Adaptive Contrast Enhancement

Apply adaptive contrast enhancement using CLAHE (Contrast Limited Adaptive Histogram Equalization) for superior local contrast improvement.

Request Parameters

Response

Returns the contrast-enhanced image in the same format as the input file.

Example Request

    curl -X POST "https://oyyi.xyz/api/image/adaptive-contrast" \
  -H "accept: application/json" \
  -H "Content-Type: multipart/form-data" \
  -F "file=@image.jpg" \
  -F "clip_limit=2.0" \
  -F "tile_grid_size=8" \
  --output enhanced.jpg
  

Example with Python

    import requests

url = "https://oyyi.xyz/api/image/adaptive-contrast"

files = {
    'file': open('image.jpg', 'rb')
}

data = {
    'clip_limit': 2.0,
    'tile_grid_size': 8
}

response = requests.post(url, files=files, data=data)

# Save the enhanced image
with open('enhanced.jpg', 'wb') as f:
    f.write(response.content)
  

Example with JavaScript

    // Using fetch API
const formData = new FormData();
formData.append('file', fileInput.files[0]);
formData.append('clip_limit', '2.0');
formData.append('tile_grid_size', '8');

fetch('https://oyyi.xyz/api/image/adaptive-contrast', {
  method: 'POST',
  body: formData
})
.then(response => response.blob())
.then(blob => {
  // Create a URL for the blob
  const url = URL.createObjectURL(blob);

  // Create a link to download the image
  const a = document.createElement('a');
  a.href = url;
  a.download = 'enhanced.jpg';
  a.click();

  // Clean up by revoking the URL
  URL.revokeObjectURL(url);
})
.catch(error => console.error('Error:', error));
  

How It Works

CLAHE (Contrast Limited Adaptive Histogram Equalization) is an advanced contrast enhancement technique that improves upon standard histogram equalization:

• The image is divided into small tiles (grid cells) based on the tile_grid_size parameter.
• Histogram equalization is applied to each tile independently, enhancing local contrast.
• The clip_limit parameter prevents over-amplification of noise by limiting the contrast enhancement.
• Bilinear interpolation is used to eliminate artificial boundaries between tiles.
• This approach enhances local details while maintaining the overall appearance of the image.

Parameter Effects

Error Responses

Notes

• CLAHE is particularly effective for enhancing details in medical images, foggy scenes, and underwater photography.
• For color images, the enhancement is applied to the luminance/value channel only, preserving the hue and saturation.
• Higher clip limits can amplify noise in smooth areas of the image.
• Smaller tile sizes enhance local details but may create an unnatural appearance.
• The maximum file size allowed is 10MB.
• This operation preserves the alpha channel (transparency) if present in the original image.

Use Cases

• Enhancing medical imaging data like X-rays, CT scans, or ultrasound images
• Improving visibility in foggy, hazy, or underwater images
• Enhancing details in satellite or aerial imagery
• Preprocessing images for computer vision and object detection
• Improving the readability of scanned documents with uneven lighting
• Enhancing details in photographs with challenging lighting conditions

Comparison with Regular Contrast Enhancement

Unlike regular contrast enhancement or histogram equalization, CLAHE:

• Enhances local contrast rather than global contrast
• Preserves details in both dark and bright regions simultaneously
• Prevents over-amplification of noise through contrast limiting
• Adapts to different regions of the image based on local content
• Produces more natural-looking results for many types of images