Skip to content

Image Processing

Featrix can understand images referenced by URL in your datasets, turning product photos, document scans, user avatars, and any other images into rich features that interact with all your other columns.

The Problem

Many real-world datasets contain image URLs — product photos in e-commerce catalogs, property photos in real estate listings, document scans in insurance claims, profile pictures in user databases. Traditional tabular ML ignores these entirely or requires a separate computer vision pipeline with manual feature engineering.

How Featrix Solves It

When image understanding is enabled, Featrix automatically:

  1. Detects which columns contain image URLs
  2. Downloads and analyzes each image using three complementary models
  3. Learns how image content relates to every other column in your data

No separate vision pipeline. No manual feature engineering. Images become first-class features alongside your text, numbers, and categories.

What Gets Extracted

Model What It Captures Example
DINOv2 (visual) Overall visual content — composition, color, texture, style Two similar product photos have similar embeddings
EasyOCR (text) Any text visible in the image — labels, prices, signs "Nike Air Max $129.99" read from a shoe label
ResNet (objects) What objects are in the image, with confidence scores {"running_shoe": 0.92, "sneaker": 0.05}

Cross-Column Relationships

The real value is in how Featrix connects image content to your other data:

  • Image + Text: OCR text from images is matched against text columns using word overlap, substring matching, and semantic similarity. A brand name on a product label matches the brand column.

  • Image + Categories: Detected objects are semantically matched against category values. ResNet detecting "laptop" correlates with a category column containing "Electronics".

  • Image + Numbers: Numbers found via OCR (prices, quantities) are compared to numeric columns. A receipt showing "$42.99" matches a total_amount of 42.99.

  • Image + Image: When multiple image columns exist, visual similarity, shared text, and overlapping objects create natural relationships.

Example Scenarios

E-Commerce Product Catalog

Column Type Example
product_image IMAGE_URL https://cdn.shop.com/shoes/nike-air-max.jpg
brand Set Nike
category Set Running Shoes
price Scalar 129.99
description String "Nike Air Max 90 running shoe, white/black"

Featrix discovers: the shoe label says "Nike" (matches brand), the image looks like athletic footwear (matches category), "$129.99" is visible on the tag (matches price), and the description overlaps with OCR text.

Real Estate Listings

Column Type Example
photo_url IMAGE_URL https://photos.realty.com/house-123.jpg
property_type Set House
price Scalar 450000
sqft Scalar 2200

Featrix learns: houses with pools, large yards, and modern kitchens (visual features) correlate with higher prices. Property type maps to distinctive visual patterns.

Document Processing

Column Type Example
scan_url IMAGE_URL https://docs.company.com/invoice-456.png
doc_type Set Invoice
amount Scalar 1250.00
vendor String "Acme Corp"

Featrix reads: OCR extracts "Invoice", "$1,250.00", and "Acme Corp" from the scan, matching all three columns directly.

Getting Started

Add to your config.json:

{
  "enable_image_url_detection": true
}

Featrix handles the rest. For full configuration options and technical details, see Image Understanding.