Presentation on theme: "Development of an Automated Coin Grader A Progress Report Richard A. Bassett Ping Gallivan Xiang Gao Eric Heinen Akarsh Sakalaspur MASPLAS - April 19,"— Presentation transcript:
Development of an Automated Coin Grader A Progress Report Richard A. Bassett Ping Gallivan Xiang Gao Eric Heinen Akarsh Sakalaspur MASPLAS - April 19, 2002
Long Term Goal of Project Develop a system that will be used to grade, appraise and authenticate valuable collectibles items such as rare coins providing consistent and repeatable results.
What is a rare coin? A coin is considered rare or valuable when it meets a number of the following criteria: Limited # struck (or minted) Small estimated surviving population Desirable varieties or patterns Market attraction (supply vs demand) Sometimes age is a factor
The Need for an Automated Coin Grader Rare coins are presently graded by human hand and eye inspection that often produces varied, inconsistent and sometimes dubious results. A difference of a single grade in rare coins can often mean thousands of dollars in the value of the asset. Grading judgment is suspect with subjectivity and the great financial incentives entrenched in the process. Counterfeit rare collectibles abound Great diversity exists in denominations of coinage The rare coin market is dynamic and with significant changes occurring every week or so
Example of a Rarity 1909-S VDB Cent Values & Grades Almost Good - $325 Good - $430 Fine - $590 Extra Fine - $700 MS-60 - $875 MS-63 - $975 MS-65 - $1250 Source: PCGS – Collectors Universe Apr. 2002
Architectural Design of Present System DB Scanner Image Processor Browser System Scans Extracts features Displays Grades
Step #1 - Scan the coin on flatbed scanner Obtain a GIF Image
Step #2a – Image Processing Measure Histogram Obtain statistical data on the scanned pixels in the image in terms of the Hue, Saturation & Brightness vectors
Step #2b – Image Processing Edge Detection Edge Detection allows us to look at a coin in a 3D view and pickup additional features.
Distance Matrix The statistical data collected in step 2 allows us to determine which coins are similar to others in our database in terms of known grade.
Step # 3 Grade Confirmation
Step # 4 Browser Interface
Future Work Expand image processing to include advanced feature recognition beyond HSB and Edge Detection. Increase the database to include a larger sample set and other denominations. Design an intuitive user interface for scanning and grading. Move closer towards automated grading Secure funding to cover the costs of equipment & software required