rPET QUALITY — MEASURE · RECORD · PROVE

Recycled content,
from estimates to measurement

From January 2026, beverage companies in Korea must use 10% recycled content in their bottles. Yet the only way to prove that percentage is paperwork. We replace it with records measured right on the sorting line.

MEASUREMENT LAYER
rPET
Judged, recorded, proven — batch by batch.
measured, not claimed
304,699tClear PET bottles shipped per year (2021)
76.9%Recycling rate — volume is not the problem
3,400tFood-grade output — grade is the bottleneck
5.9×Supply shortfall vs 2026 demand
PROBLEM

From bottle to bottle:
the steps nobody records

Feedstock is plentiful. What's missing is a record proving that a given batch is food-grade. Sorting is judged by eye and nobody measures batch composition — so good material cannot be proven, and sells at commodity grade.

① CollectionClear PET bottles
300k t / yr
② SortingJudged by eye
composition unknown
③ Grind & washInto flakes
④ Reclaimed resinFood-grade:
just 3,400 t / yr
⑤ New bottlesContent estimated on paper
unprovable
OUR PREMISE
Quality without measurement is never approved —
and unapproved quality never improves.
SOLUTION

SEE → RECORD → PROVE

We do not replace the sorter. We mount a device above the running conveyor. All hardware is off-the-shelf — no equipment swap, no line stoppage.

STEP 1

SEE

Cameras and NIR sensors scan PET flakes on the belt, estimating clear/colored ratio, label residue, and contamination by other plastics (PP·PE·PVC) in real time — turning visual inspection into continuous data.

Sorters — screen out low-grade flow before it downgrades the batch
STEP 2

RECORD

Input lot → sorting → grinding → washing → shipment is bound to one batch ID, with composition, yield, process conditions and energy logged. Every value is reported with a confidence interval.

Sorters — negotiate prices with composition records in hand
STEP 3

PROVE

Batch records convert automatically into Korea's usage reports, EU data carriers (QR), and California filings. A QR scan traces which batch a bottle's recycled content came from.

Brands — compliance proven by measurement, not paperwork

AI is used only for detection; regulatory figures are generated by deterministic rules. The device retrofits onto the existing line — the only workflow change is scanning a batch tag.

WHY NOW

Deadlines already set for our customers

Not a market trend — statutory deadlines. Records cannot be created retroactively; they must start accumulating now.

2024.07
EU

Tethered caps mandated — the mixed-material problem remains

2026.01
Korea

10% recycled content mandatory for clear PET bottles

2026.08
EU

PPWR fully applies

2028.08
EU

Machine-readable content labels (data carriers) on every package — paperwork will not pass

2030.01
KR·EU·US

Korea 30% · EU food-contact PET 30% · California 50%

BUSINESS MODEL

What the market requires

We start at sorting plants. The fees are small, but the data is created only there — and that data underwrites every brand contract.

Sorters & reclaimers

Detection unit + batch ledger — monthly subscription per line. Preventing downgrades lifts per-tonne prices; estimated benefit ≈ 3× the fee.

Beverage brands & fillers

Recycled-content verification reports — annual contract. Missing the mandate means sales restrictions and fines; paperwork alone cannot satisfy the EU.

EU & North America exporters

QR & API integration — annual license. From August 2028 the EU requires machine-readable content data; without it, no market access.

EDGE

One technology from measurement to proof

Sorters and analytics AI stop at "measuring"; DPP and mass-balance schemes only "prove" — from paperwork. Mass balance is plant-level arithmetic, and cannot answer the EU's 2028 package-level requirement.

CapabilitySorters
(TOMRA etc.)
Flow-analytics AI
(Greyparrot etc.)
DPP · mass balance
(Circularise · ISCC)
Flake Ledger
Real-time composition measurement on the belt×
Batch-level composition & yield records××
Values reported with confidence intervals×××
Auto-generated KR reports & EU data carriers××
Retrofit onto existing sorting lines×
Both sorters (upstream) and brands (downstream) as customers×××

The moat is not an algorithm — it is devices installed across sorting plants and the batch records they accumulate. Records cannot be back-dated.

CLIMATE IMPACT

Emission cuts proven by measurement

Per tonne

1.70 tCO₂e

Saved when 1 t of rPET replaces virgin PET (2.15 → 0.45 kgCO₂e/kg, ISO 14044)

Across 10 sites

22,500 tCO₂e / yr

Assumes food-grade conversion improving 40%→55% per site · to be replaced by field measurements

TEAM

Built by a computer-vision researcher

CEO · Wonjin Cho

B.S. in Computer Science, Georgia Tech.
Ph.D. candidate, Seoul National University AI Graduate School — Computer Vision.

He builds the real-time composition-detection core himself; polymer and recycling-process expertise is covered by advisors (a polymer professor and a reclaimer plant process lead).

Proven track record

2026.09Paper accepted & presented at ECCV 2026 (Sweden), a top-3 computer-vision conference
2026.02Innovation Award, OKTA Global AI Startup Pitch
2024.11Silver Prize, SNU AI Graduate School Startup Competition