搜索资源列表
BimomentNormalization
- 该算法是bimoment非线性归一化的改进，可以对最终的识别率有所提高，而且该算法能够自动的调整汉字的中心，并有很强的抗干扰能力
pca2D
- 用matlab实现了2dpca算法，基于ORL人脸数据库，识别率较高
Untitled
- 人脸识别算法PCA的可执行程序，识别率为88.5％，为matlab平台程序，大家共享吧
matlab2.rar
- 一个很小手势识别工具. 这是我读Master的时候一个小作业. 我是用block FFT 来写的.70 -80 识别率.,A gesture recognition tool.It was a modle assigment, when I was doing my Master degree. I used block FFT. The recognition rate is round 70-80
dtw
- dtw的matlab算法，识别率达到100 。可直接使用或转成c语言代码，下到下位机运行。-dtw' s matlab algorithm to achieve 100 recognition rate. Can be used directly or converted into c language code, run down to the lower machine.
PCA
- PCA人脸识别算法，识别率达到99 ，采用小波变换的方法及主成分分析法。-PCA face recognition algorithm, the recognition rate up to 99 , using wavelet transform methods and principal component analysis.
OK
- 基于PCA实现的人脸识别，识别率达到80 以上-Face Recognition Based on PCA implementation, the recognition rate of more than 80
Bayesian_Classification
- 使用高斯模型对威斯康辛州大学医学院长期乳腺癌数据进行了贝叶斯模式识别。识别率为95以上，可以作为模式识别的重要案例。-Gaussian model using the University of Wisconsin School of Medicine conducted a long-term breast cancer data Bayesian pattern recognition. Recognition rate is above 95 can be regarded as an i
rlsdtw
- 基于RLS及DTW算法的数字语音识别。用RLS算法来消噪从而提高DTW算法的识别率-Based on adaptive sub-band spectral entropy of the robustness of Speech Endpoint Detection
fftvq
- 小波变换加VQ语音识别程序。用小波变换来提高语音特征的性能，从而提高VQ算法的识别率-Wavelet transform plus VQ speech recognition program. Using wavelet transform to improve the performance of speech features to enhance the recognition rate of VQ algorithms
bprecognition
- 采用神经网络实现手写识别的一种方法，建立Bp神经网络，采用快速训练方法，可快速完成一类相关手写字体的模式识别，识别率较高，当字体变化较大识别率降低时，可重新训练具有较强的适应性。实验证实本方法较好实现了手写字符识别，但也存在识别速度较慢，有时训练不收敛等缺点-Handwriting recognition using neural network is a way to establish Bp neural network, using fast training methods, and c
matlab-carlicense
- 车牌识别程序，结合C++和MATLAB语言编写。在雨天、或光线不足时保持高识别率。-License plate recognition program, combined with C++ and MATLAB language. In the rain, or light enough to maintain a high recognition rate.
UnderdeterminedSeparationofInstaneousSpeechMixture
- 详细描述了关于几个同时说话人语音分离的情况，其中包括了原代码和测试语音，测试结果表明分离效果很好，能够区分不同人说话的语音，明显提高语音识别率。其中的参考论文在readme中。-A detailed descr iption about several while speaking voice separate conditions, including the original code and test speech, test results show that the effect is
099999998
- 这是一个说话人识别的程序，其中有十个说话人，识别率可达到90 。执行时，执行“laststep.m”-This is a speech recognition program, including dozens of speaker recognition rate can reach 90 . Implementation, implementation " laststep.m"
bpn
- 用matlab实现的神经网络识别字母的程序，识别率达到100 。-Program of neural network regnizing letters using MATLAB, the accuracy is up to 100
face4
- 基于神经网络的人脸识别的一种算法，给出了计算识别率的方法-Neural network-based face recognition algorithm, gives the recognition rate calculation method
FPGA_hslogic_face
- FPGA代做，通过matlab实现PCA人脸识别算法，并计算识别率(n the FPGA generation, the PCA face recognition algorithm is realized by MATLAB and the recognition rate is calculated.)
LPR-Matlab-master
- 基于matlab的车牌识别系统，有良好的gui，识别率良好。(The license plate recognition system based on MATLAB has good GUI and good recognition rate.)
基于小波变换的klda人脸识别
- 基于小波变换的klda人脸识别，首先用小波变换对原始输入人脸图像进行预处理，再将基于核的线性判别分析应用于人脸识别中的最佳特征抽取，最后使用欧氏距离分类器实现人脸分类。通过对ORL标准人脸库中的人脸图像进行识别实验，本文提出的方法在人脸识别上取得了较高的识别率。
数字信号识别
- 应用直接幅度方差实现mask\mfsk\mpsk的分类识别，识别率高达97%。(The direct amplitude variance is used to classify mask, MFSK and MPSK, and the recognition rate is as high as 97%.)