Search Results for author:
Found 10 papers, 2 papers with code
Cross-domain Transfer of defect features in technical domains based on partial target data
In particular, it is shown that the domain generalization capabilities and classification results are improved by the proposed architecture, allowing for larger domain shifts between source and target domains.
Discriminative Feature Learning through Feature Distance Loss
The key finding is that by forcing the models to concentrate on different features, the classification accuracy is increased.
Text Detection on Technical Drawings for the Digitization of Brown-field Processes
This paper combines a domain knowledge-based generator to generate realistic technical drawings with a state-of-the-art object detection model to solve the issue of detecting text on technical drawings.
Analysis of the Visually Detectable Wear Progress on Ball Screws
Using images from a camera system for ball screw drives, this paper elaborates on the visual analysis of pitting itself.
Intelligent Vision Based Wear Forecasting on Surfaces of Machine Tool Elements
This paper addresses the ability to enable machines to automatically detect failures on machine tool components as well as estimating the severity of the failures, which is a critical step towards autonomous production machines.
Industrial Machine Tool Component Surface Defect Dataset
Using machine learning (ML) techniques in general and deep learning techniques in specific needs a certain amount of data often not available in large quantities in technical domains.
Siamese Basis Function Networks for Data-efficient Defect Classification in Technical Domains
Training deep learning models in technical domains is often accompanied by the challenge that although the task is clear, insufficient data for training is available.
A Stitching Algorithm for Automated Surface Inspection of Rotationally Symmetric Components
This paper provides a novel approach to stitching surface images of rotationally symmetric parts.
GAN based ball screw drive picture database enlargement for failure classification
The main goal of this paper is to generate synthetic images based on the generative adversarial network (GAN) to enlarge the image dataset of ball screw surface failures.
Context-based Image Segment Labeling (CBISL)
Based on published gated PixelCNNs, we demonstrate a new approach referred to as quadro-directional PixelCNN to recover missing objects and return probable positions for objects based on the context.
