Computer vision: Adaptive Thresholding 



import cv2 as cv

import numpy as np

img = cv.imread('sudoku.png',0)

_, th1 = cv.threshold(img, 127, 255, cv.THRESH_BINARY)

th2 = cv.adaptiveThreshold(img, 255, cv.ADAPTIVE_THRESH_MEAN_C, cv.THRESH_BINARY, 11, 2);

th3 = cv.adaptiveThreshold(img, 255, cv.ADAPTIVE_THRESH_GAUSSIAN_C, cv.THRESH_BINARY, 11, 2);


cv.imshow("Image", img)

cv.imshow("THRESH_BINARY", th1)

cv.imshow("ADAPTIVE_THRESH_MEAN_C", th2)

cv.imshow("ADAPTIVE_THRESH_GAUSSIAN_C", th3)


cv.waitKey(0)

cv.destroyAllWindows()#close window


#===================================#

data used in this video


#===================================#

if you faced any issue contact me via 

what's app : +201210894349

 or facebook



Comments

Post a Comment

I hope you have benefited from this blog, and if you have any question, feel free to leave it here.

Popular posts from this blog

Image
  Computer vision: Motion Detection and Tracking Using Opencv  import cv2 import numpy as np cap = cv2.VideoCapture('vtest.avi') frame_width = int( cap.get(cv2.CAP_PROP_FRAME_WIDTH)) frame_height =int( cap.get( cv2.CAP_PROP_FRAME_HEIGHT)) fourcc = cv2.VideoWriter_fourcc('X','V','I','D') out = cv2.VideoWriter("output.avi", fourcc, 5.0, (1280,720)) ret, frame1 = cap.read()# 1st frame ret, frame2 = cap.read() #2nd frame print(frame1.shape) while cap.isOpened():     diff = cv2.absdiff(frame1, frame2)             gray = cv2.cvtColor(diff, cv2.COLOR_BGR2GRAY)             blur = cv2.GaussianBlur(gray, (5,5), 0)             _, thresh = cv2.threshold(blur, 20, 255, cv2.THRESH_BINARY)             dilated = cv2.dilate(thresh, None, iterations=3)             contours, _ = cv2.findContours(dilated, cv2.RETR_...
Read more
Image
Computer vision:Vehicle detection and  counting using openCV | Arabic import cv2 import numpy as np from time import sleep largura_min = 80 altura_min = 80 offset = 6 pos_linha = 550 # FPS to vídeo delay = 60 detec = [] carros = 0 def pega_centro(x, y, w, h):     x1 = int(w / 2)     y1 = int(h / 2)     cx = x + x1     cy = y + y1     return cx, cy # video source input cap = cv2.VideoCapture('video.mp4') subtracao = cv2.bgsegm.createBackgroundSubtractorMOG() while True:     ret, frame1 = cap.read()             tempo = float(1/delay)              sleep(tempo)              grey = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)              blur = cv2.GaussianBlur(grey, (3, 3), 5)               img_sub = subtracao.apply(blur)        ...
Read more
Image
  Computer vision: detect , track and count car and moto in video using openCV  computer vision  import cv2 from tracker import * import os os.chdir("D:\object traking\object_tracking") result = cv2.VideoWriter('ahmedd.mp4',                           cv2.VideoWriter_fourcc(*'XVID'),                          20, (250,250)) # Create tracker object tracker = EuclideanDistTracker() cap = cv2.VideoCapture("highway.mp4") # Object detection from Stable camera object_detector = cv2.createBackgroundSubtractorMOG2(history=100, varThreshold=50) # if history is big number it will be hight  while True:     ret, frame = cap.read()             if ret is not True:                 break                   height, w...
Read more