Cropped images of three hinged surgical tool categories—clamps, needle holders, and shears—labeled for binary classification of open or closed states. The dataset is intended for training and evaluating hinge-state classifiers in a two-stage surgical tool recognition pipeline. It was created by author joonhaim and last updated on 2026-04-04.
Use Cases
- Train binary classifiers to recognize open vs. closed states based on cropped images of surgical tools.
- Evaluate hinge-state classifiers as part of a two-stage surgical tool recognition pipeline.
- Benchmark model performance on specific tool categories (clamps, needle holders, shears).
Strengths
- Dataset contains images for three distinct surgical tool categories: clamps, needle holders, and shears.
- Target classes are clearly defined as 'open' and 'closed' for binary classification.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Row count is unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.
Provenance
- Source
- huggingface
- Freshness
- 2026-04-04