Search

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. [ABSTRACT FROM AUTHOR]

Scene-based image semantic extraction and its precise sentiment expression significantly enhance artistic design. To address the incongruity between image features and sentiment features caused by non-bilinear pooling, this study introduces a generative adversarial network (GAN) model that integrates visual relationships with sentiment semantics. The GAN-based regularizer is utilized during training to incorporate target information derived from the contextual information into the process. This regularization mechanism imposes stronger penalties for inaccuracies in subject-object type predictions and integrates a sentiment corpus to generate more human-like descriptive statements. The capsule network is employed to reconstruct sentences and predict probabilities in the discriminator. To preserve crucial focal points in feature extraction, the Convolutional Block Attention Mechanism (CBAM) is introduced. Furthermore, two bidirectional long short-term memory (LSTM) modules are used to model both target and relational contexts, thereby refining target labels and inter-target relationships. Experimental results highlight the model's superiority over comparative models in terms of accuracy, BiLingual Evaluation Understudy (BLEU) score, and text preservation rate. The proposed model achieves an accuracy of 95.40% and the highest BLEU score of 16.79, effectively capturing both the label content and the emotional nuances within the image. [ABSTRACT FROM AUTHOR]

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.

Scene-based image semantic extraction and its precise sentiment expression significantly enhance artistic design. To address the incongruity between image features and sentiment features caused by non-bilinear pooling, this study introduces a generative adversarial network (GAN) model that integrates visual relationships with sentiment semantics. The GAN-based regularizer is utilized during training to incorporate target information derived from the contextual information into the process. This regularization mechanism imposes stronger penalties for inaccuracies in subject-object type predictions and integrates a sentiment corpus to generate more human-like descriptive statements. The capsule network is employed to reconstruct sentences and predict probabilities in the discriminator. To preserve crucial focal points in feature extraction, the Convolutional Block Attention Mechanism (CBAM) is introduced. Furthermore, two bidirectional long short-term memory (LSTM) modules are used to model both target and relational contexts, thereby refining target labels and inter-target relationships. Experimental results highlight the model’s superiority over comparative models in terms of accuracy, BiLingual Evaluation Understudy (BLEU) score, and text preservation rate. The proposed model achieves an accuracy of 95.40% and the highest BLEU score of 16.79, effectively capturing both the label content and the emotional nuances within the image.

The rapid advancement of industrialization has sparked the emergence of diverse art and design theories. As a trailblazer in the realm of industrial art and design theory, visual communication has transcended the boundaries of merely arranging and combining individual elements. Embracing the potential of artificial intelligence technology, the extraction of multidimensional abstract data and the acceleration of the art design process have gained considerable momentum. This study delves into the abstract emotional facets within the methodology of visual communication art design. Initially, convolutional neural networks (CNN) are employed to extract expressive features from the poster's visual information. Subsequently, these features are utilized to cluster emotional elements using a variational autoencoder (VAE). Through this clustering process, the poster images are categorized into positive, negative, and neutral classes. Experimental results demonstrate a silhouette coefficient surpassing 0.7, while the system framework exhibits clustering accuracy and efficiency exceeding 80% in single sentiment class testing. These outcomes underscore the efficacy of the proposed CNN-VAE-based clustering framework in analyzing the dynamic content of design elements. This framework presents a novel approach for future art design within the realm of visual communication. [ABSTRACT FROM AUTHOR]

The rapid advancement of industrialization has sparked the emergence of diverse art and design theories. As a trailblazer in the realm of industrial art and design theory, visual communication has transcended the boundaries of merely arranging and combining individual elements. Embracing the potential of artificial intelligence technology, the extraction of multidimensional abstract data and the acceleration of the art design process have gained considerable momentum. This study delves into the abstract emotional facets within the methodology of visual communication art design. Initially, convolutional neural networks (CNN) are employed to extract expressive features from the poster's visual information. Subsequently, these features are utilized to cluster emotional elements using a variational autoencoder (VAE). Through this clustering process, the poster images are categorized into positive, negative, and neutral classes. Experimental results demonstrate a silhouette coefficient surpassing 0.7, while the system framework exhibits clustering accuracy and efficiency exceeding 80% in single sentiment class testing. These outcomes underscore the efficacy of the proposed CNN-VAE-based clustering framework in analyzing the dynamic content of design elements. This framework presents a novel approach for future art design within the realm of visual communication., Competing Interests: The author declares that there are no competing interests., (©2023 Rui.)