臺灣博碩士論文加值系統

數位相機的普及率越來越高，因此越來越多人拍照，使得數位照片成
指數性成長。面對龐大數量的照片，照片的整理與挑選成了一個很大
的問題。
照片構圖的意思是相機位置的擺設以及視野的選擇，決定什麼物體
該放進來或該排除在外，一般來說，照片構圖幾乎決定了一張照片的
好壞，所以我們針對照片構圖的部分做研究。照片構圖這個問題往往
是主觀的，也跟人類的視覺感受有關，雖然是主觀的，但幸運的是，
根據攝影學家多年來的經驗，可以萃取出一些比較通用性的原則，這
些規則在各種談攝影的書中被談到。我們從書中挑選出幾個定義較明
確、且較適用於電腦量化分析的規則，將他們實作成可以自動化執行
的程序，用這些規則挑選出比較不好的照片，以及對照片做一些建議
與評分。
一張不是很好的照片如果經過很好的裁切，可以讓一張照片起死
回生，現在數位相機的能力也越來越強，照片的解析度越來越高，在
沒有輸出太大尺寸照片需求的原則下，很有本錢可以對照片做一些裁
切，我們以構圖分析的結果來做裁切的原則，有機會能讓照片變的更
好。
我們初步的結果是基於132 張照片，這些照片是針對每個規則（水
平線、照片平衡、主體位置、線條及形狀、避免融合）挑選出比較
簡化的情況，每個規則的準確率分別在71%、96.8%、73.1%、78.4%以
及71.4%。

Digital camera is very popular and the number of digital photos grows exponentially.
Faced to huge number of photos, the collection and selection of
photos becomes a big problem.
Photo composition means the placement of camera and the selection of
the field of view. It determines whether objects should be placed inside the
photo or be excluded outside. Most people agree that photo composition
almost determines whether a photo is good or not. Therefore, our research is
focus on photo composition. This problem is subjective and relates to human
visual perception. Although this problem is subjective, it is fortunate that
from the experience accumulated by photographers in recent years, certain
common rules were extracted. We select the rules that have clear definition
and suitable for automatic quantitative analysis to pick out bad photos or to
make recommendations and scores.
It is said that a not very good photo after doing a good cropping will let a
photo turn from death into life. The performance of digital camera nowadays
is more and more powerful and image resolution is higher and higher, and
so images can be cropped without serious loss of resolution. Our results in
automatic cropping support this observation.
Our preliminary results for 132 photos are based on five rules (the horizon,
photo balance, location of main object, revealing line patterns and shapes,
and avoiding mergers), and the precision of each rule is 71%, 96.8%, 73.1%,
78.4%, and 71.4%, respectively.

致謝i
摘要ii
Abstract iii
1 Introduction 1
2 Related work 4
2.1 Recomposition, information preserving, and automatic cropping . . . . . 4
2.2 Feature extraction tools for photo composition . . . . . . . . . . . . . . . 5
2.2.1 Canny edge detection . . . . . . . . . . . . . . . . . . . . . . . . 5
2.2.2 Hough transform for line detection . . . . . . . . . . . . . . . . . 9
2.2.3 Region of interest (ROI) . . . . . . . . . . . . . . . . . . . . . . 11
2.2.4 Face detection . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3 Rules of esthetics in photo composition 17
3.1 The horizon . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2 Photo balance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
3.3 Location of main object: the rule of thirds . . . . . . . . . . . . . . . . . 18
3.4 Revealing line patterns and shapes . . . . . . . . . . . . . . . . . . . . . 18
3.5 Avoiding mergers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
3.6 Others: Reserving more space for the viewing direction, etc. . . . . . . . 20
4 Implementation 22
4.1 Scoring system . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
4.1.1 The horizon . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
4.1.2 Photo balance . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4.1.3 Location of main object . . . . . . . . . . . . . . . . . . . . . . 25
4.1.4 Revealing line patterns and shapes . . . . . . . . . . . . . . . . . 26
4.1.5 Avoiding mergers . . . . . . . . . . . . . . . . . . . . . . . . . . 29
4.1.6 Parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
4.2 Automatic correction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
4.2.1 Rotational correction . . . . . . . . . . . . . . . . . . . . . . . . 30
4.2.2 Cropping correction . . . . . . . . . . . . . . . . . . . . . . . . 32
5 Results 33
5.1 The horizon . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
5.2 Photo balance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
5.3 Location of main object . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
5.4 Revealing line patterns and shapes . . . . . . . . . . . . . . . . . . . . . 37
5.5 Avoiding mergers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
5.6 Better photo composition by cropping . . . . . . . . . . . . . . . . . . . 37
6 Conclusion and future work 40
6.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
6.2 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
6.3 Future work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
Bibliography 44

