Python cv2.Laplacian() Examples

The following are 30 code examples of cv2.Laplacian(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module cv2 , or try the search function .
Example #1
Source File: pycv2.py    From vrequest with MIT License 16 votes vote down vote up
def laplacian(filepathname):
    v = cv2.imread(filepathname)
    s = cv2.cvtColor(v, cv2.COLOR_BGR2GRAY)
    s = cv2.Laplacian(s, cv2.CV_16S, ksize=3)
    s = cv2.convertScaleAbs(s)
    cv2.imshow('nier',s)
    return s

    # ret, binary = cv2.threshold(s,40,255,cv2.THRESH_BINARY)
    # contours, hierarchy = cv2.findContours(binary,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
    # for c in contours:
    #     x,y,w,h = cv2.boundingRect(c)
    #     if w>5 and h>10:
    #         cv2.rectangle(v,(x,y),(x+w,y+h),(155,155,0),1)
    # cv2.imshow('nier2',v)

    # cv2.waitKey()
    # cv2.destroyAllWindows() 
Example #2
Source File: BlurDetection.py    From python-- with GNU General Public License v3.0 10 votes vote down vote up
def _lapulaseDetection(self, imgName):
        """
        :param strdir: 文件所在的目录
        :param name: 文件名称
        :return: 检测模糊后的分数
        """
        # step1: 预处理
        img2gray, reImg = self.preImgOps(imgName)
        # step2: laplacian算子 获取评分
        resLap = cv2.Laplacian(img2gray, cv2.CV_64F)
        score = resLap.var()
        print("Laplacian %s score of given image is %s", str(score))
        # strp3: 绘制图片并保存  不应该写在这里  抽象出来   这是共有的部分
        newImg = self._drawImgFonts(reImg, str(score))
        newDir = self.strDir + "/_lapulaseDetection_/"
        if not os.path.exists(newDir):
            os.makedirs(newDir)
        newPath = newDir + imgName
        # 显示
        cv2.imwrite(newPath, newImg)  # 保存图片
        cv2.imshow(imgName, newImg)
        cv2.waitKey(0)

        # step3: 返回分数
        return score 
Example #3
Source File: OpenCV_var.py    From Image-Blur-Detection with GNU General Public License v3.0 6 votes vote down vote up
def variance_of_laplacian(image):
	# compute the Laplacian of the image and then return the focus
	# measure, which is simply the variance of the Laplacian
	return cv2.Laplacian(image, cv2.CV_64F).var()



# In[ ]:



# In[ ]:


#accuracy_score(y, y_pred)


# In[4]: 
Example #4
Source File: find_best_quality_images.py    From ALPR_System with Apache License 2.0 6 votes vote down vote up
def get_best_images(plate_images, num_img_return):
    """
    Get the top num_img_return quality images (with the least blur).
    Laplacian function returns a value which indicates how blur the image is.
    The lower the value, the more blur the image have
    """

    # first, pick the image with the largest area because the bigger the image, the bigger the characters on the plate
    if len(plate_images) > (num_img_return + 2):
        plate_images = sorted(plate_images, key=lambda x : x[0].shape[0]*x[0].shape[1], reverse=True)[:(num_img_return+2)]

    # secondly, pick the images with the least blur
    if len(plate_images) > num_img_return:
        plate_images = sorted(plate_images, key=lambda img : cv2.Laplacian(img[0], cv2.CV_64F).var(), reverse=True)[:num_img_return]
        # img[0] because plate_images = [plate image, char on plate]
    return plate_images 
Example #5
Source File: FocusStack.py    From focusstack with Apache License 2.0 6 votes vote down vote up
def doLap(image):

    # YOU SHOULD TUNE THESE VALUES TO SUIT YOUR NEEDS
    kernel_size = 5         # Size of the laplacian window
    blur_size = 5           # How big of a kernal to use for the gaussian blur
                            # Generally, keeping these two values the same or very close works well
                            # Also, odd numbers, please...

    blurred = cv2.GaussianBlur(image, (blur_size,blur_size), 0)
    return cv2.Laplacian(blurred, cv2.CV_64F, ksize=kernel_size)

