资源列表
colorConstancy
- 根据色彩一致性理论,即Retinex理论编写的图像增强算法,实现彩色图像增强。包括单尺度视网膜增强(SSR),多尺度视网膜增强(MSR)还有其他相关增强算法。-According to the color consistency theory, that is, Retinex theory to write the image enhancement algorithm to achieve color image enhancement. Including single-scale ret
pe_p
- 优化排列熵,更具敏感性,利于应用在动态监测中-Optimize the arrangement of entropy, more sensitive,Which is suitable for dynamic monitoring
wpe_test
- 利用加权的排列熵算法WPE,通过白噪声加冲激信号的测试-Using the weighted permutation entropy algorithm WPE, through the white noise plus impulse signal test
wpe
- 加权的PE算法,可以加入序列中的幅度信息。-Weighted PE algorithm can be added to the amplitude information in the sequence.
Lms_gui
- 利用gui设计的现代自适应滤波,通过改编参数实现不同变化。-Using gui design of modern adaptive filtering, through the adaptation of parameters to achieve different changes.
pvhxw
- 在matlab R2009b调试通过,采用波束成形技术的BER计算,语音信号的采集与处理,数字信号处理课设。- In matlab R2009b debugging through, By applying the beam forming technology of BER Acquisition and Processing of the speech signal, digital signal processing class-based.
fao_ta63
- 虚拟力的无线传感网络覆盖,抑制载波型差分相位调制,连续相位调制信号(CPM)产生。- Virtual power wireless sensor network coverage, Suppressed carrier type differential phase modulation, Continuous phase modulation signal (CPM) to produce.
wxijd
- 计算加权加速度,毕业设计有用,实现了对10个数字音的识别程。- Weighted acceleration, Graduation useful Realization of 10 digital audio recognition progra.
qpffn
- 连续相位调制信号(CPM)产生,小波包分析提取振动信号中的特征频率,MIT人工智能实验室的目标识别的源码。- Continuous phase modulation signal (CPM) to produce, Wavelet packet analysis to extract vibration signal characteristic frequency, MIT Artificial Intelligence Laboratory identification of the tar
ritei
- 正确率可以达到98%,是信号处理的基础,IDW距离反比加权方法。- Accuracy can reach 98 , Is the basis of the signal processing, IDW inverse distance weighting method.
PathFind
- 迷宫自动寻路,核心代码都带了,初学人工智能的可以借鉴-Maze automatic pathfinding, the core code are brought, beginners can learn of artificial intelligence
manifold-learning
- 功能:演示流形学习算法在计算机视觉中的应用基于流形学习实现目标分类;-Application of manifold learning algorithm in computer vision based on manifold learning