搜索资源列表
AnimprovedBayesianfacerecognitionalgorithm
- 对人脸识别的贝叶斯方法ML中相似度计算公式进行了简化,对数据集的训练和人脸图像的预处理进 行了修改,提出了一种改进的贝叶斯人脸识另1】算法SML。在FERET人脸图像库的子集和南大人脸图像实验库上对 识别算法进行了测试和比较。实验表明,SML算法提高了ML算法的效率,克服了ML算法计算效率不高的缺陷,而 且SML的识别效率明显高于PCA方法。-Bayesian face recognition method on the ML in the similarity formula ha
Iris
- iris标准数据集 模式识别; matlab环境-iris data
PCAPLDA
- PCA+LDA人脸识别,PCA降维到N-C,(N为训练样本数,C为类别数)使得Sw非奇异,主要是解决小样本,数据集为ORL,每类取9(可改)个图片-PCA+LDA recognition, PCA dimensionality reduction to NC, (N is the number of training samples, C is the number of categories) make Sw nonsingular, mainly to resolve the small s
Parallel-axis
- 平行坐标轴是可视化的一种传统方法,用于模式识别聚类等,数据是‘鸢尾花数据集’,有较好的分类效果。-Parallel to the axis is a traditional way to visualize, used for clustering and pattern recognition, data is the iris data set, have better classification effect.
faceRecognition
- 基于SVM和PCA的人脸识别,使用了ORL人脸数据集和libsvm.jar-Face recognition based on SVM and PCA. ORL faces dataset and libsvm.jar are used
QuadricHandModel-master
- 这是一个基于openGl制作的一个手势识别程序(This is a 3D hand model developed mainly for vision-based hand motion analysis. The hand model is modeled as a set of rigid quadratic surfaces, and has 27 degrees-of-freedom (DoFs) including 6 DoFs of global motion and 21 DoFs
code
- 基于python的cifar10数据集的识别和读取的三种方法(Recognition and reading of cifar10 data set based on Python)
download
- DMO-DB[24]是由柏林工业大学录制的德语情感语音库,由10位演员(5男5女)对10个语句(5长5短)进行7种情感(中性/nertral、生气/anger、害怕/fear、高兴/joy、悲伤/sadness、厌恶/disgust、无聊/boredom)的模拟得到,共包含800句语料,采样率48kHz(后压缩到16kHz),16bit量化.语料文本的选取遵从语义中性、无情感倾向的原则,且为日常口语化风格,无过多的书面语修饰.语音的录制在专业录音室中完成,要求演员在演绎某个特定情感前通过回忆自身
LeNet
- tensorflow实现手写体识别(包含mnist数据集)(Handwritten recognition by tensorflow)
纯C-CNN
- 纯C深度学习库,里面包含MNIST手写数字识别数据集,编译就能训练和预测(Pure C depth learning library, which contains MNIST handwritten digital recognition data sets, compiling can be trained and predicted.)
dataset_SkodaMiniCP
- skoca活动识别数据集 包括开车门 关车门等动作(The skoca activity recognition data set includes the action of the door of the car door and so on)
deep-learning-HAR-master
- 一份用tensorflow平台做的cnn分类时序信号,是分类UCI 项目中的人体活动识别(HAR)数据集。该数据集包含原始的时序数据和经预处理的数据(包含 561 个特征)(A CNN classification timing signal made by tensorflow platform is a human activity recognition (HAR) dataset in the classified UCI project. The dataset contains or
#-nina-semimyo-master
- 基于肌电信号的手势识别,数据来自开源数据集ninapro(Hand gesture recognition based on electromyography)
cnn人脸识别
- 使用CNN实现人脸识别,包括训练数据集与测试数据集(Face recognition using CNN, including training data set and test data set)
LSTM-Human-Activity-Recognition-master
- 与经典的方法相比,使用具有长时间记忆细胞的递归神经网络(RNN)不需要或几乎不需要特征工程。数据可以直接输入到神经网络中,神经网络就像一个黑匣子,可以正确地对问题进行建模。其他研究在活动识别数据集上可以使用大量的特征工程,这是一种与经典数据科学技术相结合的信号处理方法。这里的方法在数据预处理的数量方面非常简单(Compared with the classical methods, the recursive neural network (RNN) with long-term memory
数据集
- 对网上一些数据集的整理,分类和归纳,对目标识别方向有用(Sorting, classifying and summarizing some data sets on the Internet, useful for target recognition)
语音识别demo
- rnn循环神经网络训练数据集及进行语音识别实现语音输出(Training data set of RNN cyclic neural network and speech recognition for speech output)