Card Detection Computer Vision Project

* 50% probability of horizontal flip * 50% probability of vertical flip * Auto-orientation of pixel data (with EXIF-orientation stripping) * Equal probability of one of the following 90-degree rotations: none, clockwise, counter-clockwise, upside-down * Random Gaussian blur of between 0 and 1.75 pixels * Random brigthness adjustment of between -25 and +25 percent * Random exposure adjustment of between -15 and +15 percent * Random rotation of between -10 and +10 degrees * Random shear of between -2° to +2° horizontally and -2° to +2° vertically * Randomly crop between 0 and 15 percent of the image * Resize to 640x640 (Stretch) * Salt and pepper noise was applied to 2 percent of pixels * annotate, and create datasets * collaborate with your team on computer vision projects * collect & organize images * export, train, and deploy computer vision models * understand and search unstructured image data * use active learning to improve your dataset over time 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 ============================== Cards are annotated in YOLOv8 format. For state of the art Computer Vision training notebooks you can use with this dataset, Playing Cards - v4 FASTmodel-resized640-aug3x Roboflow is an end-to-end computer vision platform that helps you The dataset includes 24240 images. The following augmentation was applied to create 3 versions of each source image: The following pre-processing was applied to each image: This dataset was exported via roboflow.com on March 7, 2023 at 7:04 PM GMT To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com visit https://github.com/roboflow/notebooks