搜索资源列表
DeepFace
- DeepFace一文依旧是沿着“检测-对齐-人脸表示-分类”这一人脸识别技术路线来的，其贡献在于对人脸对齐和人脸表示环节的改进。1）在人脸对齐环节，引入了3D人脸模型对有姿态的人脸就行分片的仿射对齐。2）在人脸表示环节，利用一个9层的深度卷积在包含4000人、400万张人脸的数据集上学习人脸表示，这个9层的DCNN网络有超过1.2亿个参数。本文的模型在LFW数据集上取得了97.25 的平均精度（逼近了人类97.5 的极限），同时在Youtube数据集上取得了当前最好的结果，比之前的NO.1整整高
AVA_dataset
- ava数据库下载代码,用于图像美学质量评价-download ava dataset，image aesthetic assessment
Face_PCA
- 在人脸数据库中应用PCA，以及重建误差分析-Applying PCA in human face dataset and doing analysis on reconstruction differences
yaleB_9
- 从yaleB人脸数据集中提取的9维subspaces(subspaces with dimension 9 extracted from YaleB dataset)
yaleB_13
- 从yaleB人脸数据集中提取的4维subspaces(subspaces with dimension 13 extracted from YaleB dataset)
hed-master
- We develop a new edge detection algorithm, holistically-nested edge detection (HED), which performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automat
dataset
- .熟悉BMP图像的结构，编程实现BMP图像的阅读和显示。 编程实现彩色BMP图像的三个分量R、G、B的显示，Y、I、Q，H、S、I分量和X、Y、Z的显示。 获取图像任意一点的像素值(Familiar with the structure of BMP image, programming to realize the reading and display of BMP image. The programming realizes the display of three compone
Objctioforsmage
- Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years(The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level conte
shujuk
- 多模态表情数据库，用于多模态的情绪识别，含音频，视频，图像。(CREMA-D Crowd-sourced Emotional Multimodal Actors Dataset)
superresolution_dataset
- 用于图像超分辨成像应用的标准数据库，希望对初学者有用(A standard dataset for super-resolution imaging, hoping to be useful for beginners)
模仿mnist数据集制作自己的数据集代码
- 自己的数据集制作,模仿mnist数据集，制作自己的数据集(based on the mnist dataset to make your own data)
SURFpipei_matlabfunctiontest
- 实现SURF特征点描述子算法，并使用Oxford Dataset图像自动进行精度评价(SURF feature descr iptor and matching precision evaluation)
yale-face
- 耶鲁大学的人脸数据集 yale-face(Yale University face dataset yale-face)