python类FeatureDetector_create()的实例源码

def get_dense_detector(step=4, levels=7, scale=np.sqrt(2)): 
    """
    Standalone dense detector instantiation
    """
    detector = cv2.FeatureDetector_create('Dense')
    detector.setInt('initXyStep', step)
    # detector.setDouble('initFeatureScale', 0.5)

    detector.setDouble('featureScaleMul', scale)
    detector.setInt('featureScaleLevels', levels)

    detector.setBool('varyImgBoundWithScale', True)
    detector.setBool('varyXyStepWithScale', False)

    # detector = cv2.PyramidAdaptedFeatureDetector(detector, maxLevel=4)
    return detector

def get_detector(detector='dense', step=4, levels=7, scale=np.sqrt(2)): 
    """ Get opencv dense-sampler or specific feature detector """
    if detector == 'dense': 
        return get_dense_detector(step=step, levels=levels, scale=scale)
    else: 
        detector = cv2.FeatureDetector_create(detector)
        return cv2.PyramidAdaptedFeatureDetector(detector, maxLevel=levels)

def test_feature_detector(detector, imfname):
    image = cv2.imread(imfname)
    forb = cv2.FeatureDetector_create(detector)
    # Detect crashes program if image is not greyscale
    t1 = time.time()
    kpts = forb.detect(cv2.cvtColor(image, cv2.COLOR_BGR2GRAY))
    t2 = time.time()
    print detector, 'number of KeyPoint objects', len(kpts), '(time', t2-t1, ')'

    return kpts

def obtainSimilarityScore(img1,img2):
    detector = cv2.FeatureDetector_create("SIFT")
    descriptor = cv2.DescriptorExtractor_create("SIFT")
    skp = detector.detect(img1)
    skp, sd = descriptor.compute(img1, skp)
    tkp = detector.detect(img2)
    tkp, td = descriptor.compute(img2, tkp)
    num1 = 0
    for i in range(len(sd)):
          kp_value_min = np.inf
          kp_value_2min = np.inf
          for j in range(len(td)):
               kp_value = 0
               for k in range(128):
                     kp_value = (sd[i][k]-td[j][k]) *(sd[i][k]-td[j][k]) + kp_value
               if kp_value < kp_value_min:
                     kp_value_2min = kp_value_min
                     kp_value_min = kp_value
          if kp_value_min < 0.8*kp_value_2min:
               num1 = num1+1     
    num2 = 0
    for i in range(len(td)):
          kp_value_min = np.inf
          kp_value_2min = np.inf
          for j in range(len(sd)):
               kp_value = 0
               for k in range(128):
                     kp_value = (td[i][k]-sd[j][k]) *(td[i][k]-sd[j][k]) + kp_value
               if kp_value < kp_value_min:
                     kp_value_2min = kp_value_min
                     kp_value_min = kp_value
          if kp_value_min < 0.8*kp_value_2min:
               num2 = num2+1
    K1 = num1*1.0/len(skp)
    K2 = num2*1.0/len(tkp)
    SimilarityScore  = 100*(K1+K2)*1.0/2    
    return SimilarityScore

def calculate_feature(bin_data):
    """
    calculate the feature data of an image

    parameter :
        'bin_data' is the binary stream format of an image
    return value :
        a tuple of ( keypoints, descriptors, (height,width) )
        keypoints is like [ pt1, pt2, pt3, ... ]
        descriptors is a numpy array
    """
    buff=numpy.frombuffer(bin_data,numpy.uint8)
    img_obj=cv2.imdecode(buff,cv2.CV_LOAD_IMAGE_GRAYSCALE)
    surf=cv2.FeatureDetector_create("SURF")
    surf.setInt("hessianThreshold",400)
    surf_extractor=cv2.DescriptorExtractor_create("SURF")
    keypoints=surf.detect(img_obj,None)
    keypoints,descriptors=surf_extractor.compute(img_obj,keypoints)
    res_keypoints=[]
    for point in keypoints:
        res_keypoints.append(point.pt)
    del buff
    del surf
    del surf_extractor
    del keypoints
    return res_keypoints,numpy.array(descriptors),img_obj.shape

