持向量机,群体智能优化,深度学习(卷积神经网络)Matlab工具箱全开源版本下载 作者: 陆振波 毕业院校：海军工程大学，船舶与海洋工程(水声工程)，博士 精通方向：信号处理，图像处理，人工智能，模式识别，支持向量机，深度学习，机器学习，机器视觉，群体智能，非线性与混沌，Matlab与VC++混编，大数据 擅长技能：团队激励，战略规划，企业文化，组织架构，C，C++，Matlab，OpenCV，并行计算，图像处理，智能视觉，卷积神经网络，人脸检测，行
image-inpainting-depth-map
- 基于深度图像的图像修复算法，首先得到待修复图像的深度图像，然后利用图像的深度图对破损区域进行修复。-Based on the image restoration algorithm of depth image, the depth image of the image to be repaired is obtained, and then the damaged region is repaired by using the depth map of the image.
attempts--distance-of-2D
- 人们之所以能够看到深度，是因为，来自三维世界的不同视角。本程序尝试从一个2D图像映射并计算对应的3D的距离-People have been able to see the depth, because the three-dimensional world different perspectives. This procedure attempts to distance a 3D and 2D image map calculates the corresponding
toolbox_nyu_depth_v2
- depth estimation of images is done on nyu .webite showa data downloade
A Fast Single Image Haze Removal Algorithm
- Single image haze removal has been a challenging problem due to its ill-posed nature. In this paper, we propose a simple but powerful color attenuation prior for haze removal from a single input hazy image. By creating a linear model for modeling
caffe-cvprw15-master
- 基于深度学习框架构建用于快速图像检索的二值哈希编码(Construction of binary hash codes for fast image retrieval based on depth learning framework)
53607900Autoencoder_Code
- 用SAE 深度学习方法做的高光谱图像分析的一个例子。里面有sae方法还有高光谱图像的特征提取过程。(One example of the depth of learning to do with SAE hyperspectral image analysis. There are sae method has hyperspectral image feature extraction process)