计算机视觉——KNN算法以及手势识别应用

概述

本文介绍了KNN算法的基本原理，以及配合dfift（稠密sift）进行一个手势识别方面的应用

KNN算法原理

KNN算法（K-Nearest Neighbor,K邻近分类法）。看似十分神秘以及高大上，实则相当简单。举一个简单的例子，在一本字典里，有很多不同的单词，它们可能对应着相同的中文意思，比如安静，在字典里它可能是“quiet”，“slience”等等。视觉图像的特征也是如此，描述视觉特征的一些信息可能属于同一类，我们可以给它们打上标签，然后储存在计算机的字典里。而在python里有这么一个用法，就叫做字典。配合字典的一些功能特性，我们可以实现KNN算法。如果对于字典的用法比较陌生，这里有一篇CSDN社区其他博主写的一篇文章，可以参考一下。

https://blog.csdn.net/qq_40678222/article/details/83448740

KNN二维分类器模型

# -*- coding: utf-8 -*-
from numpy.random import randn
import pickle
from pylab import *

# create sample data of 2D points
n = 200
# two normal distributions
class_1 = 0.6 * randn(n,2)
class_2 = 1.2 * randn(n,2) + array([5,1])
labels = hstack((ones(n),-ones(n)))
# save with Pickle
#with open('points_normal.pkl', 'w') as f:
with open('points_normal.pkl', 'w') as f:
    pickle.dump(class_1,f)
    pickle.dump(class_2,f)
    pickle.dump(labels,f)
# normal distribution and ring around it
print "save OK!"
class_1 = 0.6 * randn(n,2)
r = 0.8 * randn(n,1) + 5
angle = 2*pi * randn(n,1)
class_2 = hstack((r*cos(angle),r*sin(angle)))
labels = hstack((ones(n),-ones(n)))
# save with Pickle
#with open('points_ring.pkl', 'w') as f:
with open('points_ring.pkl', 'w') as f:
    pickle.dump(class_1,f)
    pickle.dump(class_2,f)
    pickle.dump(labels,f)
    
print "save OK!"

这里进行了两次保存，第二次需要改一下代码中的文件名，这样我们可以的到一个训练集以及一个测试集。
我们可以利用一段代码来可视化KNN算法的分类效果

# -*- coding: utf-8 -*-
import pickle
from pylab import *
from PCV.classifiers import knn
from PCV.tools import imtools

pklist=['points_normal.pkl','points_ring.pkl']

figure()

# load 2D points using Pickle
for i, pklfile in enumerate(pklist):
    with open(pklfile, 'r') as f:
        class_1 = pickle.load(f)
        class_2 = pickle.load(f)
        labels = pickle.load(f)
    # load test data using Pickle
    with open(pklfile[:-4]+'_test.pkl', 'r') as f:
        class_1 = pickle.load(f)
        class_2 = pickle.load(f)
        labels = pickle.load(f)

    model = knn.KnnClassifier(labels,vstack((class_1,class_2)))
    # test on the first point
    print model.classify(class_1[0])

    #define function for plotting
    def classify(x,y,model=model):
        return array([model.classify([xx,yy]) for (xx,yy) in zip(x,y)])

    # lot the classification boundary
    subplot(1,2,i+1)
    imtools.plot_2D_boundary([-6,6,-6,6],[class_1,class_2],classify,[1,-1])
    titlename=pklfile[:-4]
    title(titlename)
show()

DSIFT

dsift（dense—sift），稠密sift，其特点如字面意思，它是密集采样的sift描述子。具体操作过程可以参考下面这篇博客

https://blog.csdn.net/langb2014/article/details/48738669
这里我们利用对一张图片进行了DSIFT特征提取，并记录了它的可视化结果

# -*- coding: utf-8 -*-
from PCV.localdescriptors import sift, dsift
from pylab import  *
from PIL import Image

dsift.process_image_dsift('gesture/empire.jpg','empire.dsift',90,40,True)
l,d = sift.read_features_from_file('empire.dsift')
im = array(Image.open('gesture/empire.jpg'))
sift.plot_features(im,l,True)
title('dense SIFT')
show()

可视化结果：

手势识别应用

我们要利用上面提到的KNN算法以及DSIFT，实现手势识别

手势识别具体流程

• 提取dsift特征
• 利用KNN算法构建“字典”
• 使用测试集训练模型

这是手势意义以及对应dense-sift的可视化
# -*- coding: utf-8 -*-
import os
from PCV.localdescriptors import sift, dsift
from pylab import  *
from PIL import Image

imlist=['gesture/train/C-uniform02.ppm','gesture/train/B-uniform01.ppm',
        'gesture/train/A-uniform01.ppm','gesture/train/Five-uniform01.ppm',
        'gesture/train/Point-uniform01.ppm','gesture/train/V-uniform01.ppm']

figure()
for i, im in enumerate(imlist):
    print im
    dsift.process_image_dsift(im,im[:-3]+'dsift',10,5,True)
    l,d = sift.read_features_from_file(im[:-3]+'dsift')
    dirpath, filename=os.path.split(im)
    im = array(Image.open(im))
    #显示手势含义title
    titlename=filename[:-14]
    subplot(2,3,i+1)
    sift.plot_features(im,l,True)
    title(titlename)
show()

下面是针对我们一个训练集的训练结果

# -*- coding: utf-8 -*-
from PCV.localdescriptors import dsift
import os
from PCV.localdescriptors import sift
from pylab import *
from PCV.classifiers import knn

def get_imagelist(path):
    """    Returns a list of filenames for
        all jpg images in a directory. """

    return [os.path.join(path,f) for f in os.listdir(path) if f.endswith('.ppm')]

def read_gesture_features_labels(path):
    # create list of all files ending in .dsift
    featlist = [os.path.join(path,f) for f in os.listdir(path) if f.endswith('.dsift')]
    # read the features
    features = []
    for featfile in featlist:
        l,d = sift.read_features_from_file(featfile)
        features.append(d.flatten())
    features = array(features)
    # create labels
    labels = [featfile.split('/')[-1][0] for featfile in featlist]
    return features,array(labels)

def print_confusion(res,labels,classnames):
    n = len(classnames)
    # confusion matrix
    class_ind = dict([(classnames[i],i) for i in range(n)])
    confuse = zeros((n,n))
    for i in range(len(test_labels)):
        confuse[class_ind[res[i]],class_ind[test_labels[i]]] += 1
    print 'Confusion matrix for'
    print classnames
    print confuse

filelist_train = get_imagelist('gesture/train')
filelist_test = get_imagelist('gesture/test')
imlist=filelist_train+filelist_test

# process images at fixed size (50,50)
for filename in imlist:
    featfile = filename[:-3]+'dsift'
    dsift.process_image_dsift(filename,featfile,10,5,resize=(50,50))

features,labels = read_gesture_features_labels('gesture/train/')
test_features,test_labels = read_gesture_features_labels('gesture/test/')
classnames = unique(labels)

# test kNN
k = 1
knn_classifier = knn.KnnClassifier(labels,features)
res = array([knn_classifier.classify(test_features[i],k) for i in
range(len(test_labels))])
# accuracy
acc = sum(1.0*(res==test_labels)) / len(test_labels)
print 'Accuracy:', acc

print_confusion(res,test_labels,classnames)

修改一行代码：
dsift.process_image_dsift(filename,featfile,10,5,resize=(100,100))，把第一次中的50 * 50改为100 * 100，可以得到如下结果：

在改为100 * 100后，准确率提高了约8个百分点，在原大小下“p”和“v”的较高混淆率也得到了降低。