搜索资源列表
Chapter7_HeadPoseEstimation
- 全套头部姿势识别代码,识别率极高,亲测无误。(Full set of head posture recognition code, high recognition rate, pro-test error.)
easypr
- 中文车牌识别系统: 它基于openCV这个开源库。这意味着你可以获取全部源代码,并且移植到opencv支持的所有平台。 它能够识别中文。例如车牌为苏EUK722的图片,它可以准确地输出std:string类型的"苏EUK722"的结果。 它的识别率较高。图片清晰情况下,车牌检测与字符识别可以达到80%以上的精度。(Chinese car license plate recognition system: It is based on ope
fhmm1
- 可以将不同的人脸进行识别分类,使用隐马尔科夫算法实现较高的识别率(Different faces can be identified and classified, using hidden Markov algorithm to achieve higher recognition rate)
gait-sp-beta1.tar
- 本代码主要是稀疏编码的方法来进行步态识别的,识别率高,错误率低。(This code is mainly sparse coding method for gait recognition, high recognition rate, low error rate.)
MATLAB夜间车牌识别程序
- 能准确识别车牌,提高识别率,算法精准,没有错误(Can accurately identify the license plate, improve the recognition rate, accurate algorithm, no error)
plate-recognition
- 基于python的车牌识别,端对端,目前识别率还不高,仅供学习(chepaishibie based on python)
SR
- WinForm界面,实现实时的离线中英文混合语音识别。速度很棒,识别率有待提高。(WinForm interface for real-time offline mixed speech recognition in Chinese and english. The speed is great, and the recognition rate needs to be improved.)
sogouOCR
- sogouOCR,搜狗OCR调用,屏幕截图识别文字。图片转文字,识别率非常高,98%以上。绝对值得直接使用。(SogouOCR, Sogou OCR calls, screenshots to identify text. Picture to text, the recognition rate is very high, more than 98%. Absolutely worth using directly.)
QRCode.jar
- 去掉zip 就是jar包文件,识别率比zxing强多了(QRCode.jar,good!!!!!!!!!!!!!!!!!!!)
test1
- 需要tesseract ocr api支持,测试用手写识别(Tesseract OCR API support is required for handwriting recognition test)
基于航天遥感图像的飞机目标识别
- 基于航天遥感图像的飞机目标识别,算法简单实用,检测率也不错。(Aircraft target recognition based on space remote sensing images, the algorithm is simple and practical, and the detection rate is good.)
基于加权小波分形的卫星遥感图像飞机类型识别
- 基于加权小波分形的卫星遥感图像飞机类型识别,检测率不错,推荐。(The detection rate of satellite remote sensing image based on weighted wavelet fractal is good, and it is recommended.)
Adaboost人脸识别(有GUI)
- 实现人脸识别,有多种算法,包含gui界面,识别率高,程序易懂,值得借鉴(The realization of face recognition has a variety of algorithms, including the GUI interface, high recognition rate, easy to understand program, and it is worth reference.)
基于pca+lda+粗糙集+模糊神经网络的人脸识别
- 各种算法用于人脸识别,各个算法的识别率都不错,有lda,pca等算法(Various algorithms are used for face recognition, and the recognition rate of each algorithm is good. There are algorithms such as LDA, PCA and so on)
test
- 该方法利用人脸具有镜像对称的自然特性,依据奇偶分解原理,生成成镜像奇、偶对称样本,井利用人脸对称图像作为训练样本,再利用主分量分析(PCA)对训练样本进行二阶相关和降维处理,然后对处理后的样本进行ICA特征提取。理论和分析实验证明,该算法有效减线了人脸受到视角、光照、人脸表情、姿势变化等因素的最响,又增加了训练样本容量,减少了计算复杂度,同时有效解决了小样本问题,提高了识别率.(The method uses the natural characteristics of mirror symme
faceRecognization
- 本程序中,利用了LBP特征对人脸特征进行提取,并且利用SVM对提取的人脸特征进行训练和识别,其中,所用的图像处理库OpenCV2.4.9版本;通过对人脸库中的标准标本进行测试,算法识别率高达95%以上;(LBP features extract facial features, and use SVM to extract and recognize the facial features. The OpenCV2.4.9 version of the image processing libr
testandtrain
- 利用三层卷积神经网络识别信号星座图,准确识别8psk,16psk,32psk,64qpsk四种调制方式,在低信噪比的情况下已然有良好的识别率。(The three layer convolution neural network is used to identify signal constellation, and accurately identify four modulation modes of 8PSK, 16PSK, 32psk and 64qpsk. It has a good
EasyPR-master
- 能够有效从自然环境中定位以及识别车牌,利用人工神经网络ANN,进行数字识别,识别率达到90%(The ability to locate and identify the license plate effectively from the natural environment)
zhiwen
- 这个程序就是从联合开发网下载的,但是有一个错误导致识别率不足60%。 原始版本在图像旋转后提取的指纹中心点算法有误,每次提取的中心点都在图像边缘,造成后面提取的FingerCode也会出错。 这个修改使旋转前的中心点与旋转后的中心点保持一致,同时减少了运算复杂度(This program is downloaded from www.pudn.com, but one error led to recognition rate of less than 60%. The original
python_face_recog
- 基于python+opencv 的 人脸识别,对一段视频进行读取,并检测出人脸,然后进行PCA 降维,最后用SVM进行人脸识别,识别率94%左右。(Based on python + opencv face recognition, a video was read, and face detection, and then PCA dimension reduction, and finally SVM face recognition, recognition rate of about 9