(3.236.231.61) 您好!臺灣時間:2021/05/11 22:14
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:邱明輝
研究生(外文):Chiu, Ming-Hui
論文名稱:頻繁項目用於圖片風格模仿之建議
論文名稱(外文):Frequent Itemset Mining for Suggestion of Photo Style Imitation
指導教授:黃于飛
指導教授(外文):Huang, Fay
口試委員:李遠坤孫士韋
口試委員(外文):Lee, Yeuan-KuenSun, Shih-Wei
口試日期:2016-08-25
學位類別:碩士
校院名稱:國立宜蘭大學
系所名稱:資訊工程學系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2016
畢業學年度:105
語文別:中文
論文頁數:80
中文關鍵詞:頻繁項目探勘邊緣偵測顯著性區域偵測
外文關鍵詞:Frequent Itemset MiningImage Edge DetectionSalient Region Detection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:60
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:7
  • 收藏至我的研究室書目清單書目收藏:0
在數位相機和智慧型拍照手機普及的現代,分享照片並期望引起回響成為很多人生活中的樂趣,但並非每個使用者都熟悉攝影的構圖技巧,目前的智慧型手持裝置尚無輔助改善畫面結構的功能。本論文目標為開發一個圖片風格學習系統,透過事先學習高品質圖庫的構圖風格,系統能提供給使用者構圖建議來協助拍出好照片。
在學習的階段採用頻繁項目探勘的演算法從高品質圖庫中挖掘出出現機率較高的圖片屬性組合也就是構圖風格,並做為爾後建議的依據。本論文利用影像邊緣偵測的結果來分析圖片複雜度,使用顯著性區域偵測演算法來分析主體架構,再採用色相分布情況分析顏色對比度,整理出15種圖片屬性。
實驗結果顯示系統能確實學習不同種類的圖片構圖風格,並比較使用者所輸入的圖片與學習到的構圖風格之差異性,提出改善構圖之建議。使用者可以依照建議,嘗試微調圖片中的某些屬性,盡可能讓整體構圖與所學到的某一種風格相似或一致,達到幫助使用者改善構圖風格的目標。此系統分析輸入圖片並給出建議的時間在一秒鐘以內,未來可開發APP成為相機內建的功能。
Nowadays, we live in an era which digital cameras and smartphones are very popular devices. Sharing photos on social networks using these devices has become a joyful habit in many people's lives. However not everyone is familiar with photography composition rules. Currently, the smart handheld devices are not yet equipped with the function of automatic photo composition adjustment. The major goal of this thesis is to develop a photo style imitation system. The system is able to assist users in better photo taking through a pre-learning process on a high quality image database.
In the learning process, frequent itemset mining algorithm was utilized to obtain a set of most frequent combinations of image characteristics, namely the style of the pictures, from the high quality image database. The obtained combinations of image characteristics were then used as bases for assisting composition of photographic image. In this thesis, totally 15 image characteristics were taken into account. Image edge detection method was used to determine the complexity of an image. Salient region detection algorithm was used to understand the main structure of the picture. Hue distribution was used to analyze the contrast of a color image.
The experimental results show that the developed system is able to characterize different styles of photos. Moreover, it is able to provide users suggestions on how to improve photo composition according to the image characteristic differences between the user input photo and the pre-learnt knowledge. Users may adjust some particular image characteristics of their photos according to the provided suggestions to improve the overall photo composition. This system can analyze the input photo and offer suggestions within one second, and thus potentially an App can be developed to become a built-in function for all smartphone cameras.
