ISSN 2249-6343

International Journal of Computer Technology and Electronics Engineering (IJCTEE)

Volume 1 , Issue 2

187

Abstract— In this paper A scene-based video watermarking

scheme is proposed, which is robust against the attacks of frame

dropping, averaging and statistical analysis, which were not

solved effectively in the past [6,7,8] . Moreover, a second

approach is proposed, which can improve the robustness of the

watermarking scheme

Index Terms—Video Water Marking, Histograms,

clustering-based cut detection scheme, scene-based

watermarking scheme.

I. INTRODUCTION

The new watermarking scheme we propose is based on

scene change analysis. In our scheme, a video and a

watermark are taken as the input, and the color binary

watermark is then decomposed into different

components(R,G,B) which are embedded in corresponding

components of frames of the original color video. As applying

a fixed image watermark to each frame in the video leads to

the problem of maintaining statistical and perceptual

invisibility [1], our scheme employs independent watermarks

for successive but different scenes. However, applying

independent watermarks to each frame also presents a

problem if regions in each video frame remain little or no

motion frame after frame. These motionless regions may be

statistically compared or averaged to remove the independent

watermarks [2]. Consequencely ,we use an identical

watermark within each motionless scene. With these

mechanisms, the proposed method is robust against the

attacks of frame dropping, averaging, swapping, and

statistical analysis. The first approach tested at Dublin was a

shot detection based on color histograms. They computed

frame-to-frame similarities based on colors which appeared

within them, albeit of the relative positions of those colors in

the frame. After computing the inter-frame similarities, a

threshold can be used to indicate shot boundaries. It needs

dynamic threshold to work on other effects than simple shot

boundaries[3].

To extract robust frame difference from consecutive

frames, we used verified x2 test which shows good

performance comparing existing histogram based algorithm

and to increase detection effect of color value subdivision

work, color histogram comparison using the weight of

brightness grade. Also to reduce the loss of spatial

information and to solve the problem for two different frames

to have similar histogram, we used local histogram

comparison.

II. PROPOSED METHODOLOGY

Color histogram comparison (d r,g,b (fi,fj)) is calculated by

histogram comparison of each color space of adjacent two

frame (fi,fj ) and it is defined as Equation (1.1)[9,10].

𝑑𝑟,g,𝑏 (𝑓𝑖 ,𝑓𝑗)= (|𝐻𝑖𝑟𝑘 −𝐻𝑗𝑟𝑘 |+ |𝐻𝑖𝑔𝑘 −𝐻𝑗𝑔k|+ |𝐻𝑖𝑏 𝑘 −𝐻𝑗𝑏 𝑘|) …(1.1)

Where 𝐻𝑖𝑟 K ,H𝑖𝑔 𝑘 ,𝐻𝑖𝑏 𝑘 represent the number (N) of

bean (k) of each color space (r,g,b) in frame fi.. Using the

weight for brightness grade change of each color space from

(1), we can redefine it as Equation (1.2).

𝑑𝑟,,( 𝑓𝑖 ,𝑓𝑗) =(| 𝐻𝑖𝑟 𝑘 −𝐻𝑗𝑟 𝑘| ×𝛼+| 𝐻𝑖𝑔 𝑘 −𝐻𝑗𝑔 𝑘|×𝛽+ |𝐻𝑖𝑏 𝑘 −𝐻𝑗𝑏 𝑘| ×𝛾) …(1.2)

α ,β ,γ shows the constants to change the brightness grade

according to NTSC standard and it is defined as α = 0.299, β =

0.587, γ = 0.114. Among static analysis method for

emphasizing the difference of two frames, X2 test comparison

(dwx2(fi , fj)) is efficient method to detect scene change by

comparison change of the histogram and it is defined as

Equation (1.3).

