资源列表
IDLmean
- 利用ENVI/IDL，计算多幅图像的各个像元的平均值。并忽略空缺值(Use ENVI/IDL, calculate the average of each pixel of multiple images. And ignores the value of vacancies)
lbp
- 提取一幅图像的LBP特征，输入为一幅图片，输出为一个256维的行向量，代表图像的LBP特征。(The LBP feature of an image is extracted, and input is a picture. The output is a 256 dimensional row vector, representing the LBP characteristic of the image.)
XH_SD_Event_Freeze
- 摄像头画面冻结检测，c++，代码已经有完整的功能实现函数。(Camera freeze detection, c++, code has a complete function to achieve functions.)
1
- 图形图像雾霾去雾的基础算法之一，Retinex算法是多尺度Retinex算法以及单尺度算法的基础算法(One of the algorithms for fogging)
LOG
- 实现在LOG算法下，探讨不同σ对LOG的影响，卷积核(Under the LOG algorithm, we discuss the influence of different Sigma on LOG and convolution kernel.)
图像识别部分
- 基于大宝sod蜜塑料瓶瓶口的堵料识别程序。包含预处理和图像分割及特征提取等部分。(Based on the Dabao sod honey plastic bottle bottle block identification program. Contains preprocessing, image segmentation, and feature extraction.)
Naive CNN 18 multiplication per clock cycle_V3
- 此文件是卷积神经网络中的卷积核的硬件实现代码(CNN:filter/filter3*3 filter4*4 filter5*5 filter6*6)
focusing_of_SAR_raw_data
- 一个简单的雷达成像程序，使用matlab语言，可供参考(A simple radar imaging program, data, for reference.)
04897653imagerecgonition
- 图像识别图像复原用于运动图像的复原具有很好的作用，大家可以随意下载，可以应用(mage recognition and image restoration play a good role in motion image restoration. You can download them freely, and you can apply them.)
first
- 车牌定位 车牌分割 字符识别 正如上面所讲,车牌识别主要分为3个部分,其中第一部分车牌定位,一般采用颜色定位,特征定位等,这方面一堆资料我就不写了.分割一般采用投影法.识别的话方法就比较多了,有模板匹配,bp神经网络,卷积神经网络等.(pan.baidu.com/s/1jIdSuXK)
视差图完整
- 对双目视觉处理的图像通过获取相机的内外参数后得出视差图，而后方便得到深度图等(The binocular vision processing image is obtained by obtaining the camera's internal and external parameters, and then the disparity map is obtained, and then the depth map is obtained.)
视差图程序
- 对于双目视觉处理中，对于已经标定好都后的系统，处理左右目的图像，形成视差图。(For binocular vision processing, for the system that has been calibrated, the left and right target images are processed to form disparity map.)