[AS07] AVIDAN S., SHAMIR A.: Seam carving for content-aware image resizing. In
SIGGRAPH ’07: ACM SIGGRAPH 2007 papers (New York, NY, USA, 2007),
ACM, p. 10.
[BC99] BURIAN P., CAPUTO R.: National Geographic Photography Field Guide (中
譯：國家地理攝影精技), 2nd ed. National Geographic, 1999, pp. 24–33.
[BE07] BANERJEE S., EVANS B.: In-camera automation of photographic composition
rules. IEEE Trans. Image Processing 16, 7 (July 2007), 1807–1820.
[Can86] CANNY J.: A computational approach to edge detection. IEEE Trans. Pattern
Anal. Mach. Intell. 8, 6 (1986), 679–698.
[Chi02] CHIANG T. J.: Perception and Photography (觀念攝影- 影像的視覺心理
剖析). Xue Ling culture Co. (雪嶺文化), 2002, pp. 82–87.
[CXF∗03] CHEN L.-Q., XIE X., FAN X., MA W.-Y., ZHANG H., ZHOU H.-Q.: A
visual attention model for adapting images on small displays. Multimedia
Syst. 9, 4 (2003), 353–364.
[DH72] DUDA R. O., HART P. E.: Use of the hough transformation to detect lines
and curves in pictures. Commun. ACM 15, 1 (1972), 11–15.
[Hu07] HU C.-J.: A real-time skin-color-enhanced face detection algorithm. Master
thesis, Dept. of Computer Science and Information Engineering, National
Taiwan University (2007).
[IKN98] ITTI L., KOCH C., NIEBUR E.: A model of saliency-based visual attention for
rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20, 11 (1998),
1254–1259.
[Pet03] PETERSON B.: Learning to See Creatively (中譯：拍照前先學會看), revised
ed. Amphoto Books, 2003, pp. 88–129.
[SAD∗06] SANTELLA A., AGRAWALA M., DECARLO D., SALESIN D., COHEN M.:
Gaze-based interaction for semi-automatic photo cropping. In CHI ’06: Proceedings
of the SIGCHI conference on Human Factors in computing systems
(New York, NY, USA, 2006), ACM, pp. 771–780.
[SEL00] SAVAKIS A. E., ETZ S. P., LOUI A. C.: Evaluation of image appeal in consumer
photography. In Human Vision and Electronic Imaging V (June 2000),
Rogowitz B. E., Pappas T. N., (Eds.), vol. 3959 of Presented at the Society of
Photo-Optical Instrumentation Engineers (SPIE) Conference, pp. 111–120.
[SLBJ03] SUH B., LING H., BEDERSON B. B., JACOBS D. W.: Automatic thumbnail
cropping and its effectiveness. In UIST ’03: Proceedings of the 16th annual
ACM symposium on User interface software and technology (New York, NY,
USA, 2003), ACM, pp. 95–104.
[Tsa98a] TSAI M.-F.: Better Photography (攝影常犯的錯誤). Recreation Press (渡假
出版社), 1998, pp. 9–15, 17–21, 23–24, 32.
[Tsa98b] TSAI M.-F.: How to Compose a Picture (構圖的訣竅). Recreation Press (渡
假出版社), 1998, pp. 24–32, 76–88, 108–117, 131.
[Yam06] YAMAGUCHI T.: Photo Composition Determines All! Methods to Take Great
Photos (中譯：構圖決定一切！高水準攝影完全攻略). Gakken Co., 2006,
pp. 5–18.