Convolutional Neural Network for Face Detection

An open source library for face detection in images. Provides a pretrained convolutional neural network based on < https://github.com/ShiqiYu/libfacedetection> which can be used to detect faces which have size greater than 10x10 pixels.

Bindings to 'OpenCV' Computer Vision Library

Exposes some of the available 'OpenCV' < https://opencv.org/> algorithms, such as a QR code scanner, and edge, body or face detection. These can either be applied to analyze static images, or to filter live video footage from a camera device.

Perform HTTP Requests and Process the Responses

Tools for creating and modifying HTTP requests, then performing them and processing the results. 'httr2' is a modern re-imagining of 'httr' that uses a pipe-based interface and solves more of the problems that API wrapping packages face.

An Interface for Face Recognition

Provides an interface to the 'Kairos' Face Recognition API < https://kairos.com/face-recognition-api>. The API detects faces in images and returns estimates for demographics like gender, ethnicity and age.

Transformer Emotion Analysis for Text, Image, Video, and Speech

Zero-shot emotion classification for text, images, video and speech, and tools to find faces and code them by hand. Text is scored with 'Hugging Face' transformer pipelines (default 'cross-encoder/nli-distilroberta-base'). Images and video are scored with 'OpenAI CLIP'; faces can be limited to those found by 'OpenCV YuNet'. Speech segments are scored with 'LAION CLAP'. Frame scores can be calibrated and combined into posteriors, and detected faces or other items can be turned into a local coding task served from R. Any other zero-shot model can be selected by its name on < https://huggingface.co/models>. For details see Tomašević, Golino, and Christensen (2026) .

Fast 3D Alpha Hull with Label Propagation

Fast 3D alpha shape (alpha hull) computation with label propagation from input points to hull vertices and faces. Uses 'CGAL' for robust geometric computations. Optimized for Light Detection and Ranging ('LiDAR') processing and tree segmentation workflows. The implementation follows the alpha shape algorithm described in Edelsbrunner et al. (1983) .

Epistasis Test in Meta-Analysis

Traditional meta-regression based method has been developed for using meta-analysis data, but it faced the challenge of inconsistent estimates. This package purpose a new statistical method to detect epistasis using incomplete information summary, and have proven it not only successfully let consistency of evidence, but also increase the power compared with traditional method (Detailed tutorial is shown in website).

Tool for Annotating Images in Preparation for Analysis

A tool to help create shiny apps for selecting and annotating elements of images. Users must supply images, questions, and answer choices. The user interface is a dynamic shiny app, that displays the images and questions and answer choices. The data generated can be saved to a file that can be used for subsequent analysis. The original purpose was to annotate still images from tennis video for face recognition and emotion detection purposes.

Discrete Morse Theory for 3D Meshes Derived from Point Clouds

Ultra-fast computation of discrete Morse (Marston Morse) gradient vector fields and critical simplices (0-simplices: vertices, 1-simplices: edges, 2-simplices: faces) on 3D triangular meshes from point clouds. Provides C++ backend with parallel processing for large-scale topological analysis, including connected component analysis and visualization tools. Perfect for Light Detection and Ranging ('LiDAR') data, computational topology, and geometric analysis applications. The implementation follows Forman (1998) for discrete Morse theory, with extensions for 3D mesh processing.

R Interface to Stan

User-facing R functions are provided to parse, compile, test, estimate, and analyze Stan models by accessing the header-only Stan library provided by the 'StanHeaders' package. The Stan project develops a probabilistic programming language that implements full Bayesian statistical inference via Markov Chain Monte Carlo, rough Bayesian inference via 'variational' approximation, and (optionally penalized) maximum likelihood estimation via optimization. In all three cases, automatic differentiation is used to quickly and accurately evaluate gradients without burdening the user with the need to derive the partial derivatives.