Monitoring of illicit pill distribution networks using an image collection exploration framework.

This paper proposes a novel approach for the analysis of illicit tablets based on their visual characteristics. In particular, the paper concentrates on the problem of ecstasy pill seizure profiling and monitoring. The presented method extracts the visual information from pill images and builds a representation of it, i.e. it builds a pill profile based on the pill visual appearance. Different visual features are used to build different image similarity measures, which are the basis for a pill monitoring strategy based on both discriminative and clustering models. The discriminative model permits to infer whether two pills come from the same seizure, while the clustering models groups of pills that share similar visual characteristics. The resulting clustering structure allows to perform a visual identification of the relationships between different seizures. The proposed approach was evaluated using a data set of 621 Ecstasy pill pictures. The results demonstrate that this is a feasible and cost effective method for performing pill profiling and monitoring.

[1]  Linda G. Shapiro,et al.  A Flexible Image Database System for Content-Based Retrieval , 1999, Comput. Vis. Image Underst..

[2]  Hiroyuki Inoue,et al.  Identification of impurities and the statistical classification of methamphetamine using headspace solid phase microextraction and gas chromatography-mass spectrometry. , 2006, Forensic science international.

[3]  Laurence Dujourdy,et al.  Development of a harmonised method for the profiling of amphetamines VI: Evaluation of methods for comparison of amphetamine. , 2007, Forensic science international.

[4]  Ian Witten,et al.  Data Mining , 2000 .

[5]  Yonghoon Park,et al.  Cross-examination of liquid-liquid extraction (LLE) and solid-phase microextraction (SPME) methods for impurity profiling of methamphetamine. , 2012, Forensic science international.

[6]  Kate Smith-Miles,et al.  A clustering algorithm based on an estimated distribution model , 2005, Int. J. Bus. Intell. Data Min..

[7]  N. Daéid,et al.  Emerging use of isotope ratio mass spectrometry as a tool for discrimination of 3,4-methylenedioxymethamphetamine by synthetic route. , 2008, Analytical chemistry.

[8]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[9]  Fabio A. González,et al.  Visual pattern mining in histology image collections using bag of features , 2011, Artif. Intell. Medicine.

[10]  M M van Deursen,et al.  Organic impurity profiling of 3,4-methylenedioxymethamphetamine (MDMA) tablets seized in The Netherlands. , 2006, Science & justice : journal of the Forensic Science Society.

[11]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[12]  K. Kuwayama,et al.  Seized methamphetamine samples with unique profiles of stable nitrogen isotopic composition documented by stable isotope ratio mass spectrometry , 2010, Forensic Toxicology.

[13]  Hiroyuki Inoue,et al.  Comparison and classification of methamphetamine seized in Japan and Thailand using gas chromatography with liquid-liquid extraction and solid-phase microextraction. , 2008, Forensic science international.

[14]  Laura Aalberg,et al.  Development of a harmonized method for the profiling of amphetamines. II. Stability of impurities in organic solvents. , 2005, Forensic science international.

[15]  Pierre Margot,et al.  Headspace solid-phase microextraction (HS-SPME) and liquid-liquid extraction (LLE): comparison of the performance in classification of ecstasy tablets. Part 2. , 2008, Forensic science international.

[16]  Pierre Margot,et al.  Optimization of HS-SPME/GC-MS analysis and its use in the profiling of illicit ecstasy tablets (Part 1). , 2009, Forensic science international.

[17]  Hiroyuki Inoue,et al.  Characterization and Profiling of Methamphetamine Seizures , 2008 .

[18]  Laura Aalberg,et al.  Drug intelligence based on MDMA tablets data: 2. Physical characteristics profiling. , 2008, Forensic science international.

[19]  Irvin Sobel,et al.  Neighborhood coding of binary images for fast contour following and general binary array processing , 1978 .

[20]  M Lopatka,et al.  Surface granularity as a discriminating feature of illicit tablets. , 2011, Forensic science international.

[21]  Laura Aalberg,et al.  Development of a harmonized method for the profiling of amphetamines. I. Synthesis of standards and compilation of analytical data. , 2005, Forensic science international.

[22]  Hans Burkhardt,et al.  Improvement of histogram-based image retrieval and classification , 2002, Object recognition supported by user interaction for service robots.

[23]  Anil K. Jain,et al.  Pill-ID: Matching and retrieval of drug pill images , 2012, Pattern Recognit. Lett..

[24]  Zeno Geradts,et al.  Content based information retrieval in forensic image databases. , 2002, Journal of forensic sciences.

[25]  Junchul Chun,et al.  Drug Image Retrieval by Shape and Color Similarity of the Medication , 2011, 2011 First ACIS/JNU International Conference on Computers, Networks, Systems and Industrial Engineering.

[26]  Francesca Odone,et al.  Histogram intersection kernel for image classification , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[27]  Michael D Cole,et al.  Development of a harmonised method for the profiling of amphetamines: IV. Optimisation of sample preparation. , 2007, Forensic science international.

[28]  Marti A. Hearst,et al.  Animated exploration of dynamic graphs with radial layout , 2001, IEEE Symposium on Information Visualization, 2001. INFOVIS 2001..

[29]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[30]  Niamh Nic Daeid,et al.  Organic impurities, stable isotopes, or both: A comparison of instrumental and pattern recognition techniques for the profiling of 3,4-methylenedioxymethamphetamine , 2011 .

[31]  Hermann Ney,et al.  Features for Image Retrieval: A Quantitative Comparison , 2004, DAGM-Symposium.

[32]  Laura Aalberg,et al.  Development of a harmonised method for the profiling of amphetamines V: Determination of the variability of the optimised method. , 2007, Forensic science international.

[33]  Elizabeth Sadler,et al.  Inclusive interface design for seniors: Image-browsing for a health information context , 2007 .