# Google - American Sign Language Fingerspelling Recognition — Data

来源：https://www.kaggle.com/competitions/asl-fingerspelling/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The goal of this competition is to detect and translate American Sign Language (ASL) fingerspelling into text. 

This competition requires submissions to be made in the form of [TensorFlow Lite models](https://www.tensorflow.org/lite). You are welcome to train your model using the framework of your choice as long as you convert the model checkpoint into the tflite format prior to submission. Please see [the evaluation page](https://www.kaggle.com/competitions/asl-fingerspelling/overview/evaluation) for details.

Update: the rerun dataset [has been published here](https://www.kaggle.com/datasets/sohier/529505295052950/).

##Files

**[train/supplemental_metadata].csv** 

*   `path` - The path to the landmark file.
*   `file_id` - A unique identifier for the data file.
*   `participant_id` - A unique identifier for the data contributor.
*   `sequence_id` - A unique identifier for the landmark sequence. Each data file may contain many sequences.
*   `phrase` - The labels for the landmark sequence. The train and test datasets contain randomly generated addresses, phone numbers, and urls derived from components of real addresses/phone numbers/urls. Any overlap with real addresses, phone numbers, or urls is purely accidental. The supplemental dataset consists of fingerspelled sentences. _Note that some of the urls include adult content._ The intent of this competition is to support the Deaf and Hard of Hearing community in engaging with technology on an equal footing with other adults.


**character_to_prediction_index.json** 


**[train/supplemental]_landmarks/** The landmark data. The landmarks were extracted from raw videos with the [MediaPipe holistic model](https://google.github.io/mediapipe/solutions/holistic.html). Not all of the frames necessarily had visible hands or hands that could be detected by the model.
The landmark files contain the same data as in the ASL Signs competition (minus the row ID column) but reshaped into a wide format. This allows you to take advantage of the Parquet format to entirely skip loading landmarks that you aren't using.


*   `sequence_id` - A unique identifier for the landmark sequence. landmark files contain approximately 1,000 sequences. The sequence ID is used as the dataframe index.
*   `frame` - The frame number within a landmark sequence.
*   `[x/y/z]_[type]_[landmark_index]` - There are now 1,629 spatial coordinate columns for the x, y and z coordinates for each of the 543 landmarks. The type of landmark is one of `['face', 'left_hand', 'pose', 'right_hand']`. Details of the [hand landmark locations can be found here](https://google.github.io/mediapipe/solutions/hands.html#hand-landmark-model). The spatial coordinates have already been normalized by MediaPipe. Note that the MediaPipe model is not fully trained to predict depth so you may wish to ignore the z values. The landmarks have been converted to float32.

_Landmark data should not be used to identify or re-identify an individual. Landmark data is not intended to enable any form of identity recognition or store any unique biometric identification._