Counting Machine Parts

TL;DR

This paper presents an enhanced counting method for machine washer parts using an extended FamNet model, demonstrating improved accuracy over traditional and existing deep learning approaches.

Contribution

The authors extend FamNet with an additional loss component and evaluate its effectiveness on counting machine parts, achieving a MAE of 1.96.

Findings

Our approach outperforms baseline methods in counting accuracy.

The extended FamNet achieves a MAE of 1.96 on the dataset.

Comparison with traditional and segmentation methods shows improved performance.

Abstract

Counting objects in an image is a task applicable across many domains. For instance, crowd counting, inventory counting, and cell counting have been the focus of recent research. The major challenges in estimating the count of objects include overlapping objects, object scale issues, occlusions, and varying lighting conditions. In this report, we explore the problem of counting machine washer parts. Our technique is an extension of FamNet with an additional loss component, trained on the given dataset. We compare to three baseline methods: a traditional image processing pipeline, instance segmentation, and density map estimation. We evaluate the performance of these algorithms by computing the Mean Absolute Error (MAE) and the Root Mean Squared Error (RMSE) between the true object counts and the model outputs. Our approach achieves a performance of 1.96 MAE.