Description: 结合分级关键点互相关迭代法与搜索空间标记法,设计了一种有效提高图像相关匹配速度的算法。
其中分级关键点互相关迭代算法快速实现了由重要到不重要像素点的逐级迭代互相关匹配计算,算法在保
证精度的前提下可以随时结束并输出相关匹配值 而搜索空间标记法则能快速排除掉大量参数空间内不可
能匹配的点。实验证明,这种算法能在正确配准图像的前提下大幅度提高匹配速度。-Combination of inter-related key points classification iteration method with search space notation, design an effective image correlation matching to improve the speed of the algorithm. One key point grading iterative cross-correlation algorithm for the rapid realization of important to unimportant by pixel matching level iterative cross-correlation calculation, the algorithm to ensure the accuracy of the premise can be concluded and the output value of the relevant search space matching tag rules quickly ruled out a large number of parameter space points can not be matched. Experiments show that this algorithm can be in the right image registration under the premise of substantial increase in matching speed. Platform: |
Size: 99328 |
Author:李锋 |
Hits:
Description: naive bayes方法是用于分类的一个传统方法，它是产生的比较早的一个方法，分类的准确度比较高。-naive bayes method is used for the classification of a traditional method, which is generated as early as one way of comparison, classification accuracy is relatively high. Platform: |
Size: 1024 |
Author:李萍 |
Hits:
Description: 很好用的svm工具箱，dagsvm对于图像分类效果非常好，分类精度很高，代码清洗简单。-Good use of SVM Toolbox, dagsvm for image classification effect is very good, very high classification accuracy, code cleaning easy. Platform: |
Size: 5120 |
Author:tang |
Hits:
Description: 多维信息在改善沿海地区图像分类精度中的应用方法-Multi-dimensional information to improve the image classification accuracy in coastal areas of application method Platform: |
Size: 216064 |
Author:sds |
Hits:
Description: 利用图像增强技术对气象卫星云图进行全局性的分类，因此极大地提高了准确性-Use of satellite cloud image enhancement technology for overall classification, it greatly improves the accuracy of Platform: |
Size: 500736 |
Author:李若彤 |
Hits:
Description: 指纹图像的质量测量与评价,在指纹图像分割、增强及指纹匹配等环节都有重要应用. 同时,指纹图像的质量分类,对指纹识别算法的适用性研究也有重要意义. 本文提出一种基于支持向量机的指纹图像质量分类方法.该方法选择梯度、Gabor特征、方向对比度等指标,利用支持向量机有效实现指纹图像质量分类. 并采用少类样本合成过采样技术( SMOTE)降低指纹图像质量好坏的类别不平衡问题对分类的影响. 理论分析和实验结果都表明该方法能够较为有效地提高指纹图像质量分类的正确率.-Fingerprint Image Quality Measurement and evaluation, in the fingerprint image segmentation, enhancement and fingerprint matching has important applications such links. Meanwhile, the quality of fingerprint image classification, on the applicability of fingerprint recognition algorithm is also important. In this paper, based on support vector machine classification of fingerprint image quality. The method chosen gradient, Gabor features, such as indicators of the direction of contrast, the effective use of support vector machine classification of fingerprint image quality. and use a small sample of synthetic over-sampling technique class (SMOTE) lower quality fingerprint image the type of imbalance bad influence on the classification. Theoretical analysis and experimental results show that the method can be used effectively to improve the quality of fingerprint image classification accuracy. Platform: |
Size: 564224 |
Author:郭事业 |
Hits:
Description: 的研究彩色数字图像的计算机分类识别方法并应用于古瓷片的自动分类。方法提出
了一种色彩纹理特征的提取模型，采用该模型，利用IGabor滤波器提取数字图像的色彩纹理特征，
并构造支持向量分类机(SVM)分类器组。结果实现了高准确率多类别图像的自动分类识别，并
成功应用于古瓷片的自动分类。结论色彩纹理特征提取方法将颜色与纹理进行融合，增强了数
字图像之间的特征区分能力。-Study color digital image classification and recognition method and a computer chip used in the automatic classification of porcelain. Method presents a color texture feature extraction model, using the model, the use of IGabor filter extracts the color digital image texture features, and construct support vector classification machine (SVM) classifier group. Results to achieve a high accuracy automatic multi-class image classification and recognition, and successfully applied to automatic classification of porcelain pieces. Conclusion color texture feature extraction method for integration of color and texture to enhance the digital image characteristics between the ability to distinguish between. Platform: |
Size: 346112 |
Author:刘东 |
Hits:
