Computer vision datasets for retail intelligence
From shelf monitoring to product recognition, images.cv helps retail teams build structured datasets for in-store CV systems — with annotation, packaging, and ML-ready delivery.
Retail CV use cases
Datasets built for the computer vision problems retail teams actually solve.
Shelf & planogram compliance
Detect misplaced products and monitor shelf layout against planogram specs.
Product recognition & SKU ID
Train models to identify individual products and SKUs from shelf or catalog images.
Out-of-stock detection
Spot empty shelf slots and low-stock conditions in real time using in-store cameras.
Price tag & label reading
Extract pricing and label text from shelf-edge images for automated auditing.
Customer traffic & heatmaps
Analyze foot traffic patterns and generate store heatmaps from overhead camera feeds.
Self-checkout item recognition
Identify unscanned or misidentified items at self-checkout stations.
What you get
A structured, annotated dataset ready for your retail CV pipeline.
bboxes/
Bounding box JSON files
coco/
COCO-format annotations
data/
Final image files
masks/
Segmentation masks
yolo/
YOLO TXT annotations
index.csv
File-level dataset index
meta.json
Dataset metadata summary
Standard annotation formats
YOLO, COCO, bounding boxes, and segmentation masks included in every delivery.
Retail-specific labeling
SKU-level labels, product categories, and shelf position metadata where applicable.
Annotation alignment
All annotations are validated against image files to ensure consistency across the dataset.
Train / validation / test split
Optional dataset splitting with consistent file naming across partitions.
Tell us about your dataset needs
Fields marked with * are required.
Annotation formats needed
Ready to build your retail CV dataset?
Tell us about your use case and we'll scope a dataset that fits.