Development of a Novel Quantum Pre-processing Filter to Improve Image Classification Accuracy of Neural Network Models
This addresses image classification accuracy for neural network users, but it is incremental as it shows mixed results and requires further research for broader applicability.
The paper tackled the problem of improving image classification accuracy for neural networks by proposing a quantum pre-processing filter, resulting in accuracy increases from 92.5% to 95.4% on MNIST and from 68.9% to 75.9% on EMNIST, but it degraded performance on the GTSRB dataset.
This paper proposes a novel quantum pre-processing filter (QPF) to improve the image classification accuracy of neural network (NN) models. A simple four qubit quantum circuit that uses Y rotation gates for encoding and two controlled NOT gates for creating correlation among the qubits is applied as a feature extraction filter prior to passing data into the fully connected NN architecture. By applying the QPF approach, the results show that the image classification accuracy based on the MNIST (handwritten 10 digits) and the EMNIST (handwritten 47 class digits and letters) datasets can be improved, from 92.5% to 95.4% and from 68.9% to 75.9%, respectively. These improvements were obtained without introducing extra model parameters or optimizations in the machine learning process. However, tests performed on the developed QPF approach against a relatively complex GTSRB dataset with 43 distinct class real-life traffic sign images showed a degradation in the classification accuracy. Considering this result, further research into the understanding and the design of a more suitable quantum circuit approach for image classification neural networks could be explored utilizing the baseline method proposed in this paper.