1. Johngo学长首页
  2. 技术点详细复盘专题
  3. 人工智能

基于KNN算法的手写体数字识别

• 人工智能 • 阅读 95

基于KNN算法的手写体数字识别

KNN分类算法是一种经典的分类算法，属于懒惰学习算法的一种。

1.算法原理

工作原理：存在一个样本数据集合，也称作训练样本集，并且样本集中每个数据都存在标签，即我们知道样本集中每一数据与所属分类的对应关系。输入没有标签的新数据后，将新数据的每个特征与样本集中数据对应的特征进行比较，然后算法提取样本集中特征最相似数据（最近邻）的分类。一般来说，我们只选择样本数据集中前k个最相似的数据，这就是kNN算法中k的出处，通常k是不大于20的整数。最后，选择k个最相似数据中出现次数最多的分类，作位新数据的分类。

kNN算法的一般流程
1.收集数据：可以使用任何方法。
2.准备数据：距离计算所需要的数值，最好是结构化的数据格式。
3.分析数据：可以使用任何方法。
4.训练算法：此步骤不使用与kNN算法
5.测试算法：计算错误率
6.使用算法：首先需要输入样本数据和结构化的输出结果，然后运行kNN算法判定输入数据分别属于那个分类，最后应用对计算出的分类执行后续处理。

2.手写识别系统大致流程

使用kNN算法的手写识别系统
1.收集数据：提供文本文件
2.准备数据：编写函数img2vector(),将图像格式转换为分类器使用的向量格式。
3.分析数据：在Python命令提示符中检查数据，确保它符合要求。
4.训练算法：此步骤不适用与kNN算法
5.测试算法：编写函数使用提供的部分数据集作为测试样本，测试样本与非测试样本的区别在于测试样本是已经完成分类的数据，如果预测分类与实际类别不同，则标记为一个错误。
6.使用算法：使用已编写好的算法来对测试样本进行测试

3.算法各模块程序介绍

3.1.kNN分类算法

伪代码
计算已知类别属性的数据集中的每个点依次执行以下操作：
1.计算已知类别数据集中的点与当前点之间的距离；
2.按照距离递增次序排序；
3.选取与当前点距离最小的k个点（此处取k=3）；
4.确定前k个点所在类别的出现频率；
5.返回前k个点出现频率最高的类别作为当前点的预测分类。

#算法需要调用的python库
from numpy import *
import operator
from os import listdir
from skimage import data
import matplotlib.pyplot as plt
from skimage import io,color,transform

kNN算法程序：

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5            #距离计算
    sortedDistIndicies = distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]  #选择距离最小的k个点
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True) #排序
    return sortedClassCount[0][0]

3.2.归一化数据（手写识别不适用）

由于可能遇到的特征值量纲不同，而形成干扰，故需对数据进行归一化。

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m,1))
    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

3.3.将图像转换为测试向量

由于本系统的训练测试数据是由32*32的txt文件构成，且文件名代表该样本标签，如下图所示：

基于KNN算法的手写体数字识别

基于KNN算法的手写体数字识别
故需要将其样本格式化处理为一个向量 

def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect

3.4.测试算法


def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' %fileNameStr)
    testFileList = listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' %fileNameStr)
        classifierResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came back with: %d, the real answer is: %d" %(classifierResult,classNumStr))
        if(classifierResult != classNumStr):
            errorCount += 1.0

    print("\nthe total number of errors is: %d" %errorCount)
    print("\nthe total error rate is: %f" %(errorCount/float(mTest)))

测试效果如下：

基于KNN算法的手写体数字识别
基于KNN算法的手写体数字识别
基于KNN算法的手写体数字识别

3.5.应用图像处理函数

基于KNN算法的手写体数字识别

由于应用是使用图像作为输入的，所以需要将图像转换成32*32的txt文本格式


def photosDeal():
   filename = '/9_1'
   mytest1 = io.imread('./handwriting_Yqx'+filename+'.png')
   print('the shape is  {}'.format(mytest1.shape))
   img_gray = color.rgb2gray(mytest1)
   img_high = img_gray.shape[0]
   img_width = img_gray.shape[1]
   print('the gary_img shape is  {}'.format(img_gray.shape))
   print("the high of img is %d,the width is %d" %(img_high,img_width))
   for i in range(img_high):
       for j in range(img_width):
           if(img_gray[i][j] <= 0.5):
               img_gray[i][j] = 1
           else:
               img_gray[i][j] =0

   dst_img1 = transform.resize(img_gray,(32,32))
   io.imshow(dst_img1)

   result = ''
   for i in range(32):
       for j in range(32):
           result += str(int(dst_img1[i][j]))
       result+= '\n'
   with open('./txtYqx'+filename+'.txt',mode = 'w') as f:
       f.write(result)

