Method of and system for classifying objects using histogram segment features of multi-energy computed tomography images

US7474786B2 · kind B2 · utility

Assignee

• Analogic Corporation · US

Inventors

• Ram Naidu · Newton, US
• Zhengrong Ying · Wakefield, US
• Sergey Simanovsky · Brookline, US
• Matthew Hirsch · Stoneham, US
• Carl R. Crawford · Brookline, US

Key dates

• Filing date: Aug 4, 2005
• Grant date: Jan 6, 2009
• Expiry date: Jul 10, 2027

Classification

• Technology area (CPC G): Physics
• CPC primary: G01V5/20
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

A method of and a system for identifying objects using histogram segment features from multi-energy CT images are provided. The multi-energy CT images include a CT image, which approximates density measurements of scanned objects, and a Z image, which approximates effective atomic number measurements of scanned objects. The method comprises: computing a density histogram for each potential threat object; smoothing the density histogram using a low-pass filter; identifying peaks in the smoothed density histogram; assigning a segment to each peak; computing histogram segment features for each segment; classifying each potential threat object into a threat or a non-threat using computed features.