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.

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.