Image-Based Concealed Material Detection Using Pixel Intensity Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to automatically and accurately detect concealed prohibited materials, such as explosives, in items at security checkpoints, particularly when they are hidden within objects using various techniques that alter their appearance in images.
Innovation Solution
A system and method using processor and memory circuitry to analyze pixel intensity data from images, comparing positive and negative samples to determine the presence of prohibited materials by generating probability maps based on pixel intensity distributions and patterns, without requiring extensive training data or machine learning networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image verification methods are used, then the system is simple to operate, but the detection accuracy of concealed prohibited materials is insufficient
Solution Approach 1:
The image is divided into multiple regions of interest (ROIs) corresponding to different item parts. Each ROI is independently analyzed by comparing its pixel intensity distribution against pre-stored positive and negative reference data. This segmentation allows the system to focus computational resources on specific areas, improving detection accuracy while managing system complexity through localized analysis rather than processing the entire image uniformly.
Solution Approach 2:
The system pre-stores positive reference data (from items known to contain prohibited materials) and negative reference data (from items known to be clear) in a database before actual detection occurs. During operation, acquired images are compared against these pre-prepared references using pixel intensity distribution analysis. This preliminary preparation of reference data enables rapid comparison and decision-making during security screening without requiring complex real-time learning.
2Productivity
If manual verification by operators is used, then false positives can be reduced, but the processing speed and productivity are limited
Solution Approach 1:
The system replaces manual operator verification with an automated computerized analysis system that processes images through pixel intensity distribution comparison. The automated system extracts pixel intensity data from acquired images, compares these distributions against pre-stored positive and negative reference data, and automatically determines whether prohibited materials are present. This substitution of mechanical human analysis with automated computational processing significantly increases processing speed while maintaining consistent detection accuracy through standardized comparison algorithms.
3Measurement precision
If extensive training data and machine learning networks are used, then detection accuracy improves, but the system complexity and data requirements increase significantly
Solution Approach 1:
The system extracts only the essential feature - pixel intensity distribution - from images for comparison purposes. Instead of using complex machine learning networks that require extensive training data, the system extracts pixel intensity values from regions of interest and directly compares these extracted features against pre-stored positive and negative reference distributions. This extraction of core features without requiring comprehensive training datasets reduces data requirements while maintaining effective detection capability through straightforward statistical comparison.
Data Source
AI summary
There are provided systems and methods comprising obtaining an image of at least a part of an item, obtaining data informative of a pixel intensity of the part of the item in the image, obtaining first data informative of a pixel intensity in an image of a part of a first item associated with a prohibited material, wherein the part of the first item meets a similarity criterion with the part of the item, obtaining second data informative of a pixel intensity in an image of a part of a second item which is not associated with a prohibited material, wherein the part of the second item meets the similarity criterion with the part of the item, and using the first data, the second data and the data to determine whether the part of the item is associated with a concealed prohibited material in the image.