Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import numpy as np
- import math
- import cv2
- from numpy import ndarray
- from Lista02 import FuncoesML as fun
- #lendo a imagem
- circles = []
- circles = fun.loadFiles('C:/Users/Auricelia/Desktop/DataSetsML/New_shapes_dataset/circles/*.jpg',circles)
- #convertendo para níveis de cinza
- circles = fun.grayConversion(circles)
- #aplicando o filtro gaussiano
- circles = fun.blurConversion(circles, 5, 0)
- #convertendo para binária
- circles = fun.binaryConversion(circles, 255, 31)
- #invertendo as cores
- circles = fun.invertConversion(circles)
- # extraindo momentos da imagem
- im2, countours, hierachy = cv2.findContours(circles[0], cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
- peri = cv2.arcLength(countours[0], True) # perimetro
- aproxx = cv2.approxPolyDP(countours[0], 0.04 * peri, True) # vertices
- print('Vertices list', aproxx)
- print('shape', aproxx.shape)
- print('dtype',aproxx.dtype)
- print('type',type(aproxx))
- x1 = ndarray.item(aproxx,(0,0,0)) # recupera o primeiro elemento do ndarray
- y1 = ndarray.item(aproxx,(0,0,1))
- x2 = ndarray.item(aproxx,(1,0,0))
- y2 = ndarray.item(aproxx,(1,0,1))
- print('angle',fun.angleBetweenPoints(x1,y1,2,y2))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement