01
Computer Vision & ML
Neural networks, image classification, object and anomaly detection, medical imaging.
Available for projects
Applied Mathematics & AI
I teach machines how to see.
From medical image processing and neural networks to embedded systems, I build intelligent systems that work in the real world.
Currently working with
EyeSpec FAW Group /Juniorstudium CAU Kiel /BWKI 2026 /SterilVision
21 Projects
6 Areas
16 Technologies
2023 Active since
My own research
Object recognition that keeps its cool
S2P-Net is my own neural network. It recognizes objects reliably even when they are rotated and only a handful of training images are available, by combining spectral and spatial features in a polar representation.
- Rotation-invariant Recognizes objects regardless of how they are turned.
- Spectral & spatial Fuses frequency and spatial features in polar form.
- Low-data regime Works where hardly any training data is available.
Read the paper on arXiv
arXiv · 2026 · First author
Vision Lab
See how machines see
This portrait runs through real image processing, live in your browser. Move the cursor across it or pick a mode.
- Scan / Spotlight
- Sobel
- Threshold
Move the cursor to scan
Close to my heart
Skill-Lens: I can do this!
An assistive app for people with learning difficulties. It guides you through everyday tasks in Easy Language. The camera confirms every step as it happens. No cloud, non-profit.
- Easy Language & large buttons
- Runs offline, photos stay on the device
- Non-profit, a labor of love
About
Mathematics, models and machines.
I'm Albert Heruth, I combine applied mathematics with hands-on engineering. My focus is computer vision and machine learning, from the idea all the way to systems running on real hardware.
Alongside my work on automation and camera inspection, I build my own CV models, embedded prototypes and tools, happiest where hardware meets intelligent software.
Two themes drive me most: my own research, like my network S2P-Net, and technology that helps people in everyday life, such as my assistive app Skill-Lens.
I don't just look for the bug, I look for the solution. I'd take a well-understood, cleanly documented system over a quick hack any day.
Computer Vision PyTorch OpenCV Python Machine Learning Deep Learning Applied Mathematics C / C++ ESP32 / Arduino Raspberry Pi Flask / FastAPI Streamlit Linux Docker Kotlin / Android Git
Capabilities
What I do
Three areas I feel at home in, from the first idea to a system that actually runs.
02
Embedded & IoT
ESP32, Raspberry Pi, sensors and real-time signal processing, where software meets hardware.
03
Systems & Infrastructure
Linux, Docker, networking and clean, maintainable backends & tooling.
Selected projects
What I'm working on
A glimpse of my work. Find everything in the archive.
P
PixLang
A minimal, human-readable DSL for describing computer-vision pipelines, with variables, loops, plugins, a linter and a browser-based visual flow editor (35 commands, 253 passing tests).
Code →
SterilVision
A computer-vision platform supporting instrument inspection in a medical and surgical context.
View →
CNN-Visualizer
An interactive tool for debugging and visualizing CNNs with Grad-CAM, feature maps and misclassification analysis.
Code →
Let's build something.
Interested in working together or curious about my projects? I would love to hear from you.
Get in touch