[1]纪乐福,王永江,李启正*.基于DreamBooth的傣锦图案人工智能生成模型[J].服装学报,2024,9(05):433-442.
 JI Lefu,WANG Yongjiang,LI Qizheng*.Artificial Intelligence Generation Model for Dai Brocade Pattern Based on DreamBooth[J].Journal of Clothing Research,2024,9(05):433-442.
点击复制

基于DreamBooth的傣锦图案人工智能生成模型()
分享到:

《服装学报》[ISSN:2096-1928/CN:32-1864/TS]

卷:
第9卷
期数:
2024年05期
页码:
433-442
栏目:
民族服装
出版日期:
2024-11-01

文章信息/Info

Title:
Artificial Intelligence Generation Model for Dai Brocade Pattern Based on DreamBooth
作者:
纪乐福;  王永江;  李启正*
浙江理工大学 纺织科学与工程学院(国际丝绸学院),浙江 杭州 310018
Author(s):
JI Lefu;  WANG Yongjiang;  LI Qizheng*
College of Textile Science and Engineering(International Institute of Silk), Zhejiang Sci-Tech University, Hangzhou 310018,China
分类号:
TS 941.26
文献标志码:
A
摘要:
为推动传统文化引领下的现代纺织图案设计发展,提出了一种利用人工智能生成民族纺织图案的模型。以傣族织锦图案为例,对傣族织锦实物图案进行矢量化处理,为每张图片编写对应文本标签,并以此为训练集; 选取适用于傣锦的预训练模型,使用DreamBooth方法微调现有的文本-图像模型。对模型训练效果进行分析,得出V1模型是一个具有良好拟合度和图像生成效果的文本-图像生成模型。
Abstract:
In order to promote the development of modern textile pattern design under the guidance of traditional culture, a model of introducing ethnic textile patterns into the field of artificial intelligence creation was proposed. Taking the Dai brocade pattern as an example, the physical images of Dai brocade were vectorized, and the corresponding text labels were written for each image, and the training set was used. The research selected a pre-trained model suitable for Dai brocade, and used the DreamBooth method to fine-tune the existing text image models. By analyzing the training effect of the model, it is concluded that V1 model is a text-image generation model with good fitting degree and image generation effect.

参考文献/References:

