Investigation into color designs of product packaging through visual evaluations using machine learning methods

IF 1.9 Q3 ENGINEERING, MANUFACTURING

Manufacturing Review Pub Date : 2021-01-01 DOI:10.1051/mfreview/2021019

Yang Gao

引用次数: 0

Abstract

For a commodity, in addition to its quality, its external package is also very essential. This paper briefly introduced the intelligent support vector machine (SVM) algorithm for color design of paper packaging. The features were extracted from photos of packages using scale-invariant feature transform (SIFT), and the intelligent algorithm was trained and tested using photos of paper packaging for ceramic products collected at the ceramic crafts market as a sample set. Two paper package schemes designed in this study were used for further test. The SVM algorithm was compared with the back-propagation (BP) algorithm and the convolutional neural network (CNN) algorithm. The results showed that the three intelligent algorithms could evaluate the color design of paper packages, but the SVM algorithm was more accurate than the BP and CNN algorithms in evaluating the imagery of color design, both for the samples collected in the craft market and for the paper packaging scheme designed in this paper.

查看原文本刊更多论文

利用机器学习方法对产品包装的色彩设计进行视觉评价研究

对于一种商品来说，除了它的质量外，它的外包装也很重要。简要介绍了用于纸包装色彩设计的智能支持向量机算法。采用尺度不变特征变换(SIFT)对包装照片进行特征提取，并以在陶瓷工艺品市场采集的陶瓷产品纸包装照片为样本集对智能算法进行训练和测试。采用本研究设计的两种纸包装方案进行进一步试验。将SVM算法与BP算法和卷积神经网络(CNN)算法进行比较。结果表明，这三种智能算法都可以对纸包装的色彩设计进行评价，但SVM算法在评价色彩设计图像方面比BP和CNN算法更准确，无论是对手工市场收集的样品还是对本文设计的纸包装方案。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Manufacturing Review ENGINEERING, MANUFACTURING-

CiteScore

5.40

自引率

12.00%

发文量

审稿时长

8 weeks

期刊介绍： The aim of the journal is to stimulate and record an international forum for disseminating knowledge on the advances, developments and applications of manufacturing engineering, technology and applied sciences with a focus on critical reviews of developments in manufacturing and emerging trends in this field. The journal intends to establish a specific focus on reviews of developments of key core topics and on the emerging technologies concerning manufacturing engineering, technology and applied sciences, the aim of which is to provide readers with rapid and easy access to definitive and authoritative knowledge and research-backed opinions on future developments. The scope includes, but is not limited to critical reviews and outstanding original research papers on the advances, developments and applications of: Materials for advanced manufacturing (Metals, Polymers, Glass, Ceramics, Composites, Nano-materials, etc.) and recycling, Material processing methods and technology (Machining, Forming/Shaping, Casting, Powder Metallurgy, Laser technology, Joining, etc.), Additive/rapid manufacturing methods and technology, Tooling and surface-engineering technology (fabrication, coating, heat treatment, etc.), Micro-manufacturing methods and technology, Nano-manufacturing methods and technology, Advanced metrology, instrumentation, quality assurance, testing and inspection, Mechatronics for manufacturing automation, Manufacturing machinery and manufacturing systems, Process chain integration and manufacturing platforms, Sustainable manufacturing and Life-cycle analysis, Industry case studies involving applications of the state-of-the-art manufacturing methods, technology and systems. Content will include invited reviews, original research articles, and invited special topic contributions.