Roboflow Universe Palmdetection Crack_detection_experiment

Crack_detection_experiment Computer Vision Project

Download this Dataset Try Pre-Trained Model

TRY THIS MODEL

Drop an image or

browse your device

Images

433 images

Explore Dataset

This images and some annot was taken from this:

@misc{ 400-img_dataset,
    title = { 400 img Dataset },
    type = { Open Source Dataset },
    author = { Master dissertation },
    howpublished = { \url{ https://universe.roboflow.com/master-dissertation/400-img } },
    url = { https://universe.roboflow.com/master-dissertation/400-img },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2022 },
    month = { dec },
    note = { visited on 2023-01-14 },
}

Anyway, the instance segmentation format was wrong with some annot because it has bbox labeled format (class Xcenter Ycenter Width Height) instead of segmentation format (class X1 Y1 X2 Y2 .... Xn Yn).

So, I corrected it

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.