In [55]:
import numpy as np
import cv2
import matplotlib.pyplot as plt
In [61]:
img_path = r'C:\Users\USER\Downloads\trial2.jpg'
img = cv2.imread(img_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) #matplotlib是RGB，但是opencv是BGR
plt.imshow(img)
plt.show()
In [62]:
img
Out[62]:
In [63]:
import numpy as np
import cv2
face_cascade = cv2.CascadeClassifier(r'C:\Users\USER\Anaconda3\envs\tensorflow\Library\etc\haarcascades\haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier(r'C:\Users\USER\Anaconda3\envs\tensorflow\Library\etc\haarcascades\haarcascade_eye.xml')
img = cv2.imread(img_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#Now we find the faces in the image. If faces are found, it returns the positions of detected
#faces as Rect(x,y,w,h). Once we get these locations, we can create a ROI for the face and
#apply eye detection on this ROI (since eyes are always on the face !!! ).
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
roi_gray = gray[y:y+h, x:x+w]
roi_color = img[y:y+h, x:x+w]
eyes = eye_cascade.detectMultiScale(roi_gray)
for (ex,ey,ew,eh) in eyes:
cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),2)
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
In [7]:
import cv2
import numpy as np
import matplotlib.pyplot as plt
import dicom as pdicom
import os
import glob
%matplotlib inline
In [10]:
import pandas as pd
import scipy.ndimage
from skimage import measure, morphology
from mpl_toolkits.mplot3d.art3d import Poly3DCollection
In [11]:
INPUT_FOLDER = r'C:\Users\USER\Downloads\CT_image_tutorial\dicom_dir'
patients = os.listdir(INPUT_FOLDER)
patients.sort()
In [14]:
#Collect all dicom images
lstFilesDCM = []
def load_scan2(path):
for dirName, subdirList, fileList in os.walk(path):
for filename in fileList:
if '.dcm' in filename.lower(): #確認是dcm檔案
lstFilesDCM.append(os.path.join(dirName,filename))
#print(lstFilesDCM)
return lstFilesDCM
first_patient = load_scan2(INPUT_FOLDER)
#print(first_patient)
In [16]:
# Get ref file
RefDs = pdicom.read_file(lstFilesDCM[0])
# Load dims based on rows, cols, slices(Z-axis)
ConstPixelDims = (int(RefDs.Rows), int(RefDs.Columns), len(lstFilesDCM)) #維度跟著row，col，還有Z軸是slices
# Load spacing values (in mm)
ConstPixelSpacing = (float(RefDs.PixelSpacing[0]) , float(RefDs.PixelSpacing[1]), float(RefDs.SliceThickness))
In [17]:
x = np.arange(0.0, (ConstPixelDims[0]+1)*ConstPixelSpacing[0], ConstPixelSpacing[0] )
y = np.arange(0.0, (ConstPixelDims[1]+1)*ConstPixelSpacing[1], ConstPixelSpacing[1] )
z = np.arange(0.0, (ConstPixelDims[2]+1)*ConstPixelSpacing[2], ConstPixelSpacing[2] )
In [18]:
# The array is based on ConstPixelDims
ArrayDicom = np.zeros(ConstPixelDims, dtype = RefDs.pixel_array.dtype)
# loop through all DICOM files:
for filenameDCM in lstFilesDCM:
# read the file
ds = pdicom.read_file(filenameDCM)
# store the raw image data
ArrayDicom[:, :, lstFilesDCM.index(filenameDCM)] = ds.pixel_array
In [23]:
plt.figure(dpi=1600)
plt.axes().set_aspect('equal', 'datalim')
plt.set_cmap(plt.gray())
plt.pcolormesh(x, y, np.flipud(ArrayDicom[:, :, 99]))
Out[23]:
In [36]:
plt.figure(dpi=1600)
plt.axes().set_aspect('equal', 'datalim')
plt.set_cmap(plt.gray())
plt.pcolormesh(x, y, np.flipud(ArrayDicom[:, :, 2]))
Out[36]:
In [37]:
# 落在邊界外是-2000，要先把他們變成0
def get_pixels_hu(slices):
image = np.stack([s.pixel_array for s in slices])
# Convert to int16 (from sometimes int16),
# should be possible as values should always be low enough (<32k)
image = image.astype(np.int16)
# Set outside-of-scan pixels to 0
# The intercept is usually -1024, so air is approximately 0
image[image == -2000] = 0
# Convert to Hounsfield units (HU)
for slice_number in range(len(slices)):
intercept = slices[slice_number].RescaleIntercept
slope = slices[slice_number].RescaleSlope
if slope != 1:
image[slice_number] = slope * image[slice_number].astype(np.float64)
image[slice_number] = image[slice_number].astype(np.int16)
image[slice_number] += np.int16(intercept)
return np.array(image, dtype=np.int16)
In [40]:
In [ ]: