|
|
|
import streamlit as st |
|
from tensorflow import keras |
|
import tensorflow as tf |
|
from PIL import Image |
|
import numpy as np |
|
import cv2 |
|
import matplotlib.pyplot as plt |
|
from imutils import perspective |
|
from scipy.spatial import distance as dist |
|
import os |
|
|
|
|
|
MODEL_PATH = 'model.h5' |
|
IMAGE_DIR = 'images' |
|
|
|
|
|
def load_image(image_file): |
|
img = Image.open(image_file) |
|
return img |
|
|
|
def midpoint(ptA, ptB): |
|
return ((ptA[0] + ptB[0]) /2 , (ptA[1] + ptB[1]) /2) |
|
|
|
def draw_dimensions(orig_image,predict_image,erode_iteration,open_iteration): |
|
kernel1 =( np.ones((5,5), dtype=np.float32)) |
|
kernel_sharpening = np.array([[-1,-1,-1], |
|
[-1,9,-1], |
|
[-1,-1,-1]]) |
|
|
|
image = predict_image |
|
image2 = orig_image |
|
|
|
image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel1,iterations=open_iteration ) |
|
image = cv2.filter2D(image, -1, kernel_sharpening) |
|
image = cv2.erode(image,kernel1,iterations =erode_iteration) |
|
|
|
image=cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) |
|
|
|
thresh = cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1] |
|
labels=cv2.connectedComponents(thresh,connectivity=8)[1] |
|
a=np.unique(labels) |
|
count2=0 |
|
for label in a: |
|
if label == 0: |
|
continue |
|
|
|
|
|
mask = np.zeros(thresh.shape, dtype="uint8") |
|
mask[labels == label] = 255 |
|
|
|
cnts,hieararch = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) |
|
cnts = cnts[0] |
|
c_area = cv2.contourArea(cnts) |
|
|
|
(x,y),radius = cv2.minEnclosingCircle(cnts) |
|
rect = cv2.minAreaRect(cnts) |
|
box = cv2.boxPoints(rect) |
|
box = np.array(box, dtype="int") |
|
box = perspective.order_points(box) |
|
color1 = (list(np.random.choice(range(150), size=3))) |
|
color =[int(color1[0]), int(color1[1]), int(color1[2])] |
|
cv2.drawContours(image2,[box.astype("int")],0,color,2) |
|
(tl,tr,br,bl)=box |
|
|
|
(tltrX,tltrY)=midpoint(tl,tr) |
|
(blbrX,blbrY)=midpoint(bl,br) |
|
|
|
|
|
(tlblX,tlblY)=midpoint(tl,bl) |
|
(trbrX,trbrY)=midpoint(tr,br) |
|
|
|
cv2.circle(image2, (int(tltrX), int(tltrY)), 5, (255, 0, 0), -1) |
|
cv2.circle(image2, (int(blbrX), int(blbrY)), 5, (255, 0, 0), -1) |
|
cv2.circle(image2, (int(tlblX), int(tlblY)), 5, (255, 0, 0), -1) |
|
cv2.circle(image2, (int(trbrX), int(trbrY)), 5, (255, 0, 0), -1) |
|
cv2.line(image2, (int(tltrX), int(tltrY)), (int(blbrX), int(blbrY)),color, 2) |
|
cv2.line(image2, (int(tlblX), int(tlblY)), (int(trbrX), int(trbrY)),color, 2) |
|
dA = dist.euclidean((tltrX, tltrY), (blbrX, blbrY)) |
|
dB = dist.euclidean((tlblX, tlblY), (trbrX, trbrY)) |
|
|
|
global dimA |
|
dimA = dA*0.08 |
|
global dimB |
|
dimB = dB*0.08 |
|
cv2.putText(image2, "{:.1f} millimeter".format(dimA),(int(tltrX - 10), int(tltrY - 10)), cv2.FONT_HERSHEY_SIMPLEX,0.65, (0,0,0), 2) |
|
cv2.putText(image2, "{:.1f} millimeter".format(dimB),(int(trbrX + 10), int(trbrY+10)), cv2.FONT_HERSHEY_SIMPLEX,0.65,(0,0,0), 2) |
|
|
|
return image2 |
|
|
|
def segment_molar(image_file): |
|
|
|
img=load_image(image_file) |
|
|
|
img = np.asarray(img) |
|
img = cv2.resize(img, (512, 256)) |
|
img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) |
|
img = np.expand_dims(img, axis=0) |
|
|
|
prediction = model.predict(img) |
|
|
|
output = prediction.reshape(256,512) |
|
|
|
return img , output |
|
|
|
def measure_molar(image_file): |
|
|
|
img=load_image(image_file) |
|
|
|
img = np.asarray(img) |
|
img_prd= cv2.resize(img , (512, 256)) |
|
img_prd = cv2.cvtColor(img_prd, cv2.COLOR_RGB2GRAY) |
|
img_prd = np.expand_dims(img_prd, axis=0) |
|
prediction = model.predict(img_prd) |
|
prediction=prediction*255 |
|
prediction = prediction.astype("uint8") |
|
prediction_img=prediction.reshape(256,512) |
|
img2 = np.zeros( ( np.array(prediction_img).shape[0], np.array(prediction_img).shape[1], 3 ) ) |
|
img2[:,:,0] = prediction_img |
|
img2[:,:,1] = prediction_img |
|
img2[:,:,2] = prediction_img |
|
img2 = img2.astype("uint8") |
|
predicted = cv2.resize(img2 , (img.shape[1],img.shape[0]), interpolation=cv2.INTER_LANCZOS4) |
|
output=draw_dimensions(img,predicted,3,2) |
|
|
|
return output |
|
|
|
|
|
model = keras.models.load_model(MODEL_PATH) |
|
images = os.listdir(IMAGE_DIR) |
|
images = [f'{IMAGE_DIR}/{image}' for image in images] |
|
|
|
|
|
labels = {'fatemeh_hafari_27022022_181119right.png': 'classI', |
|
'majid_mohammadkhanlu_19022022_175338right.png': 'mesioangular', |
|
'zahra_khodabandeh_17052022_162804right.png': 'mesioangular', |
|
'133028019739531250right.png': 'classII', |
|
'khadijeh_fard_aghababaei_03012022_120330right.png': 'B', |
|
'moharam_ali_khamseh_01112021_194329right.png': 'B', |
|
'parniya_mohamadinasab_08112021_184639right.png': 'B', |
|
'afsaneh_khalaji_24022022_183000right.png': 'B', |
|
'sogand_rahmani_13072022_113636right.png': 'B', |
|
'fatemeh_mirzaei_13072022_101734right.png': 'mesioangular', |
|
'fatemeh_hoseini_24012022_111330right.png': 'C', |
|
'padisar_ebrahimi_13122021_111512right.png': 'mesioangular'} |
|
|
|
|
|
st.header("3rdMolar Segmentation") |
|
st.subheader("Select Image:") |
|
image_file = st.selectbox('Select Image' , images) |
|
|
|
if image_file is not None: |
|
|
|
img , output1 = segment_molar(image_file) |
|
output2 = measure_molar(image_file) |
|
|
|
st.subheader(f"Label : {labels[image_file.split('/')[1]]}") |
|
st.image(img[0],width=850) |
|
st.image(output1,width=850) |
|
st.image(output2,width=850) |
|
|
|
|
