Outlier Detection in Object Counting based on Hue and Distance Transform using Median Absolute Deviation (MAD)

Object counting based on image data has been developed in many research. It is fast, automatic and noncontact solution that is applied in health, microbiology, object tracking, robotics and industry. During the counting, object that differs from majority object might be presented in a frame. This outlier object should be detected and not be counted. This study present an algorithm to detect outliers in object counting based on color and shape information. The color was based on Hue whilst the shape was based on distance transform. Both features were chosen as it is invariant to position and rotation in plane. Outlier detection utilized Median Absolute Deviation (MAD) on Histograms of both features. The testing shows promising result (accuracy of 94.3%) in 35 images with simple background.

[1]  Khairuddin Omar,et al.  Automatic Detection and Quantification of WBCs and RBCs Using Iterative Structured Circle Detection Algorithm , 2014, Comput. Math. Methods Medicine.

[2]  Denis Cousineau,et al.  Outliers detection and treatment: a review , 2010 .

[3]  Jeff Miller,et al.  Short Report: Reaction Time Analysis with Outlier Exclusion: Bias Varies with Sample Size , 1991, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[4]  Lei Meng,et al.  A people counting system based on head-shoulder detection and tracking in surveillance video , 2010, 2010 International Conference On Computer Design and Applications.

[5]  K. Thilagavathi,et al.  Automatic red blood cell counting using hough transform , 2013, 2013 IEEE CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES.

[6]  M. Hubert,et al.  Multivariate outlier detection and Robustness , 2005 .

[7]  Christophe Ley,et al.  Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median , 2013 .

[8]  Sri Arttini Dwi Prasetyowati,et al.  Utilization of Digital Image Processing In Process of Quality Control of The Primary Packaging of Drug Using Color Normalization Method , 2017 .

[9]  Bin Li,et al.  A people counting method based on head detection and tracking , 2014, 2014 International Conference on Smart Computing.

[10]  Mahdi Bahaghighat,et al.  A Machine Learning-Based Approach for Counting Blister Cards Within Drug Packages , 2019, IEEE Access.

[11]  Mohd Azhar Abdul Razak,et al.  Automated Red Blood Cells Counting in Peripheral Blood Smear Image Using Circular Hough Transform , 2013, 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation.

[12]  Mehmet Karaköse,et al.  An Image Processing based Object Counting Approach for Machine Vision Application , 2018, arXiv.org.

[13]  K. S. Venkatesh,et al.  People Counting in High Density Crowds from Still Images , 2015, ArXiv.