V7 Neurons
V7 allows you to label, train, and deploy vision AI models for industrial use.
See Others

AI Defect Inspection

Spot damage, scratches, cracks, dents, or missing pieces as small as 0.01% of an image. Detect unforeseeable defects that differ in shape from previously collected examples.

V7 allows developers to turn images and video of your defects into state of the art vision AI with semi-automated tagging, model training, and inference deployment.

Get started today by automating the detection of anomalies in your production line or manufacturing process, and bring the growing value of AI to your supply chain.

Hover over the image below to see what the AI identifies

See AI Defect Inspection in Real Time

More examples of defect inspection developed on V7

Hover over the images below or click to enlarge.

What can you identify

No two defects are alike, but they generally fall within broad categories of appearances:

Scratch detection
Scratches
Defect inspection
Discoloration
Crack detection computer vision
Cracks
Pothole detection
Holes
Damage detection with computer vision
Dents
Flange rust detection
Unknown anomalies / missing pieces

Continually Improving AI

AI performance shouldn't stop at the first training session.
Sync your product with a dataset and continually improve your AI performance by turning its output into new ground truth. Continual learning will allow your models to surpass 95% accuracy barriers and reach 99% and above as more data from your use case or product is supervised by humans, and learnt by your AI.

v7 neurons product
Your product
accurate labeling with v7 darwin
Fast labeling on V7 Darwin
image dataset
Newly collected images or video
model training and pruning
Training & continual learning

Zero to State of the Art

Bring AI to life, leave the R&D to us. With the fast pace of deep learning's state of the art, V7 ensures that your models are the most accurate on the market. By continually updating our architecture, and leveraging an extensively pre-trained backbone, your models will always outperform competitors whilst saving you costly R&D efforts.

Instance Segmentation (Object Detection + Segmentation) benchmark:

V7 Neurons (VoVNet)

Average Precision
46.0
Inference speed (FPS)
20

Mask R-CNN (Detectron2)

Average Precision
41.0
Inference speed (FPS)
13

YOLACT550++ (YOLO)

Average Precision
34.6
Inference speed (FPS)
27

Model backbone benchmark:

V7 Neurons (Ours)

Average Precision - Detection
43.8
AP - Masking
39.3

ResNet-50

Average Precision - Detection
41.0
AP - Masking
37.2

MobileNetV2

Average Precision - Detection
33.0

Benchmarks were performed on the MS-COCO dataset. COCO is largely composed of large, frame-filling objects that are easy to detect by modern neural network architectures. V7 Neurons outperformed Mask-RCNN primarily on the detection of small and uncommon objects, which matter most in industry cases.

Pick a Deployment Configuration

Deploy model in the cloud on V7's scale-agnostic inference engine NJORD, or run them on-premise through a docker image at real-time speeds. Run V7 Neurons on powerful NVIDIA T4 servers in your datacenter to serve multiple cameras, or on versatile NVIDIA Jetson modules for low volume or low-power consumption.

V7 Deep and Slim model sizing
v7 on aws

Cloud - REST API

On-premise GPU Server

v7 on Jetson Xavier NX

NVIDIA Jetson

v7 on iOS

Mobile (iOS) (Coming 2021)

Ready to get started?

Schedule a demo with our team or discuss your project.