资源列表
LBP
- LBP特征提取算法，可以用于检测与识别。算法主要目的是提高车牌识别中汉字识别准确率。-Code about LBP feature extraction can be used for detection and recognition. This algorithm aims to improve the accuracy of Chinese char recognition of EasyPR.
facejiance
- 人脸角点检测与运动跟踪，挺好用，值得学习-Face corner detection and motion tracking, quite good, worth learning
chap
- 文字图像分割，识别程序,索书号文字图像分割彩色车牌分割-Text image segmentation, segmentation of color license plate recognition program, call text image segmentation
ex4
- 手写识别的实现，由bp算法和梯度下降算法实现的神经网络-Handwriting recognition achieved by the bp algorithm and gradient descent algorithm neural network
JMStdio
- 视频软件可以播放接受相机图像，甲骨文公司程序员写的例程-video software can be used to broadcast video, acquisition camera images,and the programer of Oracle company had been done it,
PDF417_decode
- PDF417译码，不涉及字节模式，经过时间优化，同时解5张图片时间约为0.4秒-PDF417 decoding, does not involve byte mode, the elapsed time optimization, and solution time is about five pictures 0.4 seconds
LDA
- 基于LDA方法应用ORL人脸识别matlab程序-Methods ORL-based LDA face recognition matlab program
PCA
- 基于PCA的人脸识别（使用的ORL的人脸库）-PCA-based face recognition (using the ORL face )
Text-detection
- 场景图像中文本占据的范围一般都较小，图像中存在着大范围的非文本区域。因此，场景图像文本定位作为一个独立步骤越来越受到重视。这包括从最先的CD和杂志封面文本定位到智能交通系统中的车牌定位、视频中的字幕提取，再到限制条件少，复杂背景下的场景文本定位。与此同时文本定位算法的鲁棒性越来越高，适用的范围也越来越广泛。-Text detection
EdgeDetection
- 程序分成两个部分，第一个部分是将原始的彩色图像转化成灰度图，第二个部分是对灰度图进行边缘检测。经过大量的图像测试，检测效果极佳。-The program is divided into two parts, the first part is the original color image into a gray-scale image, the second part of the gray-scale image edge detection. After a lot of image t
ANN
- OpenCV的ANN神经网络实现图像数字识别，可运行，能够达到99.9的准确率-ANN OpenCV neural network to achieve digital image recognition, can run, to achieve the accuracy rate of 99.9
ImageRetrieval
- ImageRetri （C++_毕业设计） sift,颜色直方图，灰度矩阵，HU不变矩，边缘方向直方图，检索方法使用K-means和K-D树两种，需要OPENCV支持-ImageRetri Color histogram, gray matrix, HU invariant moment, edge direction histogram, retri method using K-means and K-D tree two, need OPENCV support (C++ _ gradu