# Quantum Kernel for Image Classification of Real World Manufacturing Defects

arXiv: https://arxiv.org/abs/2212.08693 · HTML: https://mlsanity.com/paper/2212.08693/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 16 Dec 2022.

## Builds on (most cited first, 4 of 4)

- [Supervised learning with quantum enhanced feature spaces](https://mlsanity.com/paper/1804.11326/) (2018)
- [A rigorous and robust quantum speed-up in supervised machine learning](https://mlsanity.com/paper/2010.02174/) (2020)
- [Synthetic weather radar using hybrid quantum-classical machine learning](https://mlsanity.com/paper/2111.15605/) (2021)
- [Quantum artificial vision for defect detection in manufacturing](https://mlsanity.com/paper/2208.04988/) (2022)

## Built on by (most cited first, 3 of 3)

- [Non-variational supervised quantum kernel methods: a review](https://mlsanity.com/paper/2604.07896/) (2026)
- [Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Features](https://mlsanity.com/paper/2605.06035/) (2026)
- [Inter-case Predictive Process Monitoring: A candidate for Quantum Machine Learning?](https://mlsanity.com/paper/2307.00080/) (2023)

## Abstract (arXiv)

The quantum kernel method results clearly outperformed a classical SVM when analyzing low-resolution images with minimal feature selection on the quantum simulator, with inconsistent results when run on an actual quantum processor. We chose to use an existing quantum kernel method for classification. We applied dynamic decoupling error mitigation using the Mitiq package to the Quantum SVM kernel method, which, to our knowledge, has never been done for quantum kernel methods for image classification. We applied the quantum kernel method to classify real world image data from a manufacturing facility using a superconducting quantum computer. The manufacturing images were used to determine if a product was defective or was produced correctly through the manufacturing process. We also tested the Mitiq dynamical decoupling (DD) methodology to understand effectiveness in decreasing noise-related errors. We also found that the way classical data was encoded onto qubits in quantum states affected our results. All three quantum processing unit (QPU) runs of our angle encoded circuit returned different results, with one run having better than classical results, one run having equivalent to classical results, and a run with worse than classical results. The more complex instantaneous quantum polynomial (IQP) encoding approach showed better precision than classical SVM results when run on a QPU but had a worse recall and F1-score. We found that DD error mitigation did not improve the results of IQP encoded circuits runs and did not have an impact on angle encoded circuits runs on the QPU. In summary, we found that the angle encoded circuit performed the best of the quantum kernel encoding methods on real quantum hardware. In future research projects using quantum kernels to classify images, we recommend exploring other error mitigation techniques than Mitiq DD.