资源列表
adaptive-midfilter
- 自己编写的自适应中值滤波器，对去除图像噪声有一定效果-adaptive midfilter ,help to suppress the noise of images
technology-to-fog
- 基于直方图优化的图像去雾技术； 三种去雾方法，包括局部直方图、全局直方图、retinex算法-Histogram-based image optimization technology to fog defogging three kinds of methods, including local histogram global histogram, retinex algorithm
Weightbased-adaptive-image
- 基于形态学的权重自适应图像去噪；通过串并联的滤波降噪对比图，说明并联降噪的优越性-Heavy adaptive image denoising based on morphology right noise filtering by series-parallel comparison chart, show the advantages of parallel noise reduction
Nearest-neighbor-classification-code
- 最近邻分类器代码和数据，MATLAB程序，可对数据进行计算距离，识别距离最近的数据。-Nearest neighbor classification code and data, MATLAB program, the data can be calculated the data identify the nearest.
character-recognition
- 基于特征匹配的英文印刷字符识别；同时开发了GUI程序运行进行实时检测-Based on feature matching printed English character recognition also developed a GUI program running real-time detection
Pavement-detection
- 路面裂缝检测识别系统设计；通过GUI集成开发演示，并且保存入库-Pavement crack detection and identification system design integrated development through GUI presentation, storage and preservation
wavelet-technology
- 基于小波技术进行图像融合；通过小波变换分解不同分辨率和频域特征子图像后得到融合-Image fusion based on wavelet technology decomposition different resolutions and frequency domain sub-image fusion wavelet transform
DBN
- 深度信念网络 (Deep Belief Network, DBN) 由 Geoffrey Hinton 在 2006 年提出。它是一种生成模型，通过训练其神经元间的权重，我们可以让整个神经网络按照最大概率来生成训练数据。我们不仅可以使用 DBN 识别特征、分类数据，还可以用它来生成数据。下面的图片展示的是用 DBN 识别手写数字： -Depth belief networks (Deep Belief Network, DBN) proposed by the Geoffrey Hinton i
gaborga
- 高斯滤波器，对图像进行高斯滤波处理，去除噪声-Gaussian filter, the image of gaussian filtering processing, remove the noise
EOH-top
- 实现XY、XT、YT三个平面提取EOH特征-Achieve XY, XT, YT three planes feature extraction EOH
HALCON_Thread
- 利用halcon的一个多线程实现实时采集图像，抓取一帧图像。-Halcon use of a multi-threaded real-time image acquisition, crawl an image.
vehicle_detection
- vehicle_detection 的相关代码，供大家参考，haar 级联器-dode for vehicle_detection，used for reference