(1.3)

The histogram based method may have a problem to detect

two different with similar color distribution as same image as

it doesn’t use the spatial information. This problem can be

solved by the method of comparing local histogram

distribution as dividing frame area. The value of frame

difference through color histogram comparison of each area

according to the area division and its accumulation is given by

Equation (1.4)

Where,

Hi(k,bl) is the histogram distribution of k position of the

frame (fi) block(bl) and m is the number of total blocks. Using

the merits of subdivided local histogram comparison applying

weight to each color space in above Equation (1.2), value of

Video Water Marking Using Abrupt Scene

Change Detection

Kintu Patel, Mukesh Tiwari, Jaikaran Singh

ISSN 2249-6343

International Journal of Computer Technology and Electronics Engineering (IJCTEE)

Volume 1 , Issue 2

188

difference expansion using statistical method of Equation

(1.3) and use of spatial information of the frame by local

histogram as Equation (1.4),

The value of difference extraction formula, is given in

Equation (1.5) by combining above formulas, will be used for

robustness of value of difference extraction

(1.5)

In above formula, Hir (k), Hig(k), and Hib(k) is histogram

distribution of each space r, g, b owned by number i frame

where, N is total number of bean of histogram and m is the

total number of the blocks . Here, the value of difference was

created from Equation (1.5) by histogram comparison of each

block after dividing the frame into same block areas. Usually,

the performance of cut detection relies highly on frame

difference features selected to identify shot changes. Frame

differences can be defined in terms of pixel values,

histograms, motion vectors, pixel statistics, etc. Among them,

histogram difference and pixel difference between two

adjacent DC frames are the most popular features for hard cut

detection.

Histogram based comparison methods are highly preferred

because they are robust to detrimental effects such as camera

and object motion and changes in scale and rotation.

However, such methods sometimes fail to identify changes

between shots having similar color content or intensity

distribution. On the other hand, pixel-wise comparison

methods can well identify changes between shots having a

similar color content or intensity distribution, but they are

very sensitive to movements of cameras or objects. Since the

adopted pixel difference feature is extracted from DC images,

it becomes less sensitive to small object and camera motions.

However, it still is not enough for reliable shot change

detection.

To overcome the before-mentioned drawbacks of

histogram difference and pixel difference features, we

introduce a clustering-based cut detection scheme by jointly

using the two features. For their joint usage, each feature is

normalized to the values between 0 and 1 and is filtered to

remove undesirable noise. The main assumption for cut

detection is as follows:

A. Within a single shot, interframe variations are small,

which results in a slowly varying feature signal.

B. However, an abrupt change across a shot boundary

causes a sharp peak in a feature signal.

So we can detect cuts by recognizing these peaks.

However, the sensitivity of these features to camera motion,

object motion, and other noises strongly influences detection

performance. In order to remove this phenomenon, a filtering

scheme to reduce feature signal values at high activity regions

while minimizing effects on those at actual shot changes, is

needed . In this paper, we choose an unsharp masking

technique, i.e

Here, the 1-D frame difference signal d(n; n - 1) can either

be dh (n; n - 1) or dp(n; n -1). d˜(n; n - 1) denotes the low-pass

filtering and/or median filtering result of d (n; n -1), and d f

(n; n - 1) denotes the unsharp masking output, respectively.

After sequentially applying unsharp masking to both

histogram difference and pixel difference features, we obtain

the filtered signal df(n,n-1) as shown in Figure (1.1). Flow

chart for detecting the abrupt scene change in video is shown

in Figure (1.3). first of all the original video is converted in to

frames. Then each frame is decomposed in to three

components (Red, Green and Blue images).then each

component of every frame is divided in to four blocks. Now

histogram of each block is computed and find the histogram

difference between successive frame block by block wise

using equation 5.if histogram difference is greater than

threshold value scene change will detected. Independent

watermarks are embedded in frames of different scenes.

Within a motionless scene, an identical watermark is used for

each frame. As shown in Figure (1.2), watermark m1 is used

after the first scene change. When there is a scene change,

another watermark m2 is used for the next scene. Figure (1.4)

Shows 2 scene change in the video of 100 Frames.

ISSN 2249-6343

International Journal of Computer Technology and Electronics Engineering (IJCTEE)

Volume 1 , Issue 2

189

Figure 1.1.(a)Original 1-D frame difference signal

d(n,n - 1) (b) its filtered signal d f (n, n - 1). Boxes point

out the cuts.

Figure 1.2. Frames with abrupt scene change.

Figure 1.3 Flow chart for abrupt change in video

transition.