#
#   This routine finds the points of best focus in all images and produces a merged result...
# 
Example #6
Source File: process.py    From lowpolypy with MIT License 6 votes vote down vote up
def get_laplace_points(self, image: np.ndarray, num_points=500) -> np.ndarray:
        if num_points <= 0:
            return np.zeros((0, 2), dtype=np.uint8)
        image = cv2.GaussianBlur(image, (15, 15), 0)
        image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        image = np.uint8(np.absolute(cv2.Laplacian(image, cv2.CV_64F, 19)))
        image = cv2.GaussianBlur(image, (15, 15), 0)
        image = (image * (255 / image.max())).astype(np.uint8)
        image = image.astype(np.float32) / image.sum()
        if self.options['visualize_laplace']:
            self.visualize_image(image, 'laplace')
        weights = np.ravel(image)
        coordinates = np.arange(0, weights.size, dtype=np.uint32)
        choices = np.random.choice(coordinates, size=num_points, replace=False, p=weights)
        raw_points = np.unravel_index(choices, image.shape)
        points = np.stack(raw_points, axis=-1)[..., ::-1]
        return points 
Example #7
Source File: autoRIFT.py    From autoRIFT with Apache License 2.0 6 votes vote down vote up
def preprocess_filt_lap(self):
        '''
        Do the pre processing using Laplacian filter (2.5 min / 4 min).
        '''
        import cv2
        import numpy as np
        
        
        if self.zeroMask is not None:
            self.zeroMask = (self.I1 == 0)

        self.I1 = 20.0 * np.log10(self.I1)
        self.I1 = cv2.Laplacian(self.I1,-1,ksize=self.WallisFilterWidth,borderType=cv2.BORDER_CONSTANT)

        self.I2 = 20.0 * np.log10(self.I2)
        self.I2 = cv2.Laplacian(self.I2,-1,ksize=self.WallisFilterWidth,borderType=cv2.BORDER_CONSTANT) 
Example #8
Source File: 05_cartoonizing.py    From OpenCV-3-x-with-Python-By-Example with MIT License 6 votes vote down vote up
def cartoonize_image(img, ksize=5, sketch_mode=False):
    num_repetitions, sigma_color, sigma_space, ds_factor = 10, 5, 7, 4 
    # Convert image to grayscale 
    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 
 
    # Apply median filter to the grayscale image 
    img_gray = cv2.medianBlur(img_gray, 7) 
 
    # Detect edges in the image and threshold it 
    edges = cv2.Laplacian(img_gray, cv2.CV_8U, ksize=ksize) 
    ret, mask = cv2.threshold(edges, 100, 255, cv2.THRESH_BINARY_INV) 
 
    # 'mask' is the sketch of the image 
    if sketch_mode: 
        return cv2.cvtColor(mask, cv2.COLOR_GRAY2BGR) 
 
    # Resize the image to a smaller size for faster computation 
    img_small = cv2.resize(img, None, fx=1.0/ds_factor, fy=1.0/ds_factor, interpolation=cv2.INTER_AREA)
 
    # Apply bilateral filter the image multiple times 
    for i in range(num_repetitions): 
        img_small = cv2.bilateralFilter(img_small, ksize, sigma_color, sigma_space) 
 
    img_output = cv2.resize(img_small, None, fx=ds_factor, fy=ds_factor, interpolation=cv2.INTER_LINEAR) 
 
    dst = np.zeros(img_gray.shape) 
 
    # Add the thick boundary lines to the image using 'AND' operator 
    dst = cv2.bitwise_and(img_output, img_output, mask=mask) 
    return dst 
Example #9
Source File: plant_features.py    From bonnet with GNU General Public License v3.0 6 votes vote down vote up
def laplacian(mask):
  '''
    Get 2nd order gradients using the Laplacian
  '''

  # blur
  mask = cv2.GaussianBlur(mask, (5, 5), 0)

  # edges with laplacian
  laplacian = cv2.Laplacian(mask, cv2.CV_64F, 5)

  # stretch
  laplacian = contrast_stretch(laplacian)

  # cast
  laplacian = np.uint8(laplacian)

  return laplacian 
Example #10
Source File: artistic.py    From imgaug with MIT License 6 votes vote down vote up
def _find_edges_laplacian(image, edge_multiplier, from_colorspace):
    image_gray = colorlib.change_colorspace_(np.copy(image),
                                             to_colorspace=colorlib.CSPACE_GRAY,
                                             from_colorspace=from_colorspace)
    image_gray = image_gray[..., 0]
    edges_f = cv2.Laplacian(_normalize_cv2_input_arr_(image_gray / 255.0),
                            cv2.CV_64F)
    edges_f = np.abs(edges_f)
    edges_f = edges_f ** 2
    vmax = np.percentile(edges_f, min(int(90 * (1/edge_multiplier)), 99))
    edges_f = np.clip(edges_f, 0.0, vmax) / vmax

    edges_uint8 = np.clip(np.round(edges_f * 255), 0, 255.0).astype(np.uint8)
    edges_uint8 = _blur_median(edges_uint8, 3)
    edges_uint8 = _threshold(edges_uint8, 50)
    return edges_uint8


