原文
Optical recognition of handwritten digits dataset
**Data Set Characteristics:**
Number of Instances: 5620
Number of Attributes: 64
Attribute Information: 8x8 image of integer pixels in the range0..16.
Missing Attribute Values: None
Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)
Date: July; 1998
This is a copy of the test set of the UCI ML hand-written digitsdatasets
https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits
The data set contains images of hand-written digits: 10 classeswhere each class refers to a digit.
Preprocessing programs made available by NIST were used to extractnormalized bitmaps of handwritten digits from a preprinted form. From a totalof 43 people, 30 contributed to the training set and different 13 to the testset. 32x32 bitmaps are divided into nonoverlapping blocks of 4x4 and the numberof on pixels are counted in each block. This generates an input matrix of 8x8where each element is an integer in the range 0..16. This reducesdimensionality and gives invariance to small distortions.
For info on NIST preprocessing routines, see M. D. Garris, J. L.Blue, G.T. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, andC.L. Wilson, NIST Form-Based Handprint Recognition System,NISTIR 5469,1994.
topic:: References
- C. Kaynak (1995) Methods of Combining Multiple Classifiers and TheirApplications to Handwritten Digit Recognition, MSc Thesis, Institute ofGraduate Studies in Science and Engineering, Bogazici University.
- E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika.
- Ken Tang and Ponnuthurai N. Suganthan and Xi Yao and A. Kai Qin.Linear dimensionalityreduction using relevance weighted LDA. School ofElectrical and Electronic Engineering Nanyang Technological University.2005.
- Claudio Gentile. A New Approximate Maximal MarginClassification Algorithm. NIPS. 2000.
译文
手写数字数据集的光学识别
**数据集特征：**
实例数：5620
属性数：64
属性信息：0..16范围内整数像素的8x8图像。
缺少属性值：无
创建者：E.Alpaydin（Alpaydin'@'教育部)
日期：1998年7月
这是UCI ML手写数字数据集测试集的副本
https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+手写+数字
数据集包含手写数字的图像：10个类，其中每个类引用一个数字。
使用NIST提供的预处理程序从预打印表单中提取手写数字的标准化位图。在总共43人中，30人参加了培训，13人参加了测试。32x32位图被分成4x4的非重叠块，每个块中的on像素数被计数。这将生成一个8x8的输入矩阵，其中每个元素都是0..16范围内的整数。这降低了维数，并赋予小变形不变性。
有关NIST预处理程序的信息，请参见M.D.Garris、J.L.Blue、G.T.Candela、D.L.Dimmick、J.Geist、P.J.Grother、S.A.Janet和C.L.Wilson，NIST基于表格的手印识别系统，NISTIR54691994。
主题：：参考文献
- C.Kaynak（1995）多分类器组合方法及其在手写数字识别中的应用，博加西大学理工研究所硕士论文。
- E.Alpaydin，C.Kaynak（1998）《级联分类器》，Kybernetika。
- 邓肯、庞努图赖、苏嘉全、奚瑶、秦启红。使用相关加权LDA进行线性维数推导。南洋理工大学电气与电子工程学院.2005。
克劳迪奥·金蒂莱。一种新的近似最大边缘分类算法。尼普斯。2000
—————————————————————————————————
软件安全测试
https://study.163.com/course/courseMain.htm?courseId=1209779852&share=2&shareId=480000002205486
接口自动化测试
https://study.163.com/course/courseMain.htm?courseId=1209794815&share=2&shareId=480000002205486
DevOps 和Jenkins之DevOps
https://study.163.com/course/courseMain.htm?courseId=1209817844&share=2&shareId=480000002205486
DevOps与Jenkins 2.0之Jenkins
https://study.163.com/course/courseMain.htm?courseId=1209819843&share=2&shareId=480000002205486
Selenium自动化测试
https://study.163.com/course/courseMain.htm?courseId=1209835807&share=2&shareId=480000002205486
性能测试第1季:性能测试基础知识
https://study.163.com/course/courseMain.htm?courseId=1209852815&share=2&shareId=480000002205486
性能测试第2季:LoadRunner12使用
https://study.163.com/course/courseMain.htm?courseId=1209980013&share=2&shareId=480000002205486
性能测试第3季:JMeter工具使用
https://study.163.com/course/courseMain.htm?courseId=1209903814&share=2&shareId=480000002205486
性能测试第4季:监控与调优
https://study.163.com/course/courseMain.htm?courseId=1209959801&share=2&shareId=480000002205486
Django入门
https://study.163.com/course/courseMain.htm?courseId=1210020806&share=2&shareId=480000002205486
啄木鸟顾老师漫谈软件测试
https://study.163.com/course/courseMain.htm?courseId=1209958326&share=2&shareId=480000002205486
