基于神经网络的男西装图像情感语义识别

纺织学报 ›› 2013, Vol. 34 ›› Issue (12): 138-0.

基于神经网络的男西装图像情感语义识别

张海波^1,2,黄铁军³,修毅¹,赵野军¹,章江华⁴

1. 北京服装学院计算机信息中心
2. 北京服装学院服装材料研究开发与评价北京市重点实验室
3. 北京大学信息科学技术学院
4. 北京服装学院基础教学部

收稿日期:2012-11-19 修回日期:2013-08-09 出版日期:2013-12-15 发布日期:2013-12-16
通讯作者: 张海波 E-mail:hbdmzhb@126.com
基金资助:
教育部人文社会科学规划基金资助项目；北京市自然科学基金资助项目；服装材料研究开发与评价北京市重点实验室开放课题

Men’s suit image emotional semantic recognition based on BP neural network

Received:2012-11-19 Revised:2013-08-09 Online:2013-12-15 Published:2013-12-16
Contact: Hai-Bo ZHANG E-mail:hbdmzhb@126.com

摘要/Abstract

摘要： 为了实现基于内容的男西装图像情感语义识别，需要把男西装图像的低层特征映射到情感语义空间。在构建出的2维图像情感因子空间和男西装图像视觉特征（10维亮度一冷暖模糊直方图；7维的饱和度一冷暖模糊直方图+色彩对比度值的综合特征）的基础上，本文通过机器学习（BP神经网络）实现了男西装图像的低层特征到情感语义因子空间的映射，根据图像低层颜色特征可以自动完成图像情感因子值和情感描述值的计算，并把识别后的新图像数据自动加入到图像数据库中。实验证明，BP神经网络方法能较好的实现基于内容的男西装图像情感语义的识别。

关键词: 男西装图像, 情感语义, 颜色特征, BP神经网络, 图像识别

Abstract: In order to realize the content-based men’s suit image emotional semantic recognition, the primitive features of men’s suit image need to be mapped to emotion semantic space. Based on the formed two-dimension image emotional factor space and the primitive features of men’s suit image (ten-dimension of brightness, warm-cold fuzzy histogram; seven-dimension of saturation, warm-cold fuzzy histogram and color contrast value) in our previous work, the machine learning, BP neural network could help to realize the mapping that from the primitive features of men’s suit image to the emotion semantic factor space. The primitive features of image color could finish the image emotional factor values and description values calculation automatically, and the new image data could be added after identification to the image emotion database automatically. Experiments have proved that BP neural network method can be a better method to realize the content-based men’s suit image emotional semantic recognition.

Key words: men's suit image, emotional semantic, color feature, BP neural network, image recognition

张海波黄铁军修毅赵野军章江华. 基于神经网络的男西装图像情感语义识别[J]. 纺织学报, 2013, 34(12): 138-0.