# Added in 0.4.0. 
Example #11
Source File: cartoonizing.py    From Mastering-OpenCV-4-with-Python with MIT License 6 votes vote down vote up
def sketch_image(img):
    """Sketches the image applying a laplacian operator to detect the edges"""

    # Convert to gray scale
    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # Apply median filter
    img_gray = cv2.medianBlur(img_gray, 5)

    # Detect edges using cv2.Laplacian()
    edges = cv2.Laplacian(img_gray, cv2.CV_8U, ksize=5)

    # Threshold the edges image:
    ret, thresholded = cv2.threshold(edges, 70, 255, cv2.THRESH_BINARY_INV)

    return thresholded 
Example #12
Source File: video.py    From cv with MIT License 5 votes vote down vote up
def cartoonize_image(img, ds_factor=4, sketch_mode=False):
    #convert to gray scale
    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    #apply median filter
    img_gray = cv2.medianBlur(img_gray, 7)

    #detect edges and threshold the imag
    edges = cv2.Laplacian(img_gray, cv2.CV_8U, ksize=5)
    ret, mask = cv2.threshold(edges, 100, 255, cv2.THRESH_BINARY_INV)
    
    #mask is the sketch of the image
    if sketch_mode:
        return cv2.cvtColor(mask, cv2.COLOR_GRAY2BGR)
    
    img_small = cv2.resize(img, None, fx=1.0/ds_factor, fy=1.0/ds_factor, interpolation = cv2.INTER_AREA)
    num_repetitions = 10
    sigma_color = 5
    sigma_space = 7
    size = 5
    
    #apply bilateral filter multiple times
    for i in range(num_repetitions):
        img_small = cv2.bilateralFilter(img_small, size, sigma_color, sigma_space)
    
    img_output = cv2.resize(img_small, None, fx=ds_factor, fy=ds_factor, interpolation=cv2.INTER_LINEAR)
    dst = np.zeros(img_gray.shape)
    
    dst = cv2.bitwise_and(img_output, img_output, mask=mask)
    return dst 
Example #13
Source File: Util.py    From PReMVOS with MIT License 5 votes vote down vote up
def geo_dist(img, pts):
  # Import these only on demand since pyximport interferes with pycocotools
  import pyximport
  pyximport.install()
  from ReID_net.datasets.Util import sweep

  img = np.copy(img) / 255.0
  #G = nd.gaussian_gradient_magnitude(img, 1.0)
  img = cv2.GaussianBlur(img, (3,3), 1.0)
  #G = cv2.Laplacian(img,cv2.CV_64F)
  sobelx = cv2.Sobel(img, cv2.CV_64F, 1, 0, ksize=5)
  sobely = cv2.Sobel(img, cv2.CV_64F, 0, 1, ksize=5)
  sobel_abs = cv2.addWeighted(sobelx, 0.5, sobely, 0.5, 0)
  sobel_abs = (sobel_abs[:, :, 0] ** 2 + sobel_abs[:, :, 1] ** 2 + sobel_abs[:, :, 2] ** 2) ** (1 / 2.0)

  #G = (G[:, :, 0] ** 2 + G[:, :, 1] ** 2 + G[:, :, 2] ** 2) ** (1 / 2.0)
  # c = 1 + G * 200
  # c = G / np.max(G)
  #c=sobel_abs / 255.0
  c=1+sobel_abs
  # plt.imshow(sobel_abs)
  # plt.colorbar()
  # plt.show()