基于KNN算法的手写体数字识别

3.6.应用测试程序

完成后对输入图像进行测试

 #测试函数
def YqxTrail():
   hwLabels = []
   trainingFileList = listdir('trainingDigits')
   m = len(trainingFileList)
   trainingMat = zeros((m,1024))
   for i in range(m):
       fileNameStr = trainingFileList[i]
       fileStr = fileNameStr.split('.')[0]
       classNumStr = int(fileStr.split('_')[0])#从文件名中解析分类数据
       hwLabels.append(classNumStr)
       trainingMat[i,:] = img2vector('trainingDigits/%s' %fileNameStr)
   testFileList = listdir('txtYqx')
   errorCount = 0.0
   mTest = len(testFileList)
   for i in range(mTest):
       fileNameStr = testFileList[i]
       fileStr = fileNameStr.split('.')[0]
       classNumStr = int(fileStr.split('_')[0])
       vectorUnderTest = img2vector('txtYqx/%s' %fileNameStr)
       classifierResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
       print("the classifier came back with: %d, the real answer is: %d" %(classifierResult,classNumStr))
       if(classifierResult != classNumStr):
          errorCount += 1.0

   print("\nthe total number of errors is: %d" %errorCount)
   print("\nthe total error rate is: %f" %(errorCount/float(mTest)))

4.程序运行效果

4.1.程序总体

kNN.py

from numpy import *
import operator
from os import listdir
from skimage import data
import matplotlib.pyplot as plt
from skimage import io,color,transform

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def createDataSet():
    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    return group, labels

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m,1))
    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
        print("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]):
            errorCount += 1.0
    print("the total error rate is: %f" % (errorCount/float(numTestVecs)))
    print(errorCount)

def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(input("liters of iceCream consumed per year?"))
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr - minVals)/ranges,normMat,datingLabels,3)
    print("You will probably like this person:",resultList[classifierResult-1])

#将图像矩阵转换为矩阵
def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect

#手写数字识别系统的测试函数
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])#从文件名中解析分类数据
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' %fileNameStr)
    testFileList = listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' %fileNameStr)
        classifierResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came back with: %d, the real answer is: %d" %(classifierResult,classNumStr))
        if(classifierResult != classNumStr):
            errorCount += 1.0

    print("\nthe total number of errors is: %d" %errorCount)
    print("\nthe total error rate is: %f" %(errorCount/float(mTest)))

#应用样本处理函数，将图像变为符合要求的测试样本（32*32的txt文本）
def photosDeal():
   filename = '/9_1'
   mytest1 = io.imread('./handwriting_Yqx'+filename+'.png')
   print('the shape is  {}'.format(mytest1.shape))
   img_gray = color.rgb2gray(mytest1) #灰度化图像
   img_high = img_gray.shape[0]
   img_width = img_gray.shape[1]
   print('the gary_img shape is  {}'.format(img_gray.shape))
   print("the high of img is %d,the width is %d" %(img_high,img_width))
   for i in range(img_high):#二值化图像
       for j in range(img_width):
           if(img_gray[i][j]  0.5):
               img_gray[i][j] = 1
           else:
               img_gray[i][j] =0

   dst_img1 = transform.resize(img_gray,(32,32)) #缩放图像
   io.imshow(dst_img1)
   #plt.show()

   #将图片转为txt
   result = ''
   for i in range(32):
       for j in range(32):
           result += str(int(dst_img1[i][j]))
       result+= '\n'
   with open('./txtYqx'+filename+'.txt',mode = 'w') as f:
       f.write(result)

   #测试函数
def YqxTrail():
   hwLabels = []
   trainingFileList = listdir('trainingDigits')
   m = len(trainingFileList)
   trainingMat = zeros((m,1024))
   for i in range(m):
       fileNameStr = trainingFileList[i]
       fileStr = fileNameStr.split('.')[0]
       classNumStr = int(fileStr.split('_')[0])#从文件名中解析分类数据
       hwLabels.append(classNumStr)
       trainingMat[i,:] = img2vector('trainingDigits/%s' %fileNameStr)
   testFileList = listdir('txtYqx')
   errorCount = 0.0
   mTest = len(testFileList)
   for i in range(mTest):
       fileNameStr = testFileList[i]
       fileStr = fileNameStr.split('.')[0]
       classNumStr = int(fileStr.split('_')[0])
       vectorUnderTest = img2vector('txtYqx/%s' %fileNameStr)
       classifierResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
       print("the classifier came back with: %d, the real answer is: %d" %(classifierResult,classNumStr))
       if(classifierResult != classNumStr):
          errorCount += 1.0

   print("\nthe total number of errors is: %d" %errorCount)
   print("\nthe total error rate is: %f" %(errorCount/float(mTest)))

kNNTest.py

import kNN
from numpy import *
import importlib
import matplotlib
import matplotlib.pyplot as plt #导入matplotlib库,并将matplotlib.pyplot模块命名为plt
#kNN.photosDeal()
kNN.YqxTrail()

4.2.运行效果：

基于KNN算法的手写体数字识别
由于训练样本较少，故错误率较高。

Original: https://blog.csdn.net/secretboys/article/details/121805574
Author: 僚机武士
Title: 基于KNN算法的手写体数字识别

原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/664471/

转载文章受原作者版权保护。转载请注明原作者出处！

赞 (0)
0

【自取】最近整理的，有需要可以领取学习：



Linux核心资料大放送~

全栈面试题汇总（持续更新&可下载）

一个提高学习100%效率的工具！

【超详细】深度学习面试题目！

LeetCode Python刷题答案下载！

LeetCode Java版刷题答案下载！

LeetCode C++ 版本，抓紧保存！

LeetCode GO语言 刷题答案下载！

大家都在看

亲爱的 Coder【最近整理，可免费获取】👉 最新必读书单  | 👏 面试题下载  | 🌎 免费的AI知识星球