{"id":37366,"date":"2025-04-04T07:00:00","date_gmt":"2025-04-04T14:00:00","guid":{"rendered":"https:\/\/cloudinary.com\/blog\/?p=37366"},"modified":"2025-04-04T11:03:10","modified_gmt":"2025-04-04T18:03:10","slug":"crop-face-eyes-copyright-and-licensing-compliance","status":"publish","type":"post","link":"https:\/\/cloudinary.com\/blog\/crop-face-eyes-copyright-and-licensing-compliance","title":{"rendered":"How to Crop at the Face (Eyes\/Mouth) Using Cloudinary for Copyright and Licensing Compliance"},"content":{"rendered":"\n

When you\u2019re producing external assets to be seen by customers and partners, ensuring compliance with copyright laws and usage rights is critical. It\u2019s also especially difficult considering assets that were once compliant can become non-compliant simply due to the passage of time.<\/p>\n\n\n\n

For example, model usage rights expire, and copyright constraints can prevent you from using an asset in your latest campaign. When issues like these arise, cropping the face can be an effective way to make the most of your visual media. <\/p>\n\n\n\n

This guide walks you through a solution using Cloudinary\u2019s Advanced Facial Attributes Detection Add-on<\/a> to handle this requirement efficiently.<\/p>\n\n\n\n

Why Crop Images at Specific Facial Features?<\/h2>\n\n\n\n
    \n
  1. Copyright restrictions.<\/strong> Certain wholesale partners require images of models to be cropped at specific facial features (e.g., below the eyes or above the mouth) before sharing.<\/li>\n\n\n\n
  2. Usage right expiry.<\/strong> When the licensing rights of a model\u2019s image expire, partial cropping allows continued usage of the image while complying with legal requirements.<\/li>\n<\/ol>\n\n\n\n

    Solution Overview<\/h2>\n\n\n\n

    By leveraging Cloudinary\u2019s Advanced Facial Attributes Detection Add-on, you can:<\/p>\n\n\n\n

      \n
    1. Detect facial landmarks like the eyes, nose, and mouth during the upload process.<\/li>\n\n\n\n
    2. Extract the lowest y coordinate for each feature (eyes, nose, mouth) and store them as contextual metadata<\/strong>.<\/li>\n\n\n\n
    3. Use this metadata to set up named transformations for cropping images at the desired facial feature.<\/li>\n\n\n\n
    4. Share the cropped images in collections with predefined templates for download.<\/li>\n<\/ol>\n\n\n\n

      Implementation Steps<\/h2>\n\n\n\n

      1. Detect Facial Features on Upload<\/h3>\n\n\n\n

      To enable detection, use the detection=adv_face<\/code> parameter during the upload process. This will analyze the image and extract facial landmarks, including the precise coordinates of key features.<\/p>\n\n\n\n

      Example Upload API Call<\/h4>\n\n\n
      const<\/span> result = {};\n\nconst<\/span> landmarks = e.upload_info?.info?.detection?.adv_face?.data[0<\/span>].facial_landmarks;\n\nfor<\/span> (const<\/span> [key, value] of<\/span> Object<\/span>.entries(landmarks)) {\n\n\u00a0\u00a0\u00a0\u00a0const<\/span> yValues = [];\n\n\u00a0\u00a0\u00a0\u00a0const<\/span> extractY = obj<\/span> =><\/span> {\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0for<\/span> (const<\/span> subKey in<\/span> obj) {\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0if<\/span> (typeof<\/span> obj[subKey] === 'object'<\/span>) {\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0extractY(obj[subKey]);\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0} else<\/span> if<\/span> (subKey === 'y'<\/span>) {\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0yValues.push(obj[subKey]);\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\n\n\u00a0\u00a0\u00a0\u00a0};\n\n\u00a0\u00a0\u00a0\u00a0extractY(value);\n\n\u00a0\u00a0\u00a0\u00a0result[key] = Math<\/span>.max(...yValues);\n\n}\n\ncurrent_asset.update({\"context\"<\/span>:{\"nose\"<\/span>: Math<\/span>.round(result.nose), \"mouth\"<\/span>: Math<\/span>.round(result.mouth), \"eye\"<\/span>: Math<\/span>.round(result.eye)}})<\/code><\/span>Code language:<\/span> JavaScript<\/span> (<\/span>javascript<\/span>)<\/span><\/small><\/pre>\n\n\n
      2. Store Contextual Metadata<\/h3>\n\n\n\n
      The on_success<\/code> callback above stores the detected coordinates of the nose, mouth, and eyes in the asset\u2019s contextual metadata. This ensures the cropping logic is reusable and can adapt to different requirements based on the customer\u2019s needs.<\/p>\n\n\n\n
      3. Set Up Named Transformations<\/h3>\n\n\n\n
      With the contextual metadata in place, you can define named transformations to crop images dynamically based on the desired facial feature.<\/p>\n\n\n\n
      In this transformation:<\/p>\n\n\n\n