  dt = np.zeros_like(c)
  dt[:] = 1000
  dt[pts] = 0
  sweeps = [dt, dt[:, ::-1], dt[::-1], dt[::-1, ::-1]]
  costs = [c, c[:, ::-1], c[::-1], c[::-1, ::-1]]
  for i, (a, c) in enumerate(it.cycle(list(zip(sweeps, costs)))):
    # print i,
    if sweep.sweep(a, c) < 1.0 or i >= 40:
      break
  return dt 
Example #14
Source File: track_preprocess.py    From sanet_relocal_demo with GNU General Public License v3.0 5 votes vote down vote up
def variance_of_laplacian(image):
    return cv2.Laplacian(image, cv2.CV_32FC3).var() 
Example #15
Source File: detection.py    From BlurDetection2 with MIT License 5 votes vote down vote up
def estimate_blur(image: numpy.array, threshold: int = 100):
    if image.ndim == 3:
        image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    blur_map = cv2.Laplacian(image, cv2.CV_64F)
    score = numpy.var(blur_map)
    return blur_map, score, bool(score < threshold) 
Example #16
Source File: toolbox_opencv.py    From remi with Apache License 2.0 5 votes vote down vote up
def on_new_image_listener(self, emitter):
        try:
            self.image_source = emitter
            border = OpencvBilateralFilter.border_type[self.border] if type(self.border) == str else self.border
            self.set_image_data(cv2.Laplacian(emitter.img, -1, borderType=border))
        except Exception:
            print(traceback.format_exc()) 
Example #17
Source File: 03_image_derivatives.py    From Practical-Computer-Vision with MIT License 5 votes vote down vote up
def plot_cv_img(input_image, output_image1, output_image2):     
    """     
    Converts an image from BGR to RGB and plots     
    """   

    fig, ax = plt.subplots(nrows=1, ncols=3)

    ax[0].imshow(input_image, cmap='gray')          
    ax[0].set_title('Input Image')
    ax[0].axis('off')
    
    ax[1].imshow(output_image1, cmap='gray')          
    ax[1].set_title('Laplacian Image')
    ax[1].axis('off')

    ax[2].imshow(output_image2, cmap = 'gray')          
    ax[2].set_title('Laplacian of Gaussian')
    ax[2].axis('off')    

    # ax[3].imshow(output_image3, cmap = 'gray')          
    # ax[3].set_title('Sharpened Image')
    # ax[3].axis('off')
    
    plt.savefig('../figures/03_image_derivatives_log.png')

    plt.show() 
Example #18
Source File: 03_image_derivatives.py    From Practical-Computer-Vision with MIT License 5 votes vote down vote up
def main():
    # read an image 
    img = cv2.imread('../figures/building_crop.jpg')
    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    
    
    
    # sobel 
    x_sobel = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=5)
    y_sobel = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=5)

    # laplacian
    lapl = cv2.Laplacian(img,cv2.CV_64F, ksize=5)

    # gaussian blur
    blur = cv2.GaussianBlur(img,(5,5),0)
    # laplacian of gaussian
    log = cv2.Laplacian(blur,cv2.CV_64F, ksize=5)
    
    # res = np.hstack([img, x_sobel, y_sobel])
    # plt.imshow(res, cmap='gray')
    # plt.axis('off')
    # plt.show()
    # lapl = np.asarray(lapl, dtype= np.uint)
    # Do plot
    plot_cv_img(img, lapl, log) 
Example #19
Source File: video.py    From cvcalib with Apache License 2.0 5 votes vote down vote up
def try_approximate_corners_blur(self, board_dims, sharpness_threshold):
        sharpness = cv2.Laplacian(self.frame, cv2.CV_64F).var()
        if sharpness < sharpness_threshold:
            return False
        found, corners = cv2.findChessboardCorners(self.frame, board_dims)
        self.current_image_points = corners
        return found 
Example #20
Source File: laplace_filter.py    From plantcv with MIT License 5 votes vote down vote up
def laplace_filter(gray_img, ksize, scale):
    """This is a filtering method used to identify and highlight fine edges based on the 2nd derivative. A very
       sensetive method to highlight edges but will also amplify background noise. ddepth = -1 specifies that the
       dimensions of output image will be the same as the input image.