Figure 1.4 Result for video with 100 frames and 2 scene

changes.

III. SIMULATION RESULT AND ANALYSIS

In figure 1.5 we have taken 50 frames of the video and we

have found seven scene changes by local histogram

comparison and cut method(using low pass or median

filter).now we can use different watermark for these seven

scene chages and identical for other similar or minor changing

successive frames of the video So it will become robust

against the attacks. Our scheme found the perfect solution for

the video watermarking techniques in which the problem is

on which frames of video watermarking should be done as we

have shown in the results of 50 frames video.Figure 1.6 shows

the results of 50 frames and seven scene changes using

proposed method.

Figure 1.5 Different Scene Of The Original Video With

50 Frames And 7 Scene Change

ISSN 2249-6343

International Journal of Computer Technology and Electronics Engineering (IJCTEE)

Volume 1 , Issue 2

190

Figure 1.6 7 Scene Change Detection Using Block

Decomposition Method.

IV. CONCLUSION

We propose a scene-based watermarking scheme. The

scheme is robust against various attacks because we do not

require original video as well as watermarked video for

original video and watermark video recovery as we have used

blind technique for watermarking according to scene change

algorithm. Our scheme gives the perfect solution for where to

do watermarking in video thus it will become robust against

every attack.

REFERENCES

[1] Priyadarshinee Adhikari, Neeta Gargote, Jyothi Digge, and B.G.

Hogade, “Abrupt Scene Change Detection,” World Academy of

Science, Engineering and Technology 42 2008.

[2] F. Duan, I. King, L. Xu, and L. Chan, “Intra-block max min algorithm

for embedding robust digital watermark into BIBLIOGRAPHY 128

image,” In Horace H.S. Ip and Arnold W.M. Smeulders, editors,

Proceedings of the IAPR International Workshop on Multimedia

Information Analysis and Retrieval, MINAR’ 98, Lecture Notes in

Computer Science, Vol. 1464, pp. 255-264, Berlin Heidelberg,

Germany, 1998. Springer- Verlag.

[3] N. Checcacci, M. Barni, F. Bartolini, and S. Basagni, “Robust video

watermarking for wireless multimedia communications,” Proceedings

IEEEE Wireless Communications and Networking Confernce 2000,

WCNC. 2000, Vol. 3, pp. 1530-1535, 2000.

[4] P.W. Chan, M.R. Lyu, R. Chin, “Copyright Protection on the Web: A

Hybrid Digital Video Watermarking Scheme,” Poster Proceedings

13th International World Wide Web Conference (WWW’2004), pp.

354-355, New York, May 17- 22, 2004.

[5] Aditya Vashistha, Rajarathnam Nallusamy, Amitabha Das, Sanjoy

Paul SETLabs, “Watermarking Video Content Using Visual

Cryptography And Scene Averaged Image,” India.Ieee Transactions

2010, Infosys Technologies Limited 44, Electronics City, Hosur Road,

Bangalore – 560100.

[6] J. Lee And S. Jung, “A Survey Of Watermarking Techniques Applied

To Multimedia,” Proceedings 2001 Ieee International Symposium On

Industrial Electronics (Isie2001), Vol. 1, Pp. 272-277, 2001.

[7] Ren-Junn Hwang, “A digital image copyright protection scheme based

on visual cryptography,” Tamkang Journal of Science and

Engineering, vol. 3, no. 2, pp. 97–106, 2000.

[8] Amir Houmansadr and Shahrokh Ghaemmaghami, “A novel video

watermarking method using visual cryptography,” IEEE International

Conference on Engineering of Intelligent Systems, Islamabad,

Pakistan, 2006.

[9] C. F. Lam and Moon-Chuen Lee, “Video segmentation using

color difference histogram,” in MINAR ’98: Proceedings of the IAPR

International Workshop on Multimedia Information Analysis and

Retrieval, London, UK, 1998, pp. 159–174, Springer-Verlag.

[10] Boon-Luck Yeo and Bede Liu, “Rapid scene analysis on

compressed video,” IEEE Transactions on Circuits andSystems for

Video Technology, vo. 5, no. 6, pp. 533–544, Dec. 1995.