搜索资源列表
deboor-cox.rar
- 目的:运用强化学习!多分类器集成!降维方法等最新计算机技术,结合细胞病理知识,设计制作/智能化肺癌细胞病理图像诊断系统0"方法:采集细胞图像,运用基于强化学习的图像分割法将细胞区域从背景中分离出来 运用基于样条和改进2方法对重叠细胞进行分离和重构 提取40个细胞特征用于贝叶斯!支持向量机!紧邻和决策树4种分类器,集成产生肺癌细胞分类结果 建立肺癌细胞病理图库,运用基于等降维方法对细胞进行比对,给予未定型癌细胞分类"结果:/智能化肺癌细胞病理诊断系统0应用于临床随机1200例肺
HOG
- 这是最简洁，注释得最好的HOG(Histogram Oriented Gradient)算法的matlab实现。可用于行人识别和物体跟踪。-This code is well commented, which enables the adjusting of the HOG parameters. This code was developed for the work: O. Ludwig, D. Delgado, V. Goncalves, and U. Nunes, Trainable
jiyutezhengronghehemohuhepanbian
- 提出了基于特征融合和模糊核判别分析(FKDA)的面部表情识别方法。首先，从每幅人脸图像中手工定 位34个基准点，作为面部表情图像的几何特征，同时采用Gabor小波变换方法对每幅表情图像进行变换，并提取基 准点处的Gabor小波系数值作为表情图像的Gabor特征；其次，利用典型相关分析技术对几何特征和Gabor特征进 行特征融合，作为表情识别的输人特征；然后，利用模糊核判别分析方法进一步提取表情的鉴别特征；最后，采用最 近邻分类器完成表情的分类识别。通过在JAFFE国际表情数据库和
refpaper6_hcrnumkannada
- Abstract. This paper describes a system for isolated Kannada handwritten numerals recognition using image fusion method. Several digital images corresponding to each handwritten numeral are fused to generate patterns, which are stored in 8x8 ma
HOG
- Image descr iptor based on Histogram of Orientated Gradients for gray-level images. This code was developed for the work: O. Ludwig, D. Delgado, V. Goncalves, and U. Nunes, Trainable Classifier-Fusion Schemes: An Application To Pedestrian De
Steganalysis-Based-on-dctdwt-space
- 基于SVM分类器的三域特征融合图像隐写分析算法。三域分别是指dct域，dwt域和空域。-A Steganalysis Based on the Fusion of Three-domain Features of Image and SVM (Support Vector Machines) Classifier.the three domain is the dct,the dwt and the space
feature-exacte
- 本文提出了一种基于特征融合的纹理图像分类方法，它结合了纹理图像的特 点和框架小波变换方法，处理过程中充分考虑了图像各尺度间的依存关系以及不 同频带中所包含的图像纹理信息，利用支撑矢量机作为分类器，对标准纹理库中 的图像进行了仿真实验。 -This paper presents a texture feature fusion based image classification method, which combines the special texture Point
knniris
- fusion svm_knn the output of svm will be the input of knn classifier
3glcm
- This paper has a further exploration and study of visual feature extraction. According to the HSV (Hue, Saturation, Value) color space, the work of color feature extraction is finished, the process is as follows: quantifying the color space in non-eq
HOG
- Image descr iptor based on Histogram of Orientated Gradients for gray-level images. This code %was developed for the work: O. Ludwig, D. Delgado, V. Goncalves, and U. Nunes, 'Trainable %Classifier-Fusion Schemes: An Application To Pedestrian Detectio
cfmatrix
- 简单的获取分类器融合矩阵的matlab程序，利于初学者理解融合矩阵的含义-Get simple classifier fusion matrix matlab program, which will help beginners to understand the meaning of the integration matrix
Fusing-Multiple-Feature
- 通过改进基于Haar-like特征和Adaboost的级联分类器，提出一种融合Haar-like特征和 HOG特征的道路车辆检测方法-By improving based on Haar-like features and Adaboost cascade classifier, presents a fusion of Haar-like features and characteristics of HOG road vehicle detection method
ensemble
- adboost算法的测试和训练，能够做多分类器融合，获得很高分类精度-adboost algrithm， it can be used to operate multi-classifier fusion
ICPR
- 1_On the Dimensionality Reduction for Sparse Representation based Face Recognition 2_Fingerprint Pore Matching based on Sparse Representation 3_Microaneurysm (MA) Detection via Sparse Representation Classifier with MA and Non-MA Dictionary
FINAL
- Nowadays security becomes a most important issue regarding a spoof attack. So, multimodal biometrics technology has attracted substantial interest for its highest user acceptance, high security, high accuracy, low spoof attack and high recognition
adaboost
- AdaBoost元算法属于boosting系统融合方法中最流行的一种，说白了就是一种串行训练并且最后加权累加的系统融合方法。 具体的流程是：每一个训练样例都赋予相同的权重，并且权重满足归一化，经过第一个分类器分类之后， 计算第一个分类器的权重alpha值，并且更新每一个训练样例的权重，然后再进行第二个分类器的训练，相同的方法....... 直到错误率为0或者达到指定的训练轮数，其中最后预测的标签计算是各系统*alpha的加权和，然后sign（预测值）。 可以看出，训练流程是串行的
NumberPlateRecognition
- 本程序融合机器学习，利用支持向量机训练车牌样本数据，然后用来识别测试数据，测试结果表明，该训练分类器正确率接近99 -This program fusion machine learning, support vector machine training license plate sample data were then used to identify the test data, test results show that the classifier is trained prop
245237271lbp_matlab
- lbp 源码详细讲解了lbp的过程，值得一看-lbp his code is well commented, which enables the adjusting of the HOG parameters. This code was developed for the work: O. Ludwig, D. Delgado, V. Goncalves, and U. Nunes, Trainable Classifier-Fusion Schemes: An Application To
one
- 基于叶片数字图像的植物识别是自动植物分类研究的热点。但是随着植物种类的增加，传统的分类方法由 于提取的特征比较单一或者分类器结构过于简单，导致叶片识别率较低。为此，本文提出使用纹理特征结合形状 特征进行识别，并且使用深度信念网络构架作为分类器。纹理特征通过局部二值模式、Gabor 滤波和灰度共生矩阵 方法得到。而形状特征向量由 Hu 氏不变量和傅里叶描述子组成。为了避免过拟合现象，使用“dropout”方法训练 深度信念网络。这种基于多特征融合的深度信念网络的植物识别方法-Plant based