Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Images

TL;DR

This paper presents a tailored elliptical object detection method using an adapted Faster R-CNN for identifying knots in lumber images, significantly improving detection accuracy over general detectors and contributing a new dataset.

Contribution

The authors adapt and extend the Gaussian Proposal Network for elliptical object detection, specifically for knots in lumber, and provide a new open-source dataset and image correction algorithm.

Findings

Knots detected with 73.05% IoU, outperforming general detectors at 63.63%.

Proposed method improves elliptical object localization accuracy.

Contributes the first open-source dataset of labeled elliptical knots.

Abstract

While general object detection has seen tremendous progress, localization of elliptical objects has received little attention in the literature. Our motivating application is the detection of knots in sawn timber images, which is an important problem since the number and types of knots are visual characteristics that adversely affect the quality of sawn timber. We demonstrate how models can be tailored to the elliptical shape and thereby improve on general purpose detectors; more generally, elliptical defects are common in industrial production, such as enclosed air bubbles when casting glass or plastic. In this paper, we adapt the Faster R-CNN with its Region Proposal Network (RPN) to model elliptical objects with a Gaussian function, and extend the existing Gaussian Proposal Network (GPN) architecture by adding the region-of-interest pooling and regression branches, as well as using the Wasserstein distance as the loss function to predict the precise locations of elliptical objects. Our proposed method has promising results on the lumber knot dataset: knots are detected with an average intersection over union of 73.05%, compared to 63.63% for general purpose detectors. Specific to the lumber application, we also propose an algorithm to correct any misalignment in the raw timber images during scanning, and contribute the first open-source lumber knot dataset by labeling the elliptical knots in the preprocessed images.