A Statistical Method for Object Counting

TL;DR

This paper introduces a statistical image analysis method for counting similar, round objects that does not require object identification, demonstrating effectiveness across various object types with good accuracy and robustness.

Contribution

The paper presents a novel statistical approach for object counting that handles touching and overlapping objects without prior object detection or configuration.

Findings

Effective on images of bone cells, oranges, and pills

Handles touching and overlapping objects well

Works across different object types without prior setup

Abstract

In this paper we present a new object counting method that is intended for counting similarly sized and mostly round objects. Unlike many other algorithms of the same purpose, the proposed method does not rely on identifying every object, it uses statistical data obtained from the image instead. The method is evaluated on images with human bone cells, oranges and pills achieving good accuracy. Its strengths are ability to deal with touching and partly overlapping objects, ability to work with different kinds of objects without prior configuration and good performance.