# A Novel Improved Whale Optimization Algorithm-Based Multi-Scale Fusion Attention Enhanced SwinIR Model for Super-Resolution and Recognition of Text Images on Electrophoretic Displays

## TL;DR

This paper introduces a new AI model to enhance text clarity and readability on e-readers by improving image resolution and recognition.

## Contribution

The novel IWOA-MFA-SwinIR model combines an improved whale optimization algorithm with multi-scale attention for better text image restoration on EPDs.

## Key findings

- The model achieved a PSNR of 24.406, SSIM of 0.8837, and CRA of 89.81% in ablation studies.
- It outperformed other models by 1% in PSNR, 0.8% in SSIM, and 8% in CRA in comparative evaluations.
- The IWOA algorithm effectively optimized hyperparameters without manual calibration.

## Abstract

Electrophoretic Displays (EPDs) are widely adopted in e-readers and portable devices due to their ultra-low power consumption and eye-friendly reflective characteristics. However, inherent hardware limitations, such as low resolution, slow response speed, and display degradation, frequently result in blurred strokes and degraded text readability. While traditional driving waveform optimizations can mitigate these issues, they are device-dependent and require extensive manual calibration. To address these challenges, this paper proposes an Improved Whale Optimization Algorithm-based Multi-scale Fusion Attention-enhanced SwinIR (IWOA-MFA-SwinIR) model for super-resolution and recognition of text images on EPDs. Structurally, the model incorporates a multi-scale fused attention (MFA) module that synergistically integrates channel, spatial, and gated attention mechanisms to precisely capture high-frequency text details while suppressing background noise within the SwinIR architecture. Furthermore, to enhance model robustness and eliminate manual tuning, an Improved Whale Optimization Algorithm (IWOA) is employed to adaptively optimize critical hyperparameters, including embedding dimension (d), attention head count (h), learning rate (lr), and dimensionality reduction coefficient (r). Experiments conducted on the TextZoom and EPD datasets demonstrate that the proposed model achieves state-of-the-art performance. In the ablation study, it attains a Peak Signal-to-Noise Ratio (PSNR) of 24.406, a Structural Similarity Index (SSIM) of 0.8837, and a Character Recognition Accuracy (CRA) of 89.81%. In the comparative evaluation, the proposed model consistently outperforms the second-best comparison model across three difficulty levels, yielding approximately a 1% improvement in PSNR, a 0.8% improvement in SSIM, and an 8% improvement in CRA. This confirms the proposed model’s superiority over mainstream comparative models in restoring text fidelity and improving recognition rates.