Skip to main content

Image

Supported formats​

BMP, GIF, JPEG, PNG, TIFF, WebP, SVG, ICO

Description​

This backend performs processing of image data in various formats, extracts metadata (including Exif) and performs additional analysis if necessary.

info

Available in Contextal Platform 1.0 and later.

Features​

Brand Detection

The image processor runs our custom AI model optimized for visual detection of well-known brands, frequently impersonated in phishing attacks. It can spot logos anywhere within an image and automatically include the findings in the object metadata under the $logos key.

NSFW Detection

The backend uses a neural network to detect images with NSFW (Not Safe For Work) content, additionally providing a category of such content. It uses GantMan's model to identify the following categories:

  • Drawing - safe for work drawings (including anime)
  • Hentai - hentai and pornographic drawings
  • Porn - pornographic images, sexual acts
  • Sexy - sexually explicit images, not pornography
  • Neutral - safe for work neutral images

The final verdict is stored in the object's metadata under the $nsfw_verdict key, which may have a value of Unknown in case there wasn't enough confidence to assign one of the above categories.

Optical Character Recognition

The backend performs optical character recognition (OCR) when requested and extracts text for further processing. The text processing backend can later detect the text's language, sentiment, profanities, embedded URLs, potential passwords, and more.

QR Code Detection & Processing

The backend detects QR codes in images, and decodes them for further processing by other backends such as Text, URL, or Domain.

Symbols​

Object​

  • LIMITS_REACHED → limits triggered while processing an image
  • SVG_ERRORS → errors detected while processing an SVG image
  • SVG_JS → JavaScript detected inside an SVG image
  • BLURRED → large portion of the image is blurred

Children​

  • TOOBIG → text extracted via OCR was not stored as it exceeds the limits

Example Metadata​

{
  "org": "ctx",
  "object_id": "c4fc7668fdafdac2839b9dd7049da07b0a12cdab62cc165b878cccdb49478f31",
  "object_type": "Image",
  "object_subtype": "PNG",
  "recursion_level": 1,
  "size": 261648,
  "hashes": {
    "sha512": "15023992bd7568e98d283a3f951f8a4359ea3d58612be78bb9bfb72fd55ba111a98444d1a3a7b08383181cf3f27160f12e441a3ef16afd90e65afdee027a673e",
    "sha256": "c4fc7668fdafdac2839b9dd7049da07b0a12cdab62cc165b878cccdb49478f31",
    "md5": "73fa882983231c19dca6c5f8b4f20fc0",
    "sha1": "02a7f35277c8f1f8321017d67419557943f69f2a"
  },
  "ctime": 1758828920.218504,
  "entropy": 7.9582562355383555,
  "relation_metadata": {
    "name": "blurry.png"
  },
  "ok": {
    "symbols": [
      "BLURRED"
    ],
    "object_metadata": {
      "_backend_version": "2.0.0",
      "format": "png",
      "height": 960,
      "logos": [
        "adobe",
        "adobe_block",
        "adobe_italic",
        "gmail",
        "outlook"
      ],
      "nsfw_predictions": {
        "Drawings": 0.007282,
        "Hentai": 0.000317,
        "Neutral": 0.992383,
        "Porn": 0.000005,
        "Sexy": 0.000013
      },
      "nsfw_verdict": "Neutral",
      "pixel_format": "RGB8",
      "width": 1280
    },
    "children": []
  }
}

Example Queries​

object_type == "Email"
    && @has_descendant(object_image == "Image" &&
        @match_object_meta($nsfw_verdict == "Hentai")
        || @match_object_meta($nsfw_verdict == "Sexy")
        || @match_object_meta($nsfw_verdict == "Porn")
    )
  • This query matches an Email object, which at some level contains an Image object with NSFW content.
object_type == "Image"
    && @has_child(object_type == "Text"
        && @match_object_meta($natural_language_profanity_count > 0))
  • This query matches an Image object, out of which a Text object was extracted (via OCR), in which some profanities were identified.

Configuration Options​

  • max_child_output_size → maximum size of a single output children object (default: 41943040)