资源列表
biomass_cal
- 利用植被指数进行生物量计算，批处理，直接输出结果图像。-Using vegetation indices for biomass calculation, batch processing, output images directly.
xt3
- 3、 请采用学过的图像复原算法（鼓励自己研究新算法），对 blur3.jpg、 sadhna_53_45.bmp和telescope.bmp 图像进行复原处理。-3, please use the learned image restoration algorithm (to encourage their study new algorithm), to blur3.jpg, sadhna_53_45.bmp and telescope.bmp image restoration proces
wrap-unwrap
- 相位解调和相位展开的matlab代码，可以从条纹图中提取出相位信息-Phase demodulation and phase unwrapping matlab code, can be extracted the fringe of the phase information
MRMRF
- 基于MRF图形的小波与分解 基于MRF图形的小波与分解 基于MRF图形的小波与分解-Wavelet and decomposition based on MRF graphWavelet and decomposition based on MRF graphWavelet and decomposition based on MRF graphWavelet and decomposition based on MRF graph
SiftRegistrationWithSCM
- 改进SIFT算法，用于光学图像和SAR图像配准-Improved SIFT methods for Registration of Optical and SAR image.
KDE
- 用MATLAB实现KDE算法，对20幅图像进行训练，用一幅图像进行测试-KDE algorithm using MATLAB to carry out training on 20 images, with an image for testing
MSCNN_dehazing2016
- 通过CNN计算大气散射模型中的传播率，从而实现图像去雾-multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps
dehaze
- 基于边界约束和上下文正则化的图像快速去雾算法-Effi cient Image Dehazing with Boundary Constraint and Contextual
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
CLAHE
- 有限对比适应性均衡化是一种有约束的局部直方图构造方法，而不是全局。在高亮区和暗区的增强能力要远优于常规的直方图均衡化，图像视觉效果更加清晰。-Finite contrast adaptive equalization is a constrained local histogram construction method, rather than a global. The enhancement capability of the highlighted area and dark regio
OMP
- OMP算法应用在DOA估计，可以分辨多个目标，估计出目标方位，且有很高的分辨性能。-OMP algorithm used in DOA estimation, can distinguish multiple targets, to estimate the target orientation, and have a high resolution performance.
star
- 星图像检测。获得的星图像存在噪声，而且星图像的背景经常是不均匀的，用形态学运算对星图像进行处理，补偿不均匀的星图像背景，然后进行星图像的阈值分割。-Star image detection