Python OpenCV 物体识别

基于Python OpenCV 隐马尔可夫模型 物体识别，汽车飞机摩托车。

网上自己收集的图片进行识别的，准确率可以达到60% 其中通过star 和sift 特征检测。

SIFT算法

来源：
尺度不变特征转换(Scale-invariant feature transform或SIFT)算法是一种特征提取的方法。它在尺度空间中寻找极值点，并提取出其位置、尺度、旋转不变量，并以此作为特征点并利用特征点的邻域产生特征向量。SIFT算法对于光线、噪声、和微小视角改变的容忍度相当高，且对于部分遮挡的物体也有较高的识别相率。
SIFT算法适合于识别旋转度达60度的平面形状，或是旋转度达到20度的三维物体。
SIFT算法对模糊的图像和边缘平滑的图像，检测出的特征点过少，对圆更是无能为力

import os
import warnings
import numpy as np
import cv2 as cv

import hmmlearn.hmm as hl

warnings.filterwarnings('ignore',category=DeprecationWarning)

np.seterr(all='ignore')


def search_objects(directory):
    directory = os.path.normpath(directory)
    if not os.path.isdir(directory):
        raise IOError("the directory '"+ directory + \
                      "' doesn't exist")
    objects ={}
    for curdir ,subdirs, files in os.walk(directory):
        for jpeg in (file for file in files if file.endswith('.jpg')):
            path = os.path.join(curdir,jpeg)
            label = path.split(os.path.sep)[-2]
            if label not in objects:
                objects[label]=[]
            objects[label].append(path)
    return objects


train_objects=search_objects('data/objects/training')
print(train_objects)

train_x, train_y =[],[]
for label, filenames in train_objects.items():
    descs = np.array([])
    for filename in filenames:
        image = cv.imread(filename)
        gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)

        #调整大小
        h,w =gray.shape[:2]
        f =200/min(h,w)
        gray = cv.resize(gray,None,fx=f,fy=f)
        star=cv.xfeatures2d.StarDetector_create()
        keypoints = star.detect(gray)
        sift = cv.xfeatures2d.SIFT_create()

        _,desc = sift.compute(gray,keypoints)
        if len(descs)==0:
            descs=desc
        else:
            descs=np.append(descs,desc,axis=0)
    train_x.append(descs)
    train_y.append(label)
models={}
for descs, label in zip(train_x,train_y):
    model= hl.GaussianHMM(n_components=4,
                          covariance_type='diag',
                          n_iter=1000
                           )
    models[label]=model.fit(descs)

test_objects=search_objects('data/objects/testing')
print(train_objects)

test_x, test_y, test_z=[],[],[]
for label, filenames in test_objects.items():
    test_z.append([])
    descs = np.array([])
    for filename in filenames:
        image = cv.imread(filename)
        test_z[-1].append(image)

        gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)

        #调整大小
        h,w =gray.shape[:2]
        f =200/min(h,w)
        gray = cv.resize(gray,None,fx=f,fy=f)
        star=cv.xfeatures2d.StarDetector_create()
        keypoints = star.detect(gray)
        sift = cv.xfeatures2d.SIFT_create()

        _,desc = sift.compute(gray,keypoints)
        if len(descs)==0:
            descs=desc
        else:
            descs=np.append(descs,desc,axis=0)
    test_x.append(descs)
    test_y.append(label)
pred_test_y=[]
for descs in test_x:
    best_score, best_label =None,None
    for label, model in models.items():
        score=model.score(descs)
        if(best_score is None)or(best_score<score):
            best_score, best_label = score,label
    pred_test_y.append(best_label)
i=0
for label,pred_label,images in zip(test_y,pred_test_y,test_z):
    for image in images:
        i+=1
        cv.imshow("{}-{} {} {}".format(i,label,'=='
                   if label == pred_label else '!=',pred_label),image)

cv.waitKey()