PowDew


PowDew aims to detect counterfeit powdered food products using only a commodity smartphone. We propose a novel method by utilizing smartphone to capture a droplet motion (i.e., spreading and penetration) for the authentication.

Abstract

The prevalence of counterfeit infant formulas worldwide poses serious threats to infant health and safety, a concern highlighted by the notorious Melamine Milk Scandal that affected hundreds of thousands of children. The primary challenge in detecting counterfeit formulas lies in their sophisticated adulteration and substitution techniques. Such detection is feasible only in laboratory settings, making it nearly impossible for average consumers to test the formula before feeding their infants. To address this problem, we propose PowDew, a novel and practical system for detecting counterfeit infant formula that utilizes only a commodity smartphone. PowDew operates by capturing and analyzing the interaction of a water droplet with the powdered formula, focusing on the droplet motion, namely its spreading and penetration. Our insight is that the droplet motions are governed by powder-specific properties such as wettability and porosity. PowDew analyzes the subtle differences in droplet motions and infers the formula’s authenticity. To demonstrate PowDew’s effectiveness, we implement PowDew and conduct comprehensive real-world experiments under varying conditions with different brands of powdered infant formula and adulterants. Our experiments result in a total of 12,000 minutes of video recordings of the droplet motions on various infant formulas, including authentic and altered. Our experiments demonstrate that PowDew yields an overall detection accuracy of up to 96.1%.

Demonstration

PowDew can be utilized by average users with commodity devices (e.g., tablets, smartwatches, and, smart TVs).

(1) User drops a water droplet on powder bed with user guidance.

(2) PowDew Application UI

(3) Smartphone captures droplet motion using its font-facing camera.

Core Idea: Checkerboard Projection


Capturing the droplet motion with a commodity smartphone camera poses several challenges.

(1) Restricted View with Single Camera



Since a commodity smartphone camera only provides a restricted two-dimensional view, it is unable to fully capture the droplet motion in three-dimensions.

(2) Subtle Changes in Droplet Motion

A commodity smartphone camera may not capture subtle changes in droplet motion for classifying authentic and counterfeit products. 

Our Solution: Checkerboard Projection!

To tackle these challenges, we propose a novel method: projecting a checkerboard pattern onto the droplet surface using a smartphone display.

(1) Restricted View with Single Camera

With our checkerboard projection, we can capture three-dimensional surface morphology with two-dimensional view.

(2) Subtle Changes in Droplet Motion

Authentic

Counterfeit

A notable difference becomes apparent when using the checkerboard projection.


System Overview of PowDew


To utilize the checkerboard projection, we implement PowDew with the following system design.

Publications