| dc.contributor | 資訊科學系 | - |
| dc.creator (作者) | 廖文宏 | zh_TW |
| dc.date (日期) | 2015-03 | - |
| dc.date.accessioned | 20-Apr-2016 17:01:11 (UTC+8) | - |
| dc.date.available | 20-Apr-2016 17:01:11 (UTC+8) | - |
| dc.date.issued (上傳時間) | 20-Apr-2016 17:01:11 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/85801 | - |
| dc.description.abstract (摘要) | 商標是一種藉由圖像或是混和圖像與文字存在的標誌，經由特定的符號或是顏色所 組成，商標圖案的設計中，除了圖像的組成、配置、形狀、顏色、混合、字體、字 體顏色等視覺元素，還包括陰影、背景色調、點、線、面等各種構成單元，這些視 覺元素應用在商標中將會帶給人們不同的視覺感受。 過去的研究中，對於視覺元素在商標中扮演的角色偏向質化的探討，通常多利用使 用者測試的方法找到設計元素與商標的相關度，較少應用電腦視覺對於圖像量化分 析的方法，本研究的目的在於利用各種視覺特徵的計算方式，分析各種商標中視覺 元素的組成，包含商標中圖像的複雜度，顏色的組成，對稱程度，比例以及其他相 關量化指標。 由於各類的視覺元素對應了許多不同的視覺特徵值計算方法，例如使用商標顏色的 計算可使用不同的色彩空間表示法，或是計算圖像中各區塊邊緣所佔的比重，抑或 是計算圖像的利用灰階值計算圖像的對稱程度等。為了解決上述問題，我們將大量 分析這些視覺元素資料，透過機器學習技術，建立商標的含意以及視覺元素的關 聯，最後利用這些視覺元素以及商標的關聯度，開發一套商標視覺元素的分析系 統，提供學習者或設計人員對於商標設計的建議。 | - |
| dc.description.abstract (摘要) | A logo is a mark composed of graph or a combination of text and graph. Typical visual elements in a logo design include higher level features such as layout, shape, color (foreground and background), composition, and typeface. Lower level descriptors such as shading, point, line and plane structure also play important roles in human perception of the logo. The graphical mark can exhibit interesting properties by mixing the elements in creative ways. Most previous researches regarding the role of visual elements in logo design are of qualitative nature. In this project, we propose to incorporate visual feature extraction and analysis algorithms commonly utilized in computer vision to compute proper index and investigate key visual elements in logo design, include complexity, balance, proportion, color, and other possible quantitative measure. There exist different approaches in defining and calculating visual features in a logo image. For example, color-related properties can be computed using different color coordinate systems. Sharpness can be approximated by accumulating the numbers of the edge pixels in a region. Symmetry can be defined by partitioning the image into sub-regions and perform the subsequent comparison. We plan to employ machine learning techniques to identify the most relevant visual features by analyzing a large collection of training images. Based on the results, we will develop an automatic visual element extraction and evaluation system to aid the creation of logos for students or graphic designers. | - |
| dc.format.extent | 4582713 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (關聯) | 計畫編號 NSC 102-2221-E004-009 | - |
| dc.title (題名) | 商標設計之視覺元素分析 | zh_TW |
| dc.title.alternative (其他題名) | Analysis of Visual Elements in Logo Design | - |
| dc.type (資料類型) | report | - |
