Xu Ming, Cui Jinwei, Ma Xiaoyu, Zou Zhiyi, Xin Zhisheng, Bilal Muhammad
School of Architecture and Art, Central South University, Changsha, China.
Department of Pharmaceutical Outcomes and Policy, University of Florida, Gainesville, FL, United States of America.
PeerJ Comput Sci. 2024 Nov 13;10:e2417. doi: 10.7717/peerj-cs.2417. eCollection 2024.
Graphic design, as a product of the burgeoning new media era, has seen its users' requirements for images continuously evolve. However, external factors such as light and noise often cause graphic design images to become distorted during acquisition. To enhance the definition of these images, this paper introduces a novel image enhancement model based on visual features. Initially, a histogram equalization (HE) algorithm is applied to enhance the graphic design images. Subsequently, image feature extraction is performed using a dual-flow network comprising convolutional neural network (CNN) and Transformer architectures. The CNN employs a residual dense block (RDB) to embed spatial local structure information with varying receptive fields. An improved attention mechanism module, attention feature fusion (AFF), is then introduced to integrate the image features extracted from the dual-flow network. Finally, through image perception quality guided adversarial learning, the model adjusts the initial enhanced image's color and recovers more details. Experimental results demonstrate that the proposed algorithm model achieves enhancement effects exceeding 90% on two large image datasets, which represents a 5%-10% improvement over other models. Furthermore, the algorithm exhibits superior performance in terms of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) image quality evaluation metrics. Our findings indicate that the fusion model significantly enhances image quality, thereby advancing the field of graphic design and showcasing its potential in cultural and creative product design.
平面设计作为新兴新媒体时代的产物，其用户对图像的要求不断演变。然而，光线和噪声等外部因素常常导致平面设计图像在采集过程中失真。为了提高这些图像的清晰度，本文介绍了一种基于视觉特征的新型图像增强模型。首先，应用直方图均衡化（HE）算法来增强平面设计图像。随后，使用由卷积神经网络（CNN）和Transformer架构组成的双流网络进行图像特征提取。CNN采用残差密集块（RDB）来嵌入具有不同感受野的空间局部结构信息。然后引入一种改进的注意力机制模块，即注意力特征融合（AFF），以整合从双流网络提取的图像特征。最后，通过图像感知质量引导的对抗学习，模型调整初始增强图像的颜色并恢复更多细节。实验结果表明，所提出的算法模型在两个大型图像数据集上实现了超过90%的增强效果，比其他模型提高了5%-10%。此外，该算法在峰值信噪比（PSNR）和结构相似性指数测量（SSIM）图像质量评估指标方面表现出卓越的性能。我们的研究结果表明，融合模型显著提高了图像质量，从而推动了平面设计领域的发展，并展示了其在文化创意产品设计中的潜力。