摘要 I
Abstract II
誌謝 III
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 1
1.3 論文架構 2
第二章 文獻探討 3
2.1 邊緣線條分析 3
2.2 顯著性區域分析 5
2.3 HSV空間色相分析 10
2.4 頻繁項目探勘 17
第三章 研究方法 20
3.1 流程介紹 21
3.2 十五項圖片風格屬性 24
3.2.1 圖片屬性一: 線條面積 25
3.2.2 圖片屬性二: 線條所占格子 27
3.2.3 圖片屬性三: 最多線條之直格 29
3.2.4 圖片屬性四: 最多線條之橫格 30
3.2.5 圖片屬性五: 未佔線條之直格數 32
3.2.6 圖片屬性六: 未佔線條之橫格數 33
3.2.7 圖片屬性七: 顯著性區域面積 36
3.2.8 圖片屬性八: 顯著性區域所占格子 38
3.2.9 圖片屬性九: 顯著性面積最大之直格 40
3.2.10 圖片屬性十: 顯著性面積最大之橫格 41
3.2.11 圖片屬性十一: 未有顯著性區域之直格數 43
3.2.12 圖片屬性十二: 未有顯著性區域之橫格數 44
3.2.13 圖片屬性十三: 顯著性區域之線條量 46
3.2.14 圖片屬性十四: 色相第一高峰和第二高峰距離 48
3.2.15 圖片屬性十五: 第一高峰色相顏色之面積 50
3.3 探勘出長度六的頻繁項目列 52
3.4 輸入圖並給出建議 54
第四章 實驗結果 56
第五章 結論與未來展望 78
參考文獻 79
[1]David Reaves.“Aesthetic Image Rating (AIR) Algorithm.”In Copenhagen, Denmark, EvoMUSART, April, 2015.
[2]John Canny.“A Computational Approach to Edge Detection.”In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, issue 6, pages 679-698, November 1986.
[3]Luca Marchesotti, Florent Perronnin, Diane Larlus and Gabriela Csurka. “Assessing the Aesthetic Quality of Photographs using Generic Image Descriptors.”In IEEE International Conference on Computer Vision, pages 1784-1791, October 2011.
[4]Kuo-Yen Lo, Keng-Hao Liu, and Chu-Song Chen. “Assessment of Photo Aesthetics with Efficiency.”In IEEE International Conference on Pattern Recognition, pages 2186-2189, November 2012.
[5]Tunc¸ Ozan Aydın, Aljoscha Smolic, and Markus Gross. “Automated Aesthetic Analysis of Photographic Images.” In IEEE Transactions on Visualization and Computer Graphics, vol. 21 , issue 1, pages 31-42, May, 2014.
[6]Wei Jiang, Alexander C. Loui and Cathleen Daniels Cerosaletti.“Automatic Aesthetic Value Assessment in Photographic Images.”In IEEE International Conference on Multimedia and Expo, pages 920-925 , July 2010.
[7]Naila Murray, Luca Marchesotti and Florent Perronnin.“A Large-Scale Database for Aesthetic Visual Analysis.”In IEEE Conference on Computer Vision and Pattern Recognition, pages 2408-2415, June 2012.
[8]Ligang Liu, Yong Jin and Qingbiao Wu.“Realtime Aesthetic Image Retargeting.”In Computational Aesthetics'10 Proceedings of the Sixth international conference on Computational Aesthetics in Graphics, Visualization and Imaging, pages 1-8, 2010.
[9]Ritendra Datta, Dhiraj Joshi, Jia Li and James Z. Wang.“Studying Aesthetics in Photographic Images Using a Computational Approach.”In ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III, pages 288-301, 2006.
[10]Xiaoou Tang, Wei Luo, and Xiaogang Wang.“Content-Based Photo Quality Assessment.”In IEEE Transactions on Multimedia, vol.15, issue 8, pages1930-1943, June 2013.

[11]Yun Zhai and Mubarak Shah.“Visual Attention Detection in Video Sequences Using Spatiotemporal Cues.”In MM '06 Proceedings of the 14th ACM international conference on Multimedia, pages 815-824, 2006.
[12]Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xiaolei Huang and Shi-Min Hu. “Global Contrast based Salient Region Detection.”In IEEE Conference on Computer Vision and Pattern Recognition, pages 409-416, June 2011.
[13]Basura Fernando, Elisa Fromont, and Tinne Tuytelaars.“Eective Use of Frequent Itemset Mining for Image Classification.”In ECCV'12 Proceedings of the 12th European conference on Computer Vision, vol. part I, pages 214-227, 2012.
[14]Vyoma Patel and G. J. Sahani.“Image Classification using Frequent Itemset Mining”In International Journal of Computer Applications, vol. 121, no. 15, July 2015.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