# Image Processing Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/image-processing
> Markdown URL: https://aitinkerers.org/technologies/image-processing.md
> Technology record last updated: 2026-03-10T02:10:44Z
> Generated: 2026-09-22T22:31:10Z

Digital Image Processing (DIP) uses algorithms to manipulate pixel data—enhancing quality, extracting features, and preparing images for autonomous machine perception (Computer Vision).

DIP is the application of computer algorithms to a digital image to achieve a specific outcome: an improved image or extracted data. Core tasks include image enhancement (e.g., noise reduction, sharpening), restoration, and segmentation. Key applications are crucial across multiple sectors: medical imaging (MRI/X-ray analysis), remote sensing (satellite data), and automated inspection for quality control. This technology, dating back to the 1964 Ranger 7 lunar photos, is the foundational signal processing layer for modern AI systems like facial recognition.

- Official technology site: https://en.wikipedia.org/wiki/Digital_image_processing
- Public AI Tinkerers demos and talks: 3
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Multi-Pass Building Defect Detection: Getting a VLM to Find Facade Defects for Visual Inspections](https://dc.aitinkerers.org/talks/rsvp_3zzrUv1SHxo)

We built an AI system that turns raw building inspection photos into annotated defect reports, detecting 15 distinct pathologies (building cracks, sealant degradation, brick spalling, mortar erosion, steel corrosion, and so on) with accurate bounding boxes across facade inspections. I'll show the architecture of how we've setup the inspection image processing pipeline: the multi-pass detection architecture, the model training process, the defect annotation catalog, the eval harness we use to verify accuracy on new datasets & catch regressions. And why this was our selected way to set it up. I'll walk through the examples of real reports going from photo dump to structured outputs (where the model gets it right and where it still needs a human check).

- Event context: AI Tinkerers DC Metro - Arlington: July 23rd Meetup — 2026-07-23 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_3zzrUv1SHxo

### [Exercise Posture Tracking Using Computer Vision](https://raleigh.aitinkerers.org/talks/rsvp_QACg5zj28MM)

I've created an unsupervised computer vision algorithm to detect back rounding during deadlift. In short, I've demonstrated that I can measure the curvature of the back in an unsupervised way, and that a rounded back produces a different signal from a flat back. I've used off-the-shelf pose tracking and segmentation models to measure the back curvature. This could help guide learning of proper form during deadlift and other exercises.

- Event context: AI Tinkerers Raleigh Meetup — February 11, 2026 — 2026-02-11 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_QACg5zj28MM

### [Omni ingestion RAG](https://medellin.aitinkerers.org/talks/rsvp_FQ91nU7B_8Q)

Ingesta multimodal en aplicación RAG (Retrieval Augmented Generation) empleando unnestructure y modelos multi modales para procesar imágenes, tablas, y texto.

- Event context: AI Tinkerers Medellín #8 - 5 de Diciembre — 2024-12-05 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_FQ91nU7B_8Q

## Related Technologies

- [Autoencoder](https://aitinkerers.org/technologies/autoencoder) ([Markdown](https://aitinkerers.org/technologies/autoencoder.md)) — 1 public demo
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [Claude Sonnet](https://aitinkerers.org/technologies/claude-sonnet) ([Markdown](https://aitinkerers.org/technologies/claude-sonnet.md)) — 20 public demos
- [Computer Vision](https://aitinkerers.org/technologies/computer-vision) ([Markdown](https://aitinkerers.org/technologies/computer-vision.md)) — 22 public demos
- [Deep learning](https://aitinkerers.org/technologies/deep-learning) ([Markdown](https://aitinkerers.org/technologies/deep-learning.md)) — 10 public demos
- [Detectron2](https://aitinkerers.org/technologies/detectron2) ([Markdown](https://aitinkerers.org/technologies/detectron2.md)) — 1 public demo
- [Gaussian Mixture Model](https://aitinkerers.org/technologies/gaussian-mixture-model) ([Markdown](https://aitinkerers.org/technologies/gaussian-mixture-model.md)) — 1 public demo
- [Google Gemini Pro](https://aitinkerers.org/technologies/google-gemini-pro) ([Markdown](https://aitinkerers.org/technologies/google-gemini-pro.md)) — 1 public demo
- [Image](https://aitinkerers.org/technologies/image) ([Markdown](https://aitinkerers.org/technologies/image.md)) — 4 public demos
- [Instance segmentation](https://aitinkerers.org/technologies/instance-segmentation) ([Markdown](https://aitinkerers.org/technologies/instance-segmentation.md)) — 1 public demo
- [Isolation Forest](https://aitinkerers.org/technologies/isolation-forest) ([Markdown](https://aitinkerers.org/technologies/isolation-forest.md)) — 1 public demo
- [K-Nearest Neighbors](https://aitinkerers.org/technologies/k-nearest-neighbors) ([Markdown](https://aitinkerers.org/technologies/k-nearest-neighbors.md)) — 1 public demo
- [Local Outlier Factor](https://aitinkerers.org/technologies/local-outlier-factor) ([Markdown](https://aitinkerers.org/technologies/local-outlier-factor.md)) — 1 public demo
- [Mask2Former](https://aitinkerers.org/technologies/mask2former) ([Markdown](https://aitinkerers.org/technologies/mask2former.md)) — 1 public demo
- [Mask R-CNN](https://aitinkerers.org/technologies/mask-r-cnn) ([Markdown](https://aitinkerers.org/technologies/mask-r-cnn.md)) — 1 public demo
- [MediaPipe](https://aitinkerers.org/technologies/mediapipe) ([Markdown](https://aitinkerers.org/technologies/mediapipe.md)) — 7 public demos
- [MMDetection](https://aitinkerers.org/technologies/mmdetection) ([Markdown](https://aitinkerers.org/technologies/mmdetection.md)) — 1 public demo
- [Multimodal Models](https://aitinkerers.org/technologies/multimodal-models) ([Markdown](https://aitinkerers.org/technologies/multimodal-models.md)) — 6 public demos