Description: 该文提出了一种在基于离散采弦变换(DCT，Discrete Coslne‘nansform)压缩域进行纹理图
像分类的方法．此方法主要利用了DCT域能量具有方向性的特电，直接在辩程长编码(RLE，Rlm I。ength
E眦ollⅢg)形成的码流中根据这种方向性来提取、组织特征矢址，对纹理图像进行分粪．此方法只需对压缩
【封像世行简单的Hu圩maⅡ解码．要处理的数据量较少，处理速度快实验结果表明．这种分类方法具有较高
的准确性．-This paper presents a string taken based on the discrete transform (DCT, Discrete Coslne' nansform) Compressed domain texture image classification method. The main advantage of this method has a directional DCT domain specific electrical energy directly in the debate process length coding (RLE, Rlm I. Ength E canthus oll Ⅲ g) formed the basis of this stream in the direction to extract, organize feature vector address points on the texture image manure. This method only on the compression seal as the World Bank [Hu Wei ma Ⅱ simple decoding. Small amount of data to be processed, fast processing speed results show. This classification method has high accuracy. Platform: |
Size: 299008 |
Author:刘东 |
Hits:
Description: 由于K-means 聚类方法对遥感图像进行分类时，对训练样本的选取依赖性很大，容易陷入局部最优的陷阱的情况，本文提出利用模拟退化算法对K-means 的聚类进行优化以获得
全局最优解的分类新方案。并以多波段影像为例进行验证分析，结果表明该方法可行，收敛
结果优于K-means 聚类算法，分类精度相对传统的K-means 算法更高。-Because K-means clustering classification depend on the training sample selection,great easy to fall into local optimum, in this paper , using Simulated Annealing algorithm to optimize K-means cluster analysis to obtain the global best optimal solution of the classification of 20 the new program. And multi-band image as an example to verify the analysis results, showing that the method is feasible, convergence results are better than K-means clustering algorithm, classification accuracy compared to traditional K-means algorithm is higher Platform: |
Size: 438272 |
Author:huaoking |
Hits:
Description: 很好用的svm工具箱，dagsvm对于图像分类效果非常好，分类精度很高，代码清洗简单。-Good use of SVM Toolbox, dagsvm for image classification effect is very good, very high classification accuracy, code cleaning easy. Platform: |
Size: 5120 |
Author:trysfi |
Hits:
Description: 高分辨率遥感影像的支持张量机分类方法，此方法能够利用少量的训练样本实现更优的分类精度。-Support tensor machines resolution remote sensing image classification method, and this method can use a small amount of training samples to achieve better classification accuracy. Platform: |
Size: 485376 |
Author:刘青松 |
Hits:
Description: 这是用ELM（极限学习机）做的关于图像识别的分类实验，有数据，有程序，有训练时间，测试时间和精度-It is used ELM (Extreme Learning Machine) to do experiments on the classification of image recognition, has data, procedures, training time, test time and accuracy Platform: |
Size: 117760 |
Author:rentingting |
Hits:
Description: 在图像精度评价中，主要用于比较分类结果和实际测得值，可以把分类结果的精度显示在一个混淆矩阵里面。混淆矩阵是通过将每个实测像元的位置和分类与分类图像中的相应位置和分类像比较计算的。-In the image to uate the accuracy, mainly for comparison of classification results and the actual measured value, the accuracy of the classification results are displayed in a confusion matrix inside. The confusion matrix is measured by each pixel position and image classification and classification in the appropriate location and classified as comparative calculations. Platform: |
Size: 1024 |
Author:晁凤云 |
Hits:
Description: 针对视觉字典的最佳表示方式、图像分类任务中亟需计算效率高、存储代价小、分类准确度高的算法等难题，提出了几种创新的算法。-Aiming at the problem of the best representation of visual dictionary and the need of high efficiency, low memory cost and high classification accuracy in image classification task, several innovative algorithms are proposed. Platform: |
Size: 20410368 |
Author:缪振振 |
Hits:
Description: 对分类后的图像求取几个经典的分类精度数据，一共包含是三个。-Image sorting after obtaining several classical classification accuracy of data, contains a total of three. Platform: |
Size: 2048 |
Author:naivoten |
Hits:
Description: Recent research has shown the speed advantage of extreme learning machine (ELM) and the accuracy
advantage of sparse representation classification (SRC) in the area of image classification. Those two
methods, however, have their respective drawbacks, e.g., in general, ELM is known to be less robust to
noise while SRC is known to be time-consuming. Platform: |
Size: 7000064 |
Author:mmaawadi
|
Hits:
Search - accuracy of image classification