def __init__(self, detector_name, feat_type):
        self.feat_type = feat_type        
        self.detector = cv2.FeatureDetector_create(detector_name)
        self.descriptor_ex = cv2.DescriptorExtractor_create(feat_type)

def find_pupil(gray_image, minsize=.1, maxsize=.5):
    detector = cv2.FeatureDetector_create('MSER')
    features_all = detector.detect(gray_image)
    features_big = [feature for feature in features_all if feature.size > gray_image.shape[0]*minsize]
    features_small = [feature for feature in features_big if feature.size < gray_image.shape[0]*maxsize]
    if len(features_small) == 0:
        return None
    features_sorted = sort_features_by_brightness(gray_image, features_small)
    pupil = features_sorted[0]
    return (int(pupil.pt[0]), int(pupil.pt[1]), int(pupil.size/2))

def _extract_feature(X, feature):
    """Performs feature extraction
        :param X:       data (rows=images, cols=pixels)
        :param feature: which feature to extract
                        - None:   no feature is extracted
                        - "gray": grayscale features
                        - "rgb":  RGB features
                        - "hsv":  HSV features
                        - "surf": SURF features
                        - "hog":  HOG features
        :returns:       X (rows=samples, cols=features)
    """

    # transform color space
    if feature == 'gray' or feature == 'surf':
        X = [cv2.cvtColor(x, cv2.COLOR_BGR2GRAY) for x in X]
    elif feature == 'hsv':
        X = [cv2.cvtColor(x, cv2.COLOR_BGR2HSV) for x in X]

    # operate on smaller image
    small_size = (32, 32)
    X = [cv2.resize(x, small_size) for x in X]

    # extract features
    if feature == 'surf':
        surf = cv2.SURF(400)
        surf.upright = True
        surf.extended = True
        num_surf_features = 36

        # create dense grid of keypoints
        dense = cv2.FeatureDetector_create("Dense")
        kp = dense.detect(np.zeros(small_size).astype(np.uint8))

        # compute keypoints and descriptors
        kp_des = [surf.compute(x, kp) for x in X]

        # the second element is descriptor: choose first num_surf_features
        # elements
        X = [d[1][:num_surf_features, :] for d in kp_des]
    elif feature == 'hog':
        # histogram of gradients
        block_size = (small_size[0] / 2, small_size[1] / 2)
        block_stride = (small_size[0] / 4, small_size[1] / 4)
        cell_size = block_stride
        num_bins = 9
        hog = cv2.HOGDescriptor(small_size, block_size, block_stride,
                                cell_size, num_bins)
        X = [hog.compute(x) for x in X]
    elif feature is not None:
        # normalize all intensities to be between 0 and 1
        X = np.array(X).astype(np.float32) / 255

        # subtract mean
        X = [x - np.mean(x) for x in X]

    X = [x.flatten() for x in X]
    return X

def main(image_file):
    image = Image.open(image_file)
    if image is None:
        print 'Could not load image "%s"' % sys.argv[1]
        return

    image = np.array(image.convert('RGB'), dtype=np.uint8)
    image = image[:, :, ::-1].copy()

    winSize = (200, 200)
    stepSize = 32

    roi = extractRoi(image, winSize, stepSize)
    weight_map, mask_scale = next(roi)

    samples = [(rect, scale, cv2.cvtColor(window, cv2.COLOR_BGR2GRAY))
               for rect, scale, window in roi]

    X_test = [window for rect, scale, window in samples]
    coords = [(rect, scale) for rect, scale, window in samples]

    extractor = cv2.FeatureDetector_create('SURF')
    detector = cv2.DescriptorExtractor_create('SURF')

    affine = AffineInvariant(extractor, detector)

    saved = pickle.load(open('classifier.pkl', 'rb'))

    feature_transform = saved['pipe']
    model = saved['model']

    print 'Extracting Affine transform invariant features'
    affine_invariant_features = affine.transform(X_test)
    print 'Matching features with template'
    features = feature_transform.transform(affine_invariant_features)

    rects = classify(model, features, coords, weight_map, mask_scale)
    for (left, top, right, bottom) in non_max_suppression_fast(rects, 0.4):
        cv2.rectangle(image, (left, top), (right, bottom), (0, 0, 0), 10)
        cv2.rectangle(image, (left, top), (right, bottom), (32, 32, 255), 5)

    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    plt.show()