Pupil: Image Processing Skills

SUMMARY

Pupil is a module in the Telekinesis SDK containing skills for image processing and low-level vision algorithms.

It provides a set of modular tools for preprocessing, filtering, and transforming images, enabling developers to build robust vision pipelines for robotics applications.

Install Telekinesis Skill Library

Create an API key, install telekinesis-ai and module specific installations and dependencies in a Python environment.

Open installation →

Go to the Quickstart

Pick a starter and run your first Skill end-to-end - 2D / 3D vision, webcam capture, robot motion, or a full vision-to-robot pipeline, all visualized in Rerun.

Open quickstart →

When to Use Pupil?

Use Pupil for robotics applications that require low-level image processing and preprocessing, such as:

• Enhancing camera input for vision-guided pick-and-place
• Preparing images for object detection or segmentation
• Noise reduction and filtering for robot navigation
• Real-time feature extraction for tracking or visual servoing
• Camera calibration and image rectification in robotics pipelines

What Does Pupil Provide?

Pupil includes a collection of modular skills for:

• Image filtering and enhancement
• Noise reduction and smoothing
• Geometric transformations and rectification
• Basic computer vision algorithms for preprocessing

How to Use Pupil?

To use the skills from Pupil, simply use:

from telekinesis import pupil

Here is a minimal example:

from telekinesis import pupil
from datatypes import datatypes, io

# Load an image
image = io.load_image(filepath=datatypes.String("path/to/image.jpg"))

# Apply Gaussian blur
blurred_image = pupil.filter_image_using_gaussian_blur(
    image=image,
    kernel_size=datatypes.Int(5),
    sigma_x=datatypes.Float(1.0)
)

# Save the result
io.save_image(image=blurred_image, filepath=datatypes.String("output.jpg"))

Overview of Skills

SDK Call	Description
enhance_image_using_clahe	Applies Contrast Limited Adaptive Histogram Equalization.
enhance_image_using_auto_gamma_correction	Applies gamma correction for brightness adjustment.
enhance_image_using_white_balance	Applies white balance correction to remove color casts.
filter_image_using_bilateral	Applies bilateral filtering for edge-preserving smoothing.
filter_image_using_blur	Applies simple box blur for fast smoothing.
filter_image_using_box	Applies normalized box filter with depth control.
filter_image_using_gaussian_blur	Applies Gaussian blur for smooth noise reduction.
filter_image_using_median_blur	Applies median filtering to remove salt-and-pepper noise.
filter_image_using_laplacian	Applies Laplacian operator for edge detection.
filter_image_using_sobel	Applies Sobel operator for gradient-based edge detection.
filter_image_using_scharr	Applies Scharr operator for improved gradient estimation.
filter_image_using_gabor	Applies Gabor filter for texture and oriented feature detection.
filter_image_using_frangi	Applies Frangi vesselness filter for detecting tubular structures.
filter_image_using_hessian	Applies Hessian-based vesselness filtering.
filter_image_using_sato	Applies Sato tubeness filter for ridge detection.
filter_image_using_meijering	Applies Meijering neuriteness filter for detecting thin structures.
filter_image_using_morphological_erode	Erodes bright regions to remove small features.
filter_image_using_morphological_dilate	Dilates bright regions to fill gaps and expand features.
filter_image_using_morphological_close	Closes holes by applying dilation followed by erosion.
filter_image_using_morphological_open	Opens regions by applying erosion followed by dilation.
filter_image_using_morphological_gradient	Computes morphological gradient for edge detection.
filter_image_using_morphological_tophat	Extracts small bright features using top-hat transform.
filter_image_using_morphological_blackhat	Extracts small dark features using black-hat transform.
transform_image_using_pyramid_downsampling	Downsamples image with anti-aliasing for pyramid construction.
transform_image_using_pyramid_upsampling	Upsamples image for pyramid reconstruction.
transform_mask_using_blob_thinning	Applies morphological thinning for skeletonization.
calculate_image_pca	Computes PCA on binary mask and visualizes centroid and principal axis.
calculate_image_centroid	Calculates centroid of non-zero pixels in a binary mask.
convert_image_color_space	Converts image between color spaces (e.g., BGR to RGB, RGB to HSV).
normalize_image_intensity	Normalizes image intensity using minmax or histogram methods.
split_image_into_channels	Splits image into color channels (B, G, R).
merge_image_from_channels	Merges channel images into multi-channel image.
resize_image	Resizes image by scale factor.
resize_image_with_aspect_fit	Resizes to target dimensions while preserving aspect ratio.
rotate_image	Rotates image by angle in degrees.
translate_image	Shifts image by dx and dy pixels.
pad_image	Pads image on top, bottom, left, and right.
crop_image_center	Crops image to fixed dimensions, centered; pads if smaller.
crop_image_using_bounding_boxes	Crops image using multiple bounding boxes.
crop_image_using_polygon	Crops image using polygon mask.
bitwise_and_images	Performs bitwise AND between two images.
bitwise_or_images	Performs bitwise OR between two images.
bitwise_xor_images	Performs bitwise XOR between two images.
bitwise_difference_images	Performs absolute difference between two images.
bitwise_not_image	Performs bitwise NOT (inversion) on image.
overlay_images_using_weighted_overlay	Blends two images using weighted overlay.
project_pixel_to_camera_point	Projects pixel and depth to 3D point in camera coordinates.
project_camera_point_to_pixel	Projects 3D camera point to pixel coordinates.
project_pixel_to_world_point	Projects pixel and depth to 3D point in world coordinates.
project_world_point_to_pixel	Projects 3D world point to pixel coordinates.