FUFurkan Ulger

Furkan Ulger

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Furkan Ulger has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Solder Joint Inspection on Printed Circuit Boards: A Survey and a Dataset

    by Furkan Ulger, Seniha Esen Yuksel, Atila Yilmaz, Dincer Gokcen

    Surface Mount Technology (SMT) is a procedure for mounting electronic components to the surface of the printed circuit boards (PCB). Although the SMT procedure is more reliable than the conventional through-hole mounting, many errors may occur in SMT lines. In this paper, we surveyed methods presented for the optical inspection of solder joints on PCBs. The methods are grouped by problem-solving approach: reference-based, machine learning/computer vision, deep learning, and 3D reconstruction. We compare and discuss these approaches according to their advantages and disadvantages, with a focus on the more recent deep learning and 3D reconstruction techniques, and list the public datasets for solder joints inspection. Since defective samples rarely occur in the SMT manufacturing lines, public datasets have few defective samples that are essential for the inspection task. To fill this gap, we publish a public dataset with both normal and different types of SMT errors. Our dataset can be used as a benchmark to compare different algorithms. The dataset is available at https://github.com/furkanulger/solder-joint-dataset.


  • Fine-Grained Classification of Solder Joints With α-Skew Jensen–Shannon Divergence

    by Furkan Ulger, Seniha Esen Yuksel, Atila Yilmaz, Dincer Gokcen

    Solder joint inspection (SJI) is a critical process in the production of printed circuit boards (PCB). Detection of solder errors during SJI is quite challenging as the solder joints have very small sizes and can take various shapes. In this study, we first show that solders have low feature diversity, and that the SJI can be carried out as a fine-grained image classification task which focuses on hard-to-distinguish object classes. To improve the fine-grained classification accuracy, penalizing confident model predictions by maximizing entropy was found useful in the literature. Inline with this information, we propose using the α-skew Jensen-Shannon divergence (α-JS) for penalizing the confidence in model predictions. We compare the α-JS regularization with both existing entropy-regularization based methods and the methods based on attention mechanism, segmentation techniques, transformer models, and specific loss functions for fine-grained image classification tasks. We show that the proposed approach achieves the highest F1-score and competitive accuracy for different models in the fine-grained solder joint classification task. Finally, we visualize the activation maps and show that with entropy-regularization, more precise class-discriminative regions are localized, which are also more resilient to noise. The code is available at https://github.com/furkanulger/SJI-entropy-reg.


  • Anomaly Detection for Solder Joints Using β-VAE

    by Furkan Ulger, Seniha Esen Yuksel, Atila Yilmaz

    In the assembly process of printed circuit boards (PCBs), most of the errors are caused by solder joints in surface mount devices (SMDs). In the literature, traditional feature extraction-based methods require designing hand-crafted features and rely on the tiered red green blue (RGB) illumination to detect solder joint errors, whereas the supervised convolutional neural network (CNN)-based approaches require a lot of labeled abnormal samples (defective solder joints) to achieve high accuracy. To solve the optical inspection problem in unrestricted environments with no special lighting and without the existence of error-free reference boards, we propose a new beta-variational autoencoder (beta-VAE) architecture for anomaly detection that can work on both integrated circuit (IC) and non-IC components. We show that the proposed model learns disentangled representation of data, leading to more independent features and improved latent space representations. We compare the activation and gradient-based representations that are used to characterize anomalies and observe the effect of different beta parameters on accuracy and untwining the feature representations in beta-VAE. Finally, we show that anomalies on solder joints can be detected with high accuracy via a model trained directly on normal samples without designated hardware or feature engineering.