Automated Narcotics Detection in Stomach via X-Ray Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current security systems at airports and secure facilities are inefficient in detecting illegal substances smuggled inside a person's stomach, as existing methods struggle with low contrast images and require manual effort, leading to potential missed detections and operator fatigue.

Innovation Solution

An automated detection system using X-ray scanner images, employing a sliding window method, saliency maps, and classifiers to differentiate drug-filled pouches within the stomach area, eliminating the need for manual analysis and improving precision and throughput.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual visual review by operator is used, then detection capability can be maintained, but operator fatigue and wrong decisions occur leading to reduced reliability

Engineering Contradiction:
Improvedetection reliabilityVSAvoidoperator fatigue
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system enables self-service detection through automated image processing algorithms that independently analyze X-ray images without human intervention. The automated detection system processes images through multiple stages including segmentation, feature extraction, and classification, eliminating operator fatigue while maintaining consistent detection reliability.

Inventive Principle:
Principle #25Self-service

2Productivity

If automated detection algorithm is used, then throughput is increased and operator fatigue is eliminated, but detection precision must be maintained without manual review

Engineering Contradiction:
Improvescanner throughputVSAvoiddetection precision
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The detection system segments the image processing task into distinct stages: initial image processing, stomach region segmentation, feature extraction, and classification. This segmentation allows each component to be optimized independently, maintaining high detection precision while enabling automated high-speed processing that increases throughput.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements feedback mechanisms where detection results are continuously refined through iterative processing. The automated algorithm adjusts detection parameters based on image characteristics and provides confidence scores, allowing the system to maintain high precision while operating at automated speeds without requiring manual review.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If shape-based object detection is used, then objects can be segmented and classified, but drugs inside stomach cavity cannot be detected due to low contrast

Engineering Contradiction:
Improveobject detection accuracyVSAvoidlow contrast detection
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system applies local quality enhancement by specifically targeting the stomach region for enhanced processing. After segmenting the stomach area from the rest of the image, the algorithm applies specialized feature extraction and analysis techniques tailored to low-contrast objects within this specific region, enabling detection of drugs that would be invisible in standard processing.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system changes processing parameters when analyzing the stomach region versus other areas. This includes adjusting contrast enhancement parameters, feature extraction thresholds, and classification criteria specifically for the low-contrast environment inside the stomach cavity, enabling reliable drug detection where standard parameters would fail.

Inventive Principle:
Principle #35Parameter changes

4Quantity of substance

If dual-energy method with atomic number analysis is used, then liquids in luggage can be detected, but drugs inside stomach cannot be detected

Engineering Contradiction:
Improveliquid detection capabilityVSAvoidstomach drug detection
Core Design Contradiction:
Quantity of substanceVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary segmentation of the stomach region before applying detailed analysis. By first isolating the stomach area and identifying its boundaries, the system prepares the data structure and processing parameters in advance, enabling subsequent detection of drugs within this pre-defined region without interference from other body parts or background noise.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system enhances detection efficiency and accuracy by automating the process, reducing operator fatigue and the need for multiple operators, while improving the detection of drugs hidden in the stomach area, thereby increasing security and reducing costs.

Implementation Method 1

security systems at airports, secure facilities and other public areas use microwave or X-ray scanners with penetrating or reflected radiation

Methodology Applied
Scientific EffectX-ray radiation penetration: X-Ray

Implementation Method 2

security systems at airports, secure facilities and other public areas use microwave or X-ray scanners with penetrating or reflected radiation

Methodology Applied
Scientific EffectMicrowave radiation penetration: Microwave Radiation

Data Source

PatentEP3323002B1Method and system for detection of contraband narcotics in human digestive tract
Publication Date: 2020.08.12 ADANI SYSTEMS INC
  • EP3323002B1 patent drawingFigure 1
  • EP3323002B1 patent drawingFigure 2
  • EP3323002B1 patent drawingFigure 3

AI summary

A method for automated detection of illegal substances smuggled inside internal cavities of a passenger, e.g., as capsules. The method provides for an automated detection of narcotics hidden in a passenger's stomach area using pictures produced by an X-ray scanner. According to an exemplary embodiment, throughput of the scanner is increased by an automated detection algorithm, which takes less time than visual analysis by an operator. The operator is only involved in cases when narcotics are detected. The automated detection method has a consistent precision, because the effects of tiredness of the operator are eliminated. Efficiency and costs of the process are improved, since fewer qualified operators can service several scanners.