摘要
织绣文物中的纹样彰显中国传统文化造型艺术的形式美感,是文创设计的重要素材源泉。针对传统Canny算子进行纹样边缘检测需人为确定阈值的问题,本文提出基于遗传算法自适应优化Canny算子阈值的方法,将边缘点、非边缘点类间梯度幅值方差设置为适应度函数,通过格雷码对阈值染色体编解码、锦标赛选择算法优选交叉变异后的阈值,求解最优适应度对应的高低阈值,用于纹样边缘检测;此外,运用形态学操作得到纹样的完整、精确轮廓;最后,添加Alpha通道抽取纹样前景。实验表明,上述方法在织绣纹样抽取精度和像素准确度(PA)上,优于传统Canny算子、混合蛙跳自适应Canny算子、Otsu法优化Canny算子等已有方法,可有效检测织绣文物图像中纹样真实边缘并完成纹样抽取。
Weaving and embroidering are the craft of weaving,knitting or embroidering with cotton,linen,silk,wool and other textile materials.China is the starting point of the Silk Road,the birthplace of sericulture,silk reeling and silk weaving,and the exquisite skills of the weaving and embroidery industry enjoy a high reputation in the world.The patterns of woven and embroidered artifacts present historical,cultural and artistic values,highlight the formal beauty of plastic arts in traditional Chinese culture,and provide rich material resources for cultural and creative design.However,the traditional weaving and embroidering design mainly relies on manual pattern extraction,which has problems such as high cost,complicated steps,long cycle and low efficiency.To this end,this paper proposed an algorithm based on genetic algorithm to adaptively determine the optimal threshold value of Canny operator to automatically extract the patterns in the images of woven and embroidered artifacts,improve the extraction efficiency and effect,make the artifacts“live”,and promote the inheritance and protection of traditional Chinese culture.To realize the automatic extraction of patterns from images of woven and embroidered artifacts,and solve the problem that traditional Canny operators need to manually determine the threshold for edge detection of images of woven and embroidered artifacts,and that the extraction efficiency is not high,the article,took the images of woven and embroidered artifacts as the research object,proposing a genetic algorithm to optimize the Canny operator for the extraction of patterns from woven and embroidered artifacts.Firstly,the paper analyzed the characteristics of the images of the woven and embroidered artifacts,and used bilateral filtering algorithm and mean drift algorithm to smooth the noisy original image;for the gray scale of the smoothed graph,it selected the genetic algorithm to solve the optimal threshold of Canny operator,and input the optimal threshold into Canny operator for the edge detection of the gray scale graph.Then,the paper expanded the morphology of the edge image,and automatically filtered out noise and incomplete pattern samples based on the area,length,and width of each connectivity domain.Finally,the algorithm was evaluated for the effect of extracting patterns and the algorithm’s running time.Experiments show that the algorithm can accurately detect the real edges of the pattern in the image of the woven and embroidered artifacts,and the edges detected are clearer and more continuous than those detected by the other five traditional operators.In terms of pattern extraction precision and pixel accuracy(PA),it is better than the existing methods such as traditional Canny operators,hybrid frog jump adaptive Canny operator,Otsu maximum optimized Canny operator and so on.The algorithm is robust to the presence of folds that lead to pattern deformation in the woven and embroidered artifacts,and all the patterns are successfully extracted.The algorithm can effectively detect the real edges of the patterns in the image of woven and embroidered artifacts and complete the pattern extraction.Woven and embroidered artifacts contain deep cultural heritage and artistic value,and through pattern extraction,designers can integrate traditional cultural elements into modern design to create unique cultural and creative products.In this paper,the algorithm solves the problem that the traditional Canny operators need to determine the threshold value for the edge detection of woven and embroidered artifacts,and that the extraction efficiency is not high.In the process of cultural and creative design,the digitization of cultural and creative materials is the first step.In addition,the grasp and application of the knowledge of history and culture,artistic connotations,unique stories and symbolic meanings embedded in patterns can more accurately capture the essence of the culture and the emotional expression it represents.For this reason,it is of deeper significance and value to carry out research on the integration and mining of multimodal information such as patterns and knowledge in the future.
作者
张宇
张健
齐林
ZHANG Yu;ZHANG Jian;QI Lin(School of Economics&Management,Beijing InformationScience&Technology University,Beijing 100192,China;Key Research Base of Beijing Municipal Cultural Heritage Bureau,Beijing InformationScience&Technology University,Beijing 100192,China;Beijing World Urban Circular Economy System(Industry)Collaborative Innovation Center,Beijing 100192,China;Beijing Key Lab ofGreen Development Decision Based on Big Data,Beijing 100192,China)
出处
《丝绸》
CAS
CSCD
北大核心
2024年第6期1-12,共12页
Journal of Silk
基金
北京市属高等学校优秀青年人才培育计划项目(BPHR202203235)
国家重点研发计划青年科学家项目(2021YFF0900200)
北京信息科技大学促进高效内涵发展项目(5026010961)。
关键词
织绣文物
遗传算法
CANNY算子
边缘检测
纹样抽取
最优阈值
woven and embroidered artifacts
genetic algorithm
Canny operator
edge detection
pattern extraction
optimal thresholding