视觉词袋模型（Bow）

BoW起始可以理解为一种直方图统计，开始是用于自然语言处理和信息检索中的一种简单的文档表示方法。 和histogram 类似，BoW也只是统计频率信息，并没有序列信息。而和histogram不同的是，histogram一般统计的某个区间的频数，BoW是选择words字典，然后统计字典中每个单词出现的次数。

视觉词袋大概过程首先提取图像集特征的集合，然后通过聚类的方法聚出若干类，将这些类作为dictionary，即相当于words，最后每个图像统计字典中words出现的频数作为输出向量，就可以用于后续的分类、检索等操作。

以sift特征为例，假设图像集中包含人脸、自行车、吉他等，我们首先对每幅图像提取sift特征，然后使用如kmeans等聚类方法，进行聚类得到码本(dictionary)

1.读图

def gettestfiles():
        imlist={}
        count=0
        for each in glob(r'./images/test/' + "*"):
            word= each.split("/")[-1]
            print( " #### Reading image category ", word, " ##### ")
            imlist[word]=[]
            for imagefile in glob(each+'/*'):
                im=cv2.imread(imagefile, 0)
                imlist[word].append(im)
                count +=1
        return [imlist, count]

2.sift特征

def trainModel(self):
        """
        This method contains the entire module 
        required for training the bag of visual words model

        Use of helper functions will be extensive.

        """

        # read file. prepare file lists.
        #self.images, self.trainImageCount = self.file_helper.getFiles()
        # extract SIFT Features from each image
        label_count = 0 
        for word in self.images.keys():
            self.name_dict[str(label_count)] = word
            print ("Computing Features for ", word)
            for im in self.images[word]:
                # cv2.imshow("im", im)
                # cv2.waitKey()
                self.train_labels = np.append(self.train_labels, label_count)
                kp, des = self.im_helper.features(im)
                self.descriptor_list.append(des)

            label_count += 1
class ImageHelpers:
	def __init__(self):
		self.sift_object = cv2.xfeatures2d.SIFT_create()

	def gray(self, image):
		gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
		return gray

	def features(self, image):
		keypoints, descriptors = self.sift_object.detectAndCompute(image, None)
		return [keypoints, descriptors]

这里得到了整个图像集的sift特征，des为128维，这里可以采用pca降维
聚类，Kmeans

# perform clustering
        bov_descriptor_stack = self.bov_helper.formatND(self.descriptor_list)
        self.bov_helper.cluster()
        self.bov_helper.developVocabulary(n_images = self.trainImageCount, descriptor_list=self.descriptor_list)
def formatND(self, l):
		"""	
		restructures list into vstack array of shape
		M samples x N features for sklearn

		"""
		vStack = np.array(l[0])
		for remaining in l[1:]:
			vStack = np.vstack((vStack, remaining))
		self.descriptor_vstack = vStack.copy()
		return vStack
def cluster(self):
		"""	
		cluster using KMeans algorithm, 

		"""
		self.kmeans_ret = self.kmeans_obj.fit_predict(self.descriptor_vstack)

	def developVocabulary(self,n_images, descriptor_list, kmeans_ret = None):
		
		"""
		Each cluster denotes a particular visual word 
		Every image can be represeted as a combination of multiple 
		visual words. The best method is to generate a sparse histogram
		that contains the frequency of occurence of each visual word 

		Thus the vocabulary comprises of a set of histograms of encompassing
		all descriptions for all images

		"""

		self.mega_histogram = np.array([np.zeros(self.n_clusters) for i in range(n_images)])
		old_count = 0
		for i in range(n_images):
			l = len(descriptor_list[i])
			for j in range(l):
				if kmeans_ret is None:
					idx = self.kmeans_ret[old_count+j]
				else:
					idx = kmeans_ret[old_count+j]
				self.mega_histogram[i][idx] += 1
			old_count += l
		print ("Vocabulary Histogram Generated")

分类：SVM

self.bov_helper.standardize()
self.bov_helper.train(self.train_labels)
def standardize(self, std=None):
		"""
		
		standardize is required to normalize the distribution
		wrt sample size and features. If not normalized, the classifier may become
		biased due to steep variances.

		"""
		if std is None:
			self.scale = StandardScaler().fit(self.mega_histogram)
			self.mega_histogram = self.scale.transform(self.mega_histogram)
		else:
			print( "STD not none. External STD supplied")
			self.mega_histogram = std.transform(self.mega_histogram)
def train(self, train_labels):
		"""
		uses sklearn.svm.SVC classifier (SVM) 


		"""
		print ("Training SVM")
		print (self.clf)
		print ("Train labels", train_labels)
		self.clf.fit(self.mega_histogram, train_labels)
		print ("Training completed")

参考：代码