File size: 4,700 Bytes
d72a22b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | """
Coffee Leaf Rust Severity Estimation
====================================
This script calculates the severity of Coffee Leaf Rust (CLR) for individual leaf images.
It processes a directory of leaf images and their corresponding binary masks (representing diseased areas).
Methodology:
1. Load the original leaf image to determine total leaf area.
2. Load the corresponding disease mask (generated by SAM or other segmentation models).
3. Calculate Severity (%) = (Diseased Area / Total Leaf Area) * 100.
4. Export results to CSV and Excel.
Filename Convention:
The script expects a naming convention like: "set_<id>_<image_id>_obj<leaf_id>"
Example: "set_16_123_obj1.jpg"
"""
import os
import cv2
import numpy as np
import pandas as pd
import re
# ================= Configuration =================
# Directory containing individual leaf images (cropped from original)
LEAF_FOLDER = "./data/leaves"
# Directory containing disease masks (binary images: white=disease, black=background)
MASK_FOLDER = "./data/masks"
# Output file paths
OUTPUT_DIR = "./results"
OUTPUT_CSV_NAME = "severity_results.csv"
OUTPUT_EXCEL_NAME = "severity_results.xlsx"
# Regex pattern to parse filename metadata
# Adjust this pattern if your filenames follow a different structure
FILE_PATTERN = r"set_\d+_(\d+)_obj(\d+)"
# =================================================
def calculate_severity():
# Ensure output directory exists
os.makedirs(OUTPUT_DIR, exist_ok=True)
output_csv = os.path.join(OUTPUT_DIR, OUTPUT_CSV_NAME)
output_excel = os.path.join(OUTPUT_DIR, OUTPUT_EXCEL_NAME)
results = []
print(f"Processing images from: {LEAF_FOLDER}")
# Iterate through all files in the leaf folder
for filename in os.listdir(LEAF_FOLDER):
if not filename.lower().endswith((".jpg", ".png", ".jpeg", ".tif")):
continue
# Parse filename to extract Image ID and Leaf ID
match = re.match(FILE_PATTERN, filename)
if not match:
print(f"⚠️ Skipping file with non-compliant name: {filename}")
continue
image_id, leaf_id = match.groups()
leaf_path = os.path.join(LEAF_FOLDER, filename)
mask_path = os.path.join(MASK_FOLDER, filename)
# --- 1. Calculate Total Leaf Area ---
# Read image to determine the leaf area.
# Assuming the leaf is segmented against a black/white background or we threshold it.
leaf_img = cv2.imread(leaf_path)
if leaf_img is None:
print(f"Error reading image: {leaf_path}")
continue
gray_leaf = cv2.cvtColor(leaf_img, cv2.COLOR_BGR2GRAY)
# Simple thresholding to separate leaf from background
# Adjust threshold value (10) as needed based on background color
_, leaf_binary = cv2.threshold(gray_leaf, 10, 255, cv2.THRESH_BINARY)
total_leaf_pixels = cv2.countNonZero(leaf_binary)
# --- 2. Calculate Diseased Area ---
if os.path.exists(mask_path):
mask_img = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)
if mask_img is not None:
diseased_pixels = cv2.countNonZero(mask_img)
else:
print(f"Warning: Mask found but unreadable for {filename}")
diseased_pixels = 0
else:
# If no mask exists, assume 0% severity (healthy leaf)
diseased_pixels = 0
# --- 3. Compute Severity ---
if total_leaf_pixels > 0:
severity = (diseased_pixels / total_leaf_pixels) * 100
else:
severity = 0
results.append({
"Image_ID": int(image_id),
"Leaf_ID": int(leaf_id),
"Total_Pixels": total_leaf_pixels,
"Diseased_Pixels": diseased_pixels,
"Severity_Percent": round(severity, 2)
})
# --- 4. Save Outputs ---
if results:
df = pd.DataFrame(results).sort_values(["Image_ID", "Leaf_ID"])
df.to_csv(output_csv, index=False)
print(f"CSV saved to: {output_csv}")
try:
df.to_excel(output_excel, index=False)
print(f"Excel saved to: {output_excel}")
except ImportError:
print("To save as Excel, please install openpyxl: pip install openpyxl")
print(f"✅ Processing complete. Computed severity for {len(results)} leaves.")
else:
print("No valid images found to process.")
if __name__ == "__main__":
calculate_severity()
|