|
|
import cv2 |
|
|
import numpy as np |
|
|
import pandas as pd |
|
|
import gradio as gr |
|
|
import matplotlib.pyplot as plt |
|
|
from datetime import datetime |
|
|
|
|
|
def preprocess_image(image): |
|
|
"""Convert image to HSV and apply adaptive thresholding for better detection.""" |
|
|
if len(image.shape) == 2: |
|
|
image = cv2.cvtColor(image, cv2.COLOR_GRAY2RGB) |
|
|
|
|
|
hsv = cv2.cvtColor(image, cv2.COLOR_RGB2HSV) |
|
|
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) |
|
|
|
|
|
|
|
|
adaptive_thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 11, 2) |
|
|
|
|
|
|
|
|
kernel = np.ones((3,3), np.uint8) |
|
|
clean_mask = cv2.morphologyEx(adaptive_thresh, cv2.MORPH_CLOSE, kernel, iterations=2) |
|
|
clean_mask = cv2.morphologyEx(clean_mask, cv2.MORPH_OPEN, kernel, iterations=2) |
|
|
|
|
|
return clean_mask |
|
|
|
|
|
def detect_blood_cells(image): |
|
|
"""Detect blood cells using contour analysis with refined filtering.""" |
|
|
mask = preprocess_image(image) |
|
|
contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) |
|
|
|
|
|
features = [] |
|
|
for i, contour in enumerate(contours, 1): |
|
|
area = cv2.contourArea(contour) |
|
|
perimeter = cv2.arcLength(contour, True) |
|
|
circularity = 4 * np.pi * area / (perimeter * perimeter) if perimeter > 0 else 0 |
|
|
|
|
|
if 100 < area < 5000 and circularity > 0.7: |
|
|
M = cv2.moments(contour) |
|
|
if M["m00"] != 0: |
|
|
cx = int(M["m10"] / M["m00"]) |
|
|
cy = int(M["m01"] / M["m00"]) |
|
|
features.append({'label': i, 'area': area, 'perimeter': perimeter, 'circularity': circularity, 'centroid_x': cx, 'centroid_y': cy}) |
|
|
|
|
|
return contours, features, mask |
|
|
|
|
|
def process_image(image): |
|
|
if image is None: |
|
|
return None, None, None, None |
|
|
|
|
|
contours, features, mask = detect_blood_cells(image) |
|
|
vis_img = image.copy() |
|
|
|
|
|
for feature in features: |
|
|
contour = contours[feature['label'] - 1] |
|
|
cv2.drawContours(vis_img, [contour], -1, (0, 255, 0), 2) |
|
|
cv2.putText(vis_img, str(feature['label']), (feature['centroid_x'], feature['centroid_y']), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1) |
|
|
|
|
|
df = pd.DataFrame(features) |
|
|
return vis_img, mask, df |
|
|
|
|
|
def analyze(image): |
|
|
vis_img, mask, df = process_image(image) |
|
|
|
|
|
plt.style.use('dark_background') |
|
|
fig, axes = plt.subplots(1, 2, figsize=(12, 5)) |
|
|
|
|
|
if not df.empty: |
|
|
axes[0].hist(df['area'], bins=20, color='cyan', edgecolor='black') |
|
|
axes[0].set_title('Cell Size Distribution') |
|
|
|
|
|
axes[1].scatter(df['area'], df['circularity'], alpha=0.6, c='magenta') |
|
|
axes[1].set_title('Area vs Circularity') |
|
|
|
|
|
return vis_img, mask, fig, df |
|
|
|
|
|
|
|
|
demo = gr.Interface(fn=analyze, inputs=gr.Image(type="numpy"), outputs=[gr.Image(), gr.Image(), gr.Plot(), gr.Dataframe()]) |
|
|
demo.launch() |
