File size: 5,445 Bytes
fbbdeab |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
"""
Validation module - Handles all edge cases and input validation
"""
import os
from PIL import Image
from .config import MAX_FILE_SIZE_MB, MIN_IMAGE_SIZE_PX, VALID_EXTENSIONS
class FishImageValidator:
"""Comprehensive image validation with edge case handling"""
def __init__(self, max_size_mb=MAX_FILE_SIZE_MB,
min_size_px=MIN_IMAGE_SIZE_PX,
valid_extensions=VALID_EXTENSIONS):
self.max_size_mb = max_size_mb
self.min_size_px = min_size_px
self.valid_extensions = valid_extensions
def validate_file(self, file_path):
"""
Validate file exists, type, size, and image integrity
Returns:
tuple: (is_valid: bool, message: str, image: PIL.Image or None)
"""
# Check 1: File exists
if not os.path.exists(file_path):
return False, "❌ File not found", None
# Check 2: File extension
if not any(file_path.lower().endswith(ext.lower()) for ext in self.valid_extensions):
return False, f"❌ Invalid file type. Accepted: {', '.join(self.valid_extensions)}", None
# Check 3: File size
try:
file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
if file_size_mb > self.max_size_mb:
return False, f"❌ File too large ({file_size_mb:.1f}MB). Max: {self.max_size_mb}MB", None
except Exception as e:
return False, f"❌ Cannot read file: {e}", None
# Check 4: Valid image file
try:
img = Image.open(file_path)
img.verify() # Check for corruption
img = Image.open(file_path) # Re-open after verify (verify closes it)
img = img.convert('RGB') # Ensure RGB format
# Check 5: Image dimensions
if img.width < self.min_size_px or img.height < self.min_size_px:
return False, f"❌ Image too small ({img.width}x{img.height}px). Min: {self.min_size_px}x{self.min_size_px}px", None
return True, "✅ File validation passed", img
except Exception as e:
return False, f"❌ Invalid or corrupted image: {str(e)}", None
def validate_with_gemini(self, image, gemini_model):
"""
AI-based validation with Gemini Vision
Handles edge cases: multiple fish, dead fish, toys, drawings, partial fish
Accepts dataset images with transparent or solid backgrounds
Returns:
tuple: (is_valid: bool, message: str)
"""
if gemini_model is None:
return True, "⚠️ Gemini validation disabled"
try:
prompt = """Analyze this image for fish disease diagnosis.
Answer these questions:
1. Is there a FISH visible in this image? (Can be a real photo, medical/diagnostic image, or isolated fish specimen on any background including transparent/solid backgrounds)
2. How many fish are in the image?
3. Is the fish body clearly visible (not just head or tail)?
4. Can you see enough fish detail for disease assessment?
Respond in this EXACT format:
CONTAINS_FISH: YES or NO
FISH_COUNT: [number]
BODY_VISIBLE: YES or NO
SUFFICIENT_DETAIL: YES or NO
REASON: [brief explanation if any answer is NO]
IMPORTANT NOTES:
- Isolated fish on transparent, white, or solid backgrounds ARE ACCEPTABLE (common in medical datasets)
- Focus on whether the FISH ITSELF is clear and detailed, not the background
- Reject only if it's clearly NOT a fish (toy, cartoon, drawing of non-fish subject)"""
response = gemini_model.generate_content([prompt, image])
answer = response.text.strip().upper()
# Parse and validate responses
# Check 1: Contains fish?
if "CONTAINS_FISH: NO" in answer:
reason = self._extract_reason(answer)
return False, f"❌ No fish detected. {reason}"
# Check 2: Fish count zero
if "FISH_COUNT: 0" in answer or "FISH_COUNT: NONE" in answer:
return False, "❌ No fish found in image"
# Check 3: Multiple fish
for i in range(2, 20):
if f"FISH_COUNT: {i}" in answer:
return False, "❌ Multiple fish detected. Upload single fish only"
# Check 4: Body visible
if "BODY_VISIBLE: NO" in answer:
return False, "❌ Fish body not clearly visible"
# Check 5: Sufficient detail
if "SUFFICIENT_DETAIL: NO" in answer:
reason = self._extract_reason(answer)
return False, f"❌ Insufficient detail for diagnosis. {reason}"
return True, "✅ Valid fish image detected"
except Exception as e:
# Graceful degradation - log but don't block
print(f"⚠️ Gemini validation error: {e}")
return True, "⚠️ AI validation skipped (error occurred)"
@staticmethod
def _extract_reason(response_text):
"""Extract reason from Gemini response"""
if "REASON:" in response_text:
reason = response_text.split("REASON:")[-1].strip()
return reason[:150] # Limit length
return "See validation details"
|