Photography: Where Art Meets Science

"The camera is an instrument that teaches people how to see without a camera."

— Dorothea Lange

Seeing Patterns: From Landscapes to Algorithms

Before I became a computational scientist, I was a professional photographer. The camera taught me to see—not just to look. To recognize patterns in chaos, to find structure in complexity, to tell stories that transcend language.

These aren't separate skills from my technical work. They're the same skill applied to different domains.

Whether I'm composing a landscape photograph or architecting a GPU-accelerated imaging pipeline, I'm asking the same fundamental questions: What's the signal? What's the noise? How do I communicate what matters?

The Artistic Lens: Natural Photography

Photography taught me to see the world as a system of patterns, light, and relationships. A compelling photograph doesn't just capture a moment—it reveals structure that was always there but rarely noticed.

📷 Environmental Portraiture

Capturing subjects in context, revealing relationships between figure and landscape

🔍 Pattern & Texture

Finding order in natural chaos—rock formations, water surfaces, weather patterns

✨ Light as Subject

Understanding how light defines form, creates mood, and directs attention

⏱️ The Decisive Moment

Recognizing when all elements align for maximum impact

See recent work on Instagram

📸 @eric.wait on Instagram

Applied Photography AI

Solving Real Problems at Scale

Making sense of 200,000+ images isn't just a technical challenge—it's personal.

Home Media AI is my open-source solution: an ML system that automatically identifies "technically excellent and aesthetically pleasing" images while providing rich searchability across subjects, locations, and hierarchical classifications.

It's the intersection philosophy in practice: artistic judgment (what makes a great photo?) meets technical implementation (how do we automate that at scale?).

Learn More About Home Media AI →

Technical Approach

  • Python/SQLAlchemy backend with MariaDB
  • OpenCV/Pillow for image processing
  • YOLO for object detection (people, pets, objects)
  • Scikit-learn for quality assessment models
  • Everything checksummed for long-term archival

From Lens to Algorithm: The Bridge

Pattern Recognition in Noisy Data

In Photography

Spotting compositional elements in a complex scene—the leading line hidden in shadows, the repeating forms that create rhythm.

In ML Systems

Identifying signal in terabyte-scale biological datasets. Recognizing when an apparent pattern is real structure versus noise.

Working Under Constraints

In Photography

Fixed focal length forces creative angles. Limited dynamic range means choosing what to preserve. Fleeting light means one chance.

In Production ML

Limited GPU memory, real-time latency requirements, edge deployment constraints. Constraints drive creativity.

Communication Over Complexity

"There is nothing worse than a sharp image of a fuzzy concept." — Ansel Adams

That applies equally to photography and to machine learning architectures.

Learning to See Without the Camera

What photography really taught me:

Structure exists in apparent chaos — Whether in a forest or a high-dimensional dataset

Context defines meaning — A pixel value means nothing without understanding its relationships

Simplicity is hard — Both in composition and in system design

The best solution requires subtracting — Knowing which computation you don't need is the ultimate optimization

The intersection of art and science isn't a compromise—it's where both become more powerful.