Image Type Classifier

Software componentKnowledge & DataKnowledge & DataVariation point (abstract)arc:ImageTypeClassifier

An abstract preprocessing classifier that assigns each image a content class, such as chart/plot versus general image, to drive processing-path selection.

Responsibility. Classifies images by content type so they can be routed to the appropriate vision model.

Also known as: Content complexity assessor, Chart detector

Direct neighbourhood (hover for relationship types)

Variants

Variant	When to choose
Heuristic Image Type Classifier	Choose when a simple rule suffices to spot charts, e.g., images containing axis labels, legends or grid patterns, as in the financial-report worked example.
VLM-based Image Type Classifier	Choose when routing at scale and a vision-language model is already deployed, reusing it for meta-classification instead of adding a separate classification model.

Relationships

is invoked by dependency

Multimodal Content Router Ch2.7

Design guidance

MUST be sufficiently accurate, because misclassifying a chart as a diagram routes it to the wrong pipeline and can lose critical data.

Classification

Quality attributes: Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated: Misrouting charts to the wrong preprocessing pipeline

Sources

Ch2.7: T. Nguyen, "Multimodal RAG Approaches," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.7. ISBN: 9798244538229.