sign_language_translator.vision.utils module

This module provides utility functions for video processing.

sign_language_translator.vision.utils.iter_frames_with_opencv(path: str) → Generator[ndarray[Any, dtype[uint8]], None, None]

Extracts individual frames from a video file or an image file.

This function reads a video file using opencv and extracts its frames as numpy arrays. It can also read an image file and treat it as a single frame video.

Parameters:

path (str) – The path to the video or image file.

Yields:

NDArray[np.uint8] – numpy arrays representing frames from the video with shape: (height, width, color_channels).

Raises:

FileNotFoundError – If the video file is not found or cannot be opened.

sign_language_translator.vision.utils.read_frames_with_opencv(path: str) → List[ndarray[Any, dtype[uint8]]]

Extracts individual frames from a video file or an image file.

This function reads a video file using opencv and extracts its frames as numpy arrays. It can also read an image file and treat it as a single frame video.

Parameters:

path (str) – The path to the video or image file.

Returns:

A list of numpy arrays, each representing a frame from the video.

Return type:

List[NDArray]

Raises:

FileNotFoundError – If the video file is not found or cannot be opened.