hybrid-quantum-classical-LPR

⚡ Quantum-Enhanced Deep Learning for Robust Night-Time License Plate Recognition

<div align="center"> <img src="images/image1.png" alt="Architecture Pipeline" width="800"/> <br> <em>Complete architectural pipeline of HybridLPRNet_8Q, illustrating the flow from night-time image input through Zero-DCE enhancement, CNN extraction, the 8-qubit VQC bottleneck, and final Bi-LSTM/CTC decoding.</em> </div> <br>

🔭 The Research Question

Most license plate recognition (LPR) systems fail after dark. This project asks: Can a quantum-enhanced neural network read license plates in night conditions more accurately than a purely classical system?

We run two systems head-to-head:

• HybridLPRNet_8Q: Zero-DCE + CNN + 8-Qubit Quantum Circuit + Bi-LSTM + CTC
• ClassicalLPRNet: Zero-DCE + CNN (larger) + Bi-LSTM + CTC

<div align="center"> <img src="images/image5.png" alt="Night-Time Examples" width="800"/> <br> <em>Representative night-time ALPR examples showing original image, synthetic night corruption, Zero-DCE enhancement, and predictions from both models.</em> </div>

---

📊 Performance Comparison & Convergence

The quantum model achieves competitive performance utilizing a dynamic 256-dimensional Hilbert space, requiring fewer overall parameters compared to the classical baseline.

<div align="center"> <img src="images/image4.png" alt="Training Convergence" width="800"/> <br> <em>Comparative training convergence plots for the Quantum (HybridLPRNet_8Q) and Classical (ClassicalLPRNet) models showing Validation Loss, CER, and Plate Accuracy over 100 epochs.</em> </div>

---

🏗️ Architecture Deep-Dive

1. Low-Light Enhancement (Zero-DCE)

<div align="center"> <img src="images/image2.png" alt="Zero-DCE" width="800"/> <br> <em>Stage 1: Detailed view of the Zero-DCE (Deep Curve Estimation) light module, showing the 8-iteration curve refinement process for low-light enhancement.</em> </div>

2. Quantum Bottleneck (VQC)

<div align="center"> <img src="images/image3.png" alt="Quantum Circuit" width="800"/> <br> <em>Stage 4: Schematic of the 8-qubit Variational Quantum Circuit (VQC) featuring AngleEmbedding and two StronglyEntanglingLayers.</em> </div>

---

🔮 Quantum Interpretability

The 8-qubit register exhibits emergent specialization during training. Different qubits learn to react to specific visual features, such as numeral density or character boundaries.

<div align="center"> <img src="images/image6.png" alt="Pauli-Z Heatmaps" width="800"/> <br> <em>Pre-circuit and post-circuit qubit activation maps across temporal slices for a representative license plate.</em> </div> <div align="center"> <img src="images/image7.png" alt="Bloch-Sphere Trajectories" width="800"/> <br> <em>Bloch-sphere state trajectories for the 8 qubits, showing specialized rotational behavior.</em> </div>

---

💻 Reproduce the Research

All execution environments and training code are fully available in the notebooks/ directory.

Inference Example

import torch

# Load the Quantum Checkpoint
checkpoint = torch.load("quantum/latest.pth", map_location="cpu")

print(f"Loaded Epoch: {checkpoint.get('epoch', 'N/A')}")
print(f"Validation CER: {checkpoint.get('val_cer', 'N/A')}")

# Assuming HybridLPRNet_8Q is defined in your scope:
# model = HybridLPRNet_8Q()
# model.load_state_dict(checkpoint['model_state_dict'])
# model.eval()

---

👤 Author

Shanmukesh Bonala — VIT-AP University
Course: CSE4019 — Applications of AI (AoAI)
Semester: Winter 2025–26