[1] 方婷玉, 艾惠花, 李启正, 等. 傣族织锦支系地域的纹样特征及矢量化研究[J]. 丝绸, 2023, 60(2): 84-92.
FANG Tingyu, AI Huihua, LI Qizheng, et al. Study on the pattern characteristics and vectorization of Dai brocade branches and regions[J]. Journal of Silk, 2023, 60(2): 84-92.(in Chinese)
[2] 桂宇,阴佳芮.从傣锦织造技艺看女性主体构建的民族文化表征[J].服装学报,2023,8(4):350-356.
GUI Yu,YIN Jiarui.Viewing the national cultural representation dominatedly constructed by female from Dai brocade weaving technique[J].Journal of Clothing Research,2023,8(4):350-356.(in Chinese)
[3] 刘倩. 自贸港背景下黎锦传统元素数字化传播机制研究[J]. 西部皮革, 2023, 45(8): 63- 65.
LIU Qian. Research on the digital communication mechanism of Lijin traditional elements under the background of free trade port[J]. West Leather, 2023, 45(8): 63- 65.(in Chinese)
[4] 肖红梅,王伟珍,房媛.基于生成对抗网络的女上装图像属性编辑[J].服装学报,2024,9(1):42- 47.
XIAO Hongmei,WANG Weizhen,FANG Yuan.Image attribute editing of women’s tops based on generating adversarial networks[J].Journal of Clothing Research,2024,9(1):42- 47.(in Chinese)
[5] RUIZ N, LI Y Z, JAMPANI V, et al. DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation[C]//2023 IEEE/CVF conference on computer vision and pattern recognition. Vancouver:IEEE, 2023: 22500-22510.
[6] 汤琳, 贺荣, 蔡王丹, 等. 傣族织锦的艺术特征及其应用分析[J]. 丝绸, 2021, 58(8): 113-119.
TANG Lin, HE Rong, CAI Wangdan, et al. Analysis on the artistic characteristics of Dai brocade and its application[J]. Journal of Silk, 2021, 58(8): 113-119.(in Chinese)
[7] 赵梦蝶, 谢颖, 李安娜. 傣锦纹样特征与民族精神内涵关系研究[J]. 中国民族博览, 2023(1): 40- 42.
ZHAO Mengdie, XIE Ying, LI Anna. Study on the relationship between Dai brocade pattern characteristics and national spirit connotation[J]. China National Exhibition, 2023(1): 40- 42.(in Chinese)
[8] 申玉红, 杨启祥, 周长军. 云南德宏傣族服饰中的数学文化[J]. 数学教育学报, 2013, 22(1): 66- 69.
SHEN Yuhong, YANG Qixiang, ZHOU Changjun. Mathematical culture of Dehong Dai dress in Yunnan Province[J]. Journal of Mathematics Education, 2013, 22(1): 66- 69.(in Chinese)
[9] 陈晴, 孙宏, 朱淑芹, 等. 傣族纹样色织小提花面料的设计[J]. 纺织科技进展, 2017(5): 28-31.
CHEN Qing, SUN Hong, ZHU Shuqin, et al. Design of yarn dyed jacquard fabric with Dai nationality pattern[J]. Progress in Textile Science and Technology, 2017(5): 28-31.(in Chinese)
[10] 骆鋆墁, 王羿. 傣锦佛幡的图案纹样及其文化内涵浅析[J]. 山东纺织经济, 2013, 30(12): 62- 63, 67.
LUO Yunman, WANG Yi. A brief analysis of the patterns and cultural connotation of Dai brocade[J]. Shandong Textile Economy, 2013, 30(12): 62- 63, 67.(in Chinese)
[11] 谭建荣, 岳小莉, 陆国栋. 图形相似的基本原理、方法及其在结构模式识别中的应用[J]. 计算机学报, 2002, 25(9): 959-967.
TAN Jianrong, YUE Xiaoli, LU Guodong. Basic principle, method of graphic similarity and its application to structure pattern recognition[J]. Chinese Journal of Computers, 2002, 25(9): 959-967.(in Chinese)
[12] 李林红, 杨杰, 蒋严宣,等. 基于改进MobileNet v2的服装图像分类算法[J]. 现代纺织技术, 2024, 32(4): 93-103.
LI Linhong,YANG Jie, JIANG Yanxuan, et al. Clothing image classification algorithm based on improved MobileNet v2[J]. Advanced Textile Technology, 2024, 32(4): 93-103.(in Chinese)
[13] 赵昀睿, 许倩倩, 姜阳邦彦, 等. 迭代式的深度PU学习与类别先验估计框架[J]. 计算机学报, 2022, 45(12): 2667-2686.
ZHAO Yunrui, XU Qianqian, JIANG Yangbangyan, et al. An iterative framework for deep PU learning and class prior estimation[J]. Chinese Journal of Computers, 2022, 45(12): 2667-2686.(in Chinese)
[14] 佟雨兵, 张其善, 祁云平. 基于PSNR与SSIM联合的图像质量评价模型[J]. 中国图象图形学报, 2006, 11(12): 1758-1763.
TONG Yubing, ZHANG Qishan, QI Yunping. Image quality assessing by combining PSNR with SSIM[J]. Journal of Image and Graphics, 2006, 11(12): 1758-1763.(in Chinese)
[15] 张小利, 李雄飞, 李军. 融合图像质量评价指标的相关性分析及性能评估[J]. 自动化学报, 2014, 40(2): 306-315.
ZHANG Xiaoli, LI Xiongfei, LI Jun. Validation and correlation analysis of metrics for evaluating performance of image fusion[J]. Acta Automatica Sinica, 2014, 40(2): 306-315.(in Chinese)
[16] 张维强, 宋国乡. 基于一种新的阈值函数的小波域信号去噪[J]. 西安电子科技大学学报, 2004, 31(2): 296-299, 303.
ZHANG Weiqiang, SONG Guoxiang. Signal de-noising in wavelet domain based on a new kind of thresholding function[J]. Journal of Xidian University, 2004, 31(2): 296-299, 303.(in Chinese)
[17] 孟琭, 杨旭. 目标跟踪算法综述[J]. 自动化学报, 2019, 45(7): 1244-1260.
MENG Lu, YANG Xu. A survey of object tracking algorithms[J]. Acta Automatica Sinica, 2019, 45(7): 1244-1260.(in Chinese)
[18] 刘贵喜, 杨万海. 基于小波分解的图像融合方法及性能评价[J]. 自动化学报, 2002, 28(6): 927-934.
LIU Guixi, YANG Wanhai. A wavelet-decomposition-based image fusion scheme and its performance evaluation[J]. Acta Automatica Sinica, 2002, 28(6): 927-934.(in Chinese)
[19] 钟建军, 宋健, 由长喜, 等. 基于信噪比评价的阈值优选小波去噪法[J]. 清华大学学报(自然科学版), 2014, 54(2): 259-263.
ZHONG Jianjun, SONG Jian, YOU Changxi, et al. Wavelet de-noising method with threshold selection rules based on SNR evaluations[J]. Journal of Tsinghua University(Science and Technology), 2014, 54(2): 259-263.(in Chinese)
[20] 褚江, 陈强, 杨曦晨. 全参考图像质量评价综述[J]. 计算机应用研究, 2014, 31(1): 13-22.
CHU Jiang, CHEN Qiang, YANG Xichen. Review on full reference image quality assessment algorithms[J]. Application Research of Computers, 2014, 31(1): 13-22.(in Chinese)
(责任编辑:沈天琦)

更新日期/Last Update: 2024-10-30