参考文献

[1] KUO CF J, HSU CT M, SHIH C Y. Automatic pattern recognition and color separation of embroidery fabrics[J]. Textile Research Journal, 2011, 81(11): 1145-1157.
[2] LIU CI C. D.S.-M. An intelligent clothes search system based on fashion styles[C]. 2008 International Conference on Machine Learning and Cybernetics, July 2008: 1592-1597.
[3] OUYANG Y. Clothes image searching system based on SIFT features[C]. E-Business and Information System Security, 2009. EBISS '09. May 2009:1-5.
[4] CHEN Y W, SOBUE S, HUANG X Y. KANSEI based clothing fabric image retrieval [C]. The 2009 Computational Color Imaging Workshop(CCIW), France, Jul. 2009:71-80.
[5] 贺静. 基于特征融合的服装图像情感语义分类研[D]. 太原：太原理工大学硕士学位论文，2007.
[6] YOSHIDA K, KATO T, YANARU T. Image retrieval system using impression words[C]. 1998 IEEE International Conference on Systems, Man, and Cybernetics,1998,3(11-14):2780-2784.
[7] BIANCHI N B. K-DIME: A affective image filtering system[J]. IEEE Multimedia, 2003,10(3):103-106.
[8] 王伟凝．基于情感语义的图像特征提取、检索与分类研究[D]．广州：华南理工大学博士学位论文，2005．
[9] MACHAJDIK J, HANBURY A. Affective image classification using features inspired by Psychology and art theory[C]. ACM Multimedia 2010 International Conference:83-92.
[10] 张海波，刘瑞璞，刘莉. 男西装情感因子空间研究[J]，东华大学学报（自然科学版），2012，38(3):292-296.
[11] 张海波，黄铁军，刘瑞璞. 基于颜色特征的男西装图像情感语义分析[J]，东华大学学报（自然科学版），2013，（2）.（已录用）.
[12] CHANG C Y, WANG H J, JIAN R H. Semantic image retrieval with fuzzy-ART[C]. International Conference on System Science and Engineering (ICSSE), 1-3 July 2010: 69-74.
[13] JYOTHI B V, SHANKER C U, VERMA S M. Research study of neural networks for image categorization and retrieval[C]. The 2nd International Conference on Computer and Automation Engineering (ICCAE), 26-28 Feb. 2010,Vol: 2: 686-690.
[14] CAO Y, LIU X B, BING J, SONG L. Using Neural Network to combine measures of word semantic similarity for image annotation[C]. International Conference on Information and Automation (ICIA), 2011 IEEE,6-8 June 2011:833-837.
[15] ZHANG H B, HUANG T J, LIU R P. Image database system of clothing emotion[C]. 2011 International Conference on E -Business and E -Government (ICEE), 6-8 May 2011: 5116-5119.

相关文章 15

[1]	向忠何旋钱淼胡旭东. 基于边缘和颜色特征的织物印花花型检索[J]. 纺织学报, 2018, 39(05): 137-143.
[2]	张成梁李蕾董全成葛荣雨. 应用区域颜色分割的机采棉杂质检测方法[J]. 纺织学报, 2017, 38(07): 135-141.
[3]	张宁潘如如高卫东. 采用图像处理的织物缝纫平整度自动评估[J]. 纺织学报, 2017, 38(04): 145-150.
[4]	曹丽胡旭东. 基于多特征融合的织物印花图像分割[J]. 纺织学报, 2016, 37(08): 149-153.
[5]	黎聪闫学娜曾祥忠梁猛张莹. 应用一维傅里叶变换的剖幅区自动识别与定位[J]. 纺织学报, 2016, 37(01): 147-151.
[6]	夏帆刘翔. 基于服装设计要素和法则的智能配搭设计[J]. 纺织学报, 2015, 36(07): 94-0.
[7]	夏明陈益松张文斌. 基于椭圆傅里叶的人体胸围断面形状研究[J]. 纺织学报, 2014, 35(7): 107-0.
[8]	杨梦星张毅郑秋婷. BP神经网络预测环境对丝织物力学性能的影响[J]. 纺织学报, 2013, 34(8): 39-0.
[9]	黄成王晓任春明王辉刘燕刘凯. 亚麻织物接枝率与透气率变化关系的数学模型[J]. 纺织学报, 2013, 34(1): 90-95.
[10]	林君焕张国庆张树有. 缝纫机缝纫性能测量评价系统的设计[J]. 纺织学报, 2013, 34(1): 116-121.
[11]	狄宏静刘冬云吴志明. 基于BP神经网络的春夏女装流行色预测[J]. 纺织学报, 2011, 32(7): 111-116.
[12]	李翔;彭志勤;金凤英;顾宗栋;薛元;胡国樑. 基于神经网络的精纺毛纱性能预测模型比较[J]. 纺织学报, 2011, 32(3): 51-56.
[13]	徐展鹏, 孙云云, 刘涵, 郭吉丰. 基于神经网络算法的工缝机节能电动机控制系统的设计[J]. 纺织学报, 2011, 32(12): 128-133.
[14]	吴雄华;刘亚;. 基于BP神经网络的熔喷非织造布工艺参数优化[J]. 纺织学报, 2011, 32(1): 51-54.
[15]	郑春玲. 改进的LM-BP算法预测活性染料染色K/S值[J]. 纺织学报, 2010, 31(8): 82-85.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed