留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于关键字的海报自动合成系统

关帅鹏 于海阳 杨震 周明 赖英旭

关帅鹏, 于海阳, 杨震, 等 . 基于关键字的海报自动合成系统[J]. 北京航空航天大学学报, 2022, 48(2): 356-368. doi: 10.13700/j.bh.1001-5965.2020.0552
引用本文: 关帅鹏, 于海阳, 杨震, 等 . 基于关键字的海报自动合成系统[J]. 北京航空航天大学学报, 2022, 48(2): 356-368. doi: 10.13700/j.bh.1001-5965.2020.0552
GUAN Shuaipeng, YU Haiyang, YANG Zhen, et al. Automatic poster synthesis system based on keywords[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(2): 356-368. doi: 10.13700/j.bh.1001-5965.2020.0552(in Chinese)
Citation: GUAN Shuaipeng, YU Haiyang, YANG Zhen, et al. Automatic poster synthesis system based on keywords[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(2): 356-368. doi: 10.13700/j.bh.1001-5965.2020.0552(in Chinese)

基于关键字的海报自动合成系统

doi: 10.13700/j.bh.1001-5965.2020.0552
基金项目: 

国家自然科学基金 61671030

北京市长城学者计划 CIT & TCD20190308

中国博士后科学基金 2019M660377

详细信息
    通讯作者:

    杨震, E-mail: yangzhen@bjut.edu.cn

  • 中图分类号: V221+.3;TB553

Automatic poster synthesis system based on keywords

Funds: 

National Natural Science Foundation of China 61671030

Beijing Great Wall Scholar CIT & TCD20190308

China Postdoctoral Science Foundation 2019M660377

More Information
  • 摘要:

    智能化的普及对图像编辑提出了新需求,海报作为一种以图像形式传递信息的方式,在日常生活和工作管理中起着重要的作用。海报的制作需要多元素图像进行合成,目前缺少一种交互式的、一键式的图像合成系统,因此,结合当前流行的图像处理技术,设计并实现了一款海报自动合成系统。提出了一种基于关键字的图像检索方案,构建基于文本和内容的双重过滤方案,为用户提供精准快捷的图像检索手段;通过对大量精心设计的海报图像统计构图规律并引入美学常识的构图规则,提出了一种基于双向规则的人像布局推荐方案;在双向规则的共同作用下辅助用户进行人像布局设计。实验结果表明:所提方案能够稳定高效地运行,用户能够通过简单的交互操作实现图像合成,最终图像合成的效果真实有效。

     

  • 图 1  海报自动合成系统流程

    Figure 1.  Procedure of automatic poster synthesis system

    图 2  复杂性过滤过程

    Figure 2.  Process of complexity filtering

    图 3  GrabCut算法交互过程

    Figure 3.  Interaction process of GrabCut algorithm

    图 4  HSV颜色空间

    Figure 4.  Space of HSV color

    图 5  人像姿态特征

    Figure 5.  Feature of human pose

    图 6  Meanshift算法迭代过程

    Figure 6.  Iterative process of Meanshift algorithm

    图 7  泊松图像编辑原理

    Figure 7.  Schematic diagram of Poisson image editing

    图 8  霍夫直线检测流程

    Figure 8.  Process of Hough line detection

    图 9  灭点概念

    Figure 9.  Concept of vanishing point

    图 10  图像检索结果

    Figure 10.  Results of image retrieval

    图 11  图像无缝融合结果

    Figure 11.  Results of seamless integration of image

    图 12  人像分布

    Figure 12.  Distribution of human position

    图 13  负规则检测结果

    Figure 13.  Results of negative rule detection

    图 14  人像布局推荐结果

    Figure 14.  Results of human position recommendation

    图 15  系统整体结果

    Figure 15.  Final result of system

    表  1  图像检索结果

    Table  1.   Results of image retrieval

    检索目标 假阳率/%
    Park Jumpdog Polar bear Soccerplayer Goalkeeper Manthrow
    互联网检索 94 80 78 86 80 71
    复杂性过滤 78 76 70 61 76 65
    一致性排序 34 27 28 30 18 21
    下载: 导出CSV
  • [1] JOHNSON M, BROSTOW G J, SHOTTON J, et al. Semantic photo synthesis[J]. Computer Graphics Forum, 2006, 25(3): 407-413. doi: 10.1111/j.1467-8659.2006.00960.x
    [2] CHEN T, CHENG M M, TAN P, et al. Sketch2Photo[J]. ACM Transactions on Graphics, 2009, 28(5): 1-10.
    [3] NIBLACK C W, BARBER R, EQUITZ W, et al. QBIC project: Querying images by content, using color, texture, and shape[C]//Proceedings SPIE 1908, Storage and Retrieval for Image and Video Databases, 1993, 1908: 173-187.
    [4] PENTLAND A, PICARD R W, SCLAROFF S. Photobook: Content-based manipulation of image databases[J]. International Journal of Computer Vision, 1996, 18(3): 233-254. doi: 10.1007/BF00123143
    [5] AGARWALA A, DONTCHEVA M, AGRAWALA M, et al. Interactive digital photomontage[C]//ACM SIGGRAPH 2004. New York: ACM, 2004: 294-302.
    [6] BEZDEK J C. Modified objective function algorithms[M]. Berlin: Springer, 1981: 155-201.
    [7] BOYKOV Y Y, JOLLY M P. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images[C]//Proceedings 8th IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2001: 105-112.
    [8] ROTHER C, KOLMOGOROV V, BLAKE A. GrabCut: Interactive foreground extraction using iterated graph cnts[J]. ACM Transactions on Graphics, 2004, 23(3): 309-314. doi: 10.1145/1015706.1015720
    [9] FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision, 2004, 59(2): 167-181. doi: 10.1023/B:VISI.0000022288.19776.77
    [10] WANG J, COHEN M F. Simultaneous matting and compositing[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2007: 1-8.
    [11] FATTAL R, LISCHINSKI D, WERMAN M. Gradient domain high dynamic range compression[C]//ACM SIGGRAPH 2002. New York: ACM, 2002: 249-256.
    [12] PÉREZ P, GANGNET M, BLAKE A. Poisson image editing[C]//ACM SIGGRAPH 2003. New York: ACM, 2003: 313-318.
    [13] INABA S, KANEZAKI A, HARADA T. Automatic image synthesis from keywords using scene context[C]//Proceedings of the 22nd ACM International Conference on Multimedia. New York: ACM, 2014: 1149-1152.
    [14] BHATTACHARYA S, SUKTHANKAR R, SHAH M. A framework for photo-quality assessment and enhancement based on visual aesthetics[C]//Proceedings of the 18th ACM International Conference on Multimedia, New York: ACM, 2010: 271-280.
    [15] ZHANG Y H, SUN X S, YAO H X, et al. Aesthetic composition represetation for portrait photographing recommendation[C]//201219th IEEE International Conference on Image Processing. Piscataway: IEEE Press, 2012: 2753-2756.
    [16] WANG Y T, SONG M L, TAO D C, et al. Where2Stand[J]. ACM Transactions on Intelligent Systems and Technology, 2015, 7(1): 1-22.
    [17] RAWAT Y S, SONG M L, KANKANHALLI M S. A spring-electric graph model for socialized group photography[J]. IEEE Transactions on Multimedia, 2018, 20(3): 754-766. doi: 10.1109/TMM.2017.2750420
    [18] YANG Z, LEI J J, FAN K F, et al. Keyword extraction by entropy difference between the intrinsic and extrinsic mode[J]. Physica A: Statistical Mechanics and Its Applications, 2013, 392(19): 4523-4531. doi: 10.1016/j.physa.2013.05.052
    [19] HOU Q B, CHENG M M, HU X W, et al. Deeply supervised salient object detection with short connections[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 5300-5309.
    [20] CHENG M M, MITRA N J, HUANG X, et al. Global contrast based salient region dection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(3): 569-582.
    [21] RAO A, SRIHARI R K, ZHANG Z. Spatial color histograms for content-based image retrieval[C]//Proceedings 11th International Conference on Tools with Artificial Intelligence. Piscataway: IEEE Press, 1999: 183-186.
    [22] 童振兴. 基于内容的图像检索技术综述与展望[J]. 计算机光盘软件与应用, 2010, 13(6): 88.

    TONG Z X. Content-based image retrieval technologies summary and prospects[J]. Computer CD Software and Applications, 2010, 13(6): 88(in Chinese).
    [23] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2005: 886-893.
    [24] XIE Y, LIU L F, LI C H, et al. Unifying visual saliency with HOG feature learning for traffic sign detection[C]//2009 IEEE Intelligent Vehicles Symposium. Piscataway: IEEE Press, 2009: 24-29.
    [25] TERASAWA K, TANAKA Y. Slit style HOG feature for document image word spotting[C]//200910th International Conference on Document Analysis and Recognition. Piscataway: IEEE Press, 2009: 116-120.
    [26] WEI S H, RAMAKRISHNA V, KANADE T, et al. Convolutional pose machines[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 4724-4732.
    [27] SIMON T, JOO H, MATTHEWS I, et al. Hand keypoint detection in single images using multiview bootstrapping[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 4645-4653.
    [28] CAO Z, SIMON T, WEI S H, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 1302-1310.
    [29] CHENG Y Z. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799. doi: 10.1109/34.400568
    [30] KANUNGO T, MOUNT D M, NETANYAHU N S, et al. An efficient K-means clustering algorithm: Analysis and implementation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 881-892. doi: 10.1109/TPAMI.2002.1017616
    [31] SCHWARZ G. Estimating the dimension of a model[J]. The Annals of Statistics, 1978, 6(2): 461-464.
    [32] DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society: Series B (Methodological), 1977, 39(1): 1-22. doi: 10.1111/j.2517-6161.1977.tb01600.x
    [33] ZUCKER M. Monte Zucker's portrait photography handbook[M]. [S. l. ]: Amherst Media, 2007.
    [34] BALLARD D H. Generalizing the Hough transform to detect arbitrary shapes[J]. Pattern Recognition, 1981, 13(2): 111-122. doi: 10.1016/0031-3203(81)90009-1
    [35] TOLDO R, FUSIELLO A. Robust multiple structures estimation with J-linkage[C]//European Conference on Computer Vision. Berlin: Springer, 2008: 537-547.
  • 加载中
图(15) / 表(1)
计量
  • 文章访问数:  301
  • HTML全文浏览量:  47
  • PDF下载量:  55
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-09-27
  • 录用日期:  2020-12-04
  • 网络出版日期:  2022-02-20

目录

    /

    返回文章
    返回
    常见问答