Real-time detection of elliptic shapes for automated object recognition and object tracking

Abstract

The detection of varying 2D shapes is a recurrent task for Computer Vision applications, and camera based object recognition has become a standard procedure. Due to the discrete nature of digital images and aliasing effects, shape recognition can be complicated. There are many existing algorithms that discuss the identification of circles and ellipses, but they are very often limited in flexibility or speed or require high quality input data. Our work considers the application of shape recognition for processes in industrial environments and, especially the automatization requires reliable and fast algorithms at the same time. We take a very practical look at the automated shape recognition for common industrial tasks and present a very fast novel approach for the detection of deformed shapes which are in the broadest sense elliptic. Furthermore, we consider the automated recognition of bacteria colonies and coded markers for both 3D object tracking and an automated camera calibration procedure

Multistage classification for bacterial colonies recognition on solid agar images

“…In [8] different colony segmentation methods have been compared. In [9] complex shape recognition has been addressed for colony detection. In [7] a neural network approach to estimate the number of colonies included in confluent growth segments is proposed.…”

A hybrid method for ellipse detection in industrial images

“…If s only contains arcs which belong to a common ellipse, then c s must be the inner point of each arc of s. Arcs of s will not belong to a common ellipse if c s is not the inner point of any arc of s. For example, in Fig. 13 (g), e 1 , e 2 , e 3 , and e 4 can be clustered to a set because the set center P 1 is the inner point of e 1 , e 2 , e 3 , and e 4 while e 1 , e 2 , e 3 , e 4 , and e 5 cannot be grouped together since P 2 is not the inner point of e 5 .…”

“…(g) e 1 , e 2 , e 3 , and e 4 can be clustered to a set but e 1 , e 2 , e 3 , e 4 , and e 5 cannot be clustered. The detailed procedures about how to cluster candidate elliptic arcs into groups are shown in Algorithm 3 .…”

“…For instance, ellipse detection can be used in surface inspection problems, camera calibration [3] , object segmentation [4] , eye gaze estimation [5] , road sign detection and classification [6] , and so on. Thus, it is particularly important to detect ellipse robustly and reliably from real images.…”

Elliptical Object Detection by a Modified RANSAC with Sampling Constraint from Boundary Curves' Clustering

“…To facilitate efficient computation, methods such as "Uprite" [21] and "arc finding" [13], [19], [26] have been proposed. Nevertheless, both methods have their individual defects.…”