    Inputs:
    gray_img    = Grayscale image data
    ksize       = apertures size used to calculate 2nd derivative filter, specifies the size of the kernel
                  (must be an odd integer: 1,3,5...)
    scale       = scaling factor applied (multiplied) to computed Laplacian values (scale = 1 is unscaled)

    Returns:
    lp_filtered = laplacian filtered image

    :param gray_img: numpy.ndarray
    :param ksize: int
    :param scale: int
    :return lp_filtered: numpy.ndarray
    """

    lp_filtered = cv2.Laplacian(src=gray_img, ddepth=-1, ksize=ksize, scale=scale)
    params.device += 1
    if params.debug == 'print':
        print_image(lp_filtered,
                    os.path.join(params.debug_outdir,
                                 str(params.device) + '_lp_out_k' + str(ksize) + '_scale' + str(scale) + '.png'))
    elif params.debug == 'plot':
        plot_image(lp_filtered, cmap='gray')
    return lp_filtered 
Example #21
Source File: detect_focus.py    From pi-tracking-telescope with MIT License 5 votes vote down vote up
def variance_of_laplacian(image):
	# compute the Laplacian of the image and then return the focus
	# measure, which is simply the variance of the Laplacian
	return cv2.Laplacian(image, cv2.CV_64F).var()

# initialize the camera and grab a reference to the raw camera capture 
Example #22
Source File: detect_focus2.py    From pi-tracking-telescope with MIT License 5 votes vote down vote up
def variance_of_laplacian(image):
	# compute the Laplacian of the image and then return the focus
	# measure, which is simply the variance of the Laplacian
	return cv2.Laplacian(image, cv2.CV_64F).var() 
Example #23
Source File: focus.py    From pi-tracking-telescope with MIT License 5 votes vote down vote up
def variance_of_laplacian(self, image):
        # compute the Laplacian of the image and then return the focus
        # measure, which is simply the variance of the Laplacian
        return cv2.Laplacian(image, cv2.CV_64F).var() 
Example #24
Source File: opencv_py.py    From python-urbanPlanning with MIT License 5 votes vote down vote up
def edgeDetection(inputImg_edge):    
    imgEdge=cv2.imread(inputImg_edge,cv2.IMREAD_GRAYSCALE)  #读取图像
    sobelHorizontal=cv2.Sobel(imgEdge,cv2.CV_64F,1,0,ksize=5) #索贝尔滤波器Sobel filter,横向。参数解释通过help(cv2.Sobel)查看
    """
    help(cv2.Sobel)
    Help on built-in function Sobel:
    .   @param src input image. 输入待处理的图像
    .   @param dst output image of the same size and the same number of channels as src . 输出图像,同大小,同通道数
    .   @param ddepth output image depth, see @ref filter_depths "combinations"; in the case of.  8-bit input images it will result in truncated derivatives. 
    图像深度,-1时与原图像深度同,目标图像的深度必须大于等于原图像深度。避免truncated derivatives而设置cv2.CV_64F数据类型
    .   @param dx order of the derivative x. x方向求导阶数,0表示这个方向没有求导,一般为0,1,2
    .   @param dy order of the derivative y. y方向求导阶数,同上
    .   @param ksize size of the extended Sobel kernel; it must be 1, 3, 5, or 7. 算子大小,必须为1、3、5、7
    .   @param scale optional scale factor for the computed derivative values; by default, no scaling is. applied (see cv::getDerivKernels for details).
    缩放导数的比例常数,默认情况五伸缩系数
    .   @param delta optional delta value that is added to the results prior to storing them in dst.
    可选增量,默认情况无额外值加到dst中
    .   @param borderType pixel extrapolation method, see cv::BorderTypes 图像边界模式
    .   @sa  Scharr, Laplacian, sepFilter2D, filter2D, GaussianBlur, cartToPolar      
    """
    sobelVertical=cv2.Sobel(imgEdge,cv2.CV_64F,0,1,ksize=5) #索贝尔滤波器Sobel filter,纵向
    laplacian=cv2.Laplacian(imgEdge,cv2.CV_64F) #拉普拉斯边检测器,Laplacian edge detector
    canny=cv2.Canny(imgEdge,50,240) #Canny边检测器Canny edge detector
    
#    print(imgEdge)
    cv2.namedWindow('img')
#    cv2.imshow('original',imgEdge)
#    cv2.imshow('sobel horizontal',sobelHorizontal) #输出显示图像
#    cv2.imwrite(os.path.join(rootDirectory,'sobel horizontal.jpg'),sobelHorizontal)
#    cv2.imshow('sobel vertical',sobelVertical)    
#    cv2.imwrite(os.path.join(rootDirectory,'sobel vertical.jpg'),sobelVertical)
    cv2.imshow('laplacian',laplacian)
    cv2.imwrite(os.path.join(rootDirectory,'laplacian.jpg'),laplacian)
#    cv2.imshow('canny',canny)
#    cv2.imwrite(os.path.join(rootDirectory,'canny.jpg'),canny)
    cv2.waitKey()

