检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:刘红娇 LIU Hongjiao(College of Mathematics,Boda College of Jilin Normal University,Siping,Jilin 136000,China)
机构地区:[1]吉林师范大学博达学院数学学院,吉林四平136000
出 处:《自动化应用》2024年第20期138-140,共3页Automation Application
摘 要:传统的图像处理模型依赖于手工设计的特征提取器,在处理全局上下文信息时存在困难,导致模型在理解图像整体语义时受限。因此,提出了一种基于视觉自注意力模型(ViT)的智能图像处理,并对其进行改进,通过引入多头自注意力机制和层级特征提取模块,提高模型的处理能力。结果表明,所提模型在训练集数量为1200左右时的性能趋于稳定,且表现出较好的性能。其他算法在训练集数量为1200时未处于最佳性能。当训练集达到2000时,所提模型的结构相似度值为0.98。结果表明,所提模型在处理图像时表现出了较高的性能和处理效率,为图像处理领域的问题带来了新的解决方法。Traditional image processing models rely on manually designed feature extractors,which may not capture high-level semantic information in the image and pose difficulties in processing global contextual information,leading to limitations in understanding overall semantics of the image.Therefore,a smart image processing based on vision transformer(ViT)was proposed and improved by introducing a multiple headed self attention mechanism and a hierarchical feature extraction module to enhance the processing and generalization capabilities of the model.The results show that the proposed model tends to stabilize and exhibits good performance when the number of training sets is around 1200.When the number of training sets for other algorithms is 1200,their model performance still fluctuates and is not at its optimal performance.When the training set reaches 2000,the structural similarity value of the proposed model is 0.98.The results indicate that the proposed model exhibits high performance and processing efficiency in image processing,bringing new solutions to problems in the field of image processing.
关 键 词:视觉自注意力模型 图像处理 多头自注意力 人工智能
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.148.250.110