基于语义分割的图像风格迁移技术研究  

Research on Image Style Transfer Technology Based on Semantic Segmentation

作　　者：李美丽 杨传颖[1] 石宝 LI Meili;YANG Chuanying;SHI Bao(School of Information Engineering,Inner Mongol University of Technology,Hohhot 010100,China)

机构地区：[1]内蒙古工业大学信息工程学院,呼和浩特010100

出　　处：《计算机工程与应用》2020年第24期207-213,共7页Computer Engineering and Applications

基　　金：内蒙古自治区自然科学基金(No.2017BS0602)。

摘　　要：随着民族服装文化的碰撞与融合,对图像风格迁移技术进行了研究,阐述了当前风格迁移的研究现状,将蒙古族服饰风格与汉族风格进行融合,继承和弘扬了民族文化。针对蒙古服饰元素多样、颜色差异大、花纹不规则性等特征而引起的风格提取难度大的问题,采用K均值与封闭式自然抠图算法相结合的方法进行图像分割,基于神经网络提取图像的风格和内容,利用图像重建技术合成结果图,实现蒙汉服饰图像风格迁移;针对输出图像伪影严重的问题,采取一种改进的图像风格迁移算法,将输入图像到输出图像的变换约束在色彩空间的局部仿射变换中,将这个约束表示成一个完全可微的参数项,有效抑制图像扭曲,针对真实照片风格迁移过程中存在的空间不一致问题,进行平滑处理确保风格处理后空间风格一致,该方法大大加快了运算速度。With the collision and fusion of national costume culture,this paper studies the image style transfer technology,expounds the current research status of style transfer,integrates Mongolian costume style with Han style,and inherits and promotes the national culture.For large difference of Mongolian costume elements variety,color,decorative pattern characteristics and cause of style such as irregularity extraction is difficult problem,it uses the algorithm of K-means and closed natural cutout combination method for image segmentation,extracts the image of style and content based on neural network,uses image reconstruction technology to synthesize results,implements the image style transfer of Mongolian and Han clothing.According to the serious output image artifact,it adopts the migration algorithm,an improved image style will constrain the transform of the input image to the output image in the local affine transformation of color space,the constraints are represented as a differentiable parameter completely,it effectively restrains image distortion,at the same time in real style photos do not match the space problems in the process of migration,it treatments smoothly to ensure the space style is consistent,this method greatly accelerates the speed.

关 键 词：服饰特征提取 封闭式自然图像抠图算法 K均值算法 图像分割 图像风格迁移 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]