#检测棱角 
Example #25
Source File: view-mongo-images.py    From smart-zoneminder with MIT License 5 votes vote down vote up
def variance_of_laplacian(image):
    # compute the Laplacian of the image and then return the focus
    # measure, which is simply the variance of the Laplacian
    return cv2.Laplacian(image, cv2.CV_64F).var() 
Example #26
Source File: face_detect_server.py    From smart-zoneminder with MIT License 5 votes vote down vote up
def variance_of_laplacian(image):
	# compute the Laplacian of the image and then return the focus
	# measure, which is simply the variance of the Laplacian
	return cv2.Laplacian(image, cv2.CV_64F).var() 
Example #27
Source File: filters.py    From VIP with MIT License 5 votes vote down vote up
def cube_filter_highpass(array, mode='laplacian', verbose=True, **kwargs):
    """
    Apply ``frame_filter_highpass`` to the frames of a 3d or 4d cube.

    Parameters
    ----------
    array : numpy ndarray
        Input cube, 3d or 4d.
    mode : str, optional
        ``mode`` parameter to the ``frame_filter_highpass`` function. Defaults
        to a Laplacian high-pass filter.
    verbose : bool, optional
        If ``True`` timing and progress bar are shown.
    **kwargs : dict
        Passed through to the ``frame_filter_highpass`` function.

    Returns
    -------
    filtered : numpy ndarray
        High-pass filtered cube.

    """
    array_out = np.empty_like(array)

    if array.ndim == 3:
        for i in Progressbar(range(array.shape[0]), verbose=verbose):
            array_out[i] = frame_filter_highpass(array[i], mode=mode, **kwargs)
    elif array.ndim == 4:
        for i in Progressbar(range(array.shape[1]), verbose=verbose):
            for lam in range(array.shape[0]):
                array_out[lam][i] = frame_filter_highpass(array[lam][i],
                                                          mode=mode, **kwargs)
    else:
        raise TypeError('Input array is not a 3d or 4d cube')

    return array_out 
Example #28
Source File: detect_servers_tpu.py    From edge-tpu-servers with MIT License 5 votes vote down vote up
def variance_of_laplacian(image):
    # compute the Laplacian of the image and then return the focus
    # measure, which is simply the variance of the Laplacian
    return cv2.Laplacian(image, cv2.CV_64F).var() 
Example #29
Source File: crop_imgs.py    From TENet with MIT License 5 votes vote down vote up
def worker(path, select_folder, waste_img_folder, crop_sz, stride, thres_sz, cont_var_thresh, freq_var_thresh):
    img_name = os.path.basename(path)
    img = cv2.imread(path, cv2.IMREAD_UNCHANGED)
    h, w, c = img.shape

    h_space = np.arange(0, h - crop_sz + 1, stride)
    if h - (h_space[-1] + crop_sz) > thres_sz:
        h_space = np.append(h_space, h - crop_sz)
    w_space = np.arange(0, w - crop_sz + 1, stride)
    if w - (w_space[-1] + crop_sz) > thres_sz:
        w_space = np.append(w_space, w - crop_sz)

    index = 0
    for x in h_space:
        for y in w_space:
            index += 1
            patch_name = img_name.replace('.png', '_s{:05d}.png'.format(index))
            patch = img[x:x + crop_sz, y:y + crop_sz, :]

            im_gray = patch[:, :, 1]

            [mean, var] = cv2.meanStdDev(im_gray)
            freq_var = cv2.Laplacian(im_gray, cv2.CV_8U).var()

            if var > cont_var_thresh and freq_var>freq_var_thresh:
                cv2.imwrite(os.path.join(select_folder, patch_name), patch)
            else:
                cv2.imwrite(os.path.join(waste_img_folder, patch_name), patch)
    return 'Processing {:s} ...'.format(img_name) 
Example #30
Source File: main.py    From Traffic-Sign-Detection with MIT License 5 votes vote down vote up
def LaplacianOfGaussian(image):
    LoG_image = cv2.GaussianBlur(image, (3,3), 0)           # paramter 
    gray = cv2.cvtColor( LoG_image, cv2.COLOR_BGR2GRAY)
    LoG_image = cv2.Laplacian( gray, cv2.CV_8U,3,3,2)       # parameter
    LoG_image = cv2.convertScaleAbs(LoG_image)
    return LoG_image