ENHANCED SECURITY IMAGE WATERMARKING SYSTEM USING PIXEL-BASED SALIENCY MAP AND HISTOGRAM EQUALIZATION

Abstract

ABSTRACT “ENHANCED SECURITY IMAGE WATERMARKING SYSTEM USING PIXEL-BASED SALIENCY MAP AND HISTOGRAM EQUALIZATION” The present invention provides enhanced security image watermarking system using pixel-based saliency map and histogram equalization. In a digital watermarking system, this study suggested using a spatial domain histogram and a visual saliency approach. The method adds watermark content in to an image using the adaptive Alpha blending technique. In order to further ensure increased imperceptibility, a saliency map is utilized as a classifier that divides an image's characteristics according to imperceptibility based on picture color distinction. The experiment's findings demonstrate that by fusing the concepts of histogram equalization and saliency map approach together, the algorithm has better robustness, coupled with improved concealing capacity and can tolerate various visual defects. Comparing the suggested copyright protection method to some other existing algorithms reveals its superiority. Figure 1

Specification

Description:TECHNICAL FIELD
[0001] The present invention relates to the field of watermarking systems, and more particularly, the present invention relates to the enhanced security image watermarking system using pixel-based saliency map and histogram equalization.
BACKGROUND ART
[0002] The following discussion of the background of the invention is intended to facilitate an understanding of the present invention. However, it should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was published, known, or part of the common general knowledge in any jurisdiction as of the application's priority date. The details provided herein the background if belongs to any publication is taken only as a reference for describing the problems, in general terminologies or principles or both of science and technology in the associated prior art.
[0003] With the rapid increase in digital data transmission, protecting intellectual property and ensuring secure media distribution have become critical issues. Digital watermarking has emerged as a widely used technique for embedding secure, invisible markers within multimedia content to protect against unauthorized reproduction, data tampering, and copyright infringement. Existing spatial domain watermarking methods often face challenges in balancing watermark robustness, imperceptibility, and computational efficiency. Frequency domain methods provide robustness but are computationally intensive and can degrade image quality, making them unsuitable for applications requiring high perceptual quality and low computational cost.
[0004] This invention addresses these issues by presenting a digital image watermarking method that combines pixel-based saliency mapping, histogram equalization, and alpha blending in the spatial domain. The pixel-based saliency map identifies inconspicuous regions within images, allowing the system to insert watermarks in a way that minimizes visual intrusion. Histogram equalization further optimizes concealment capacity by prioritizing high-value pixels. The proposed method achieves a high level of imperceptibility while providing resilience against common attacks, such as noise addition, compression, and transformations, thus offering an effective, secure, and computationally efficient watermarking solution.
[0005] In light of the foregoing, there is a need for Enhanced security image watermarking system using pixel-based saliency map and histogram equalization that overcomes problems prevalent in the prior art associated with the traditionally available method or system, of the above-mentioned inventions that can be used with the presented disclosed technique with or without modification.
[0006] All publications herein are incorporated by reference to the same extent as if each individual publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies, and the definition of that term in the reference does not apply.
OBJECTS OF THE INVENTION
[0007] The principal object of the present invention is to overcome the disadvantages of the prior art by providing enhanced security image watermarking system using pixel-based saliency map and histogram equalization.
[0008] Another object of the present invention is to provide enhanced security image watermarking system using pixel-based saliency map and histogram equalization that provides a digital watermarking system that securely embeds watermarks within grayscale images using pixel-based saliency maps and histogram equalization to ensure high imperceptibility and robustness.
[0009] Another object of the present invention is to provide enhanced security image watermarking system using pixel-based saliency map and histogram equalization that improves watermark concealment capacity through histogram equalization, enabling the watermark to be embedded in high-value pixels with minimal perceptual impact on the original image.
[0010] Another object of the present invention is to provide enhanced security image watermarking system using pixel-based saliency map and histogram equalization that achieves a watermarking method that balances robustness and imperceptibility by employing quality metrics such as Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM) to evaluate and maintain image quality post-embedding.
[0011] Another object of the present invention is to provide enhanced security image watermarking system using pixel-based saliency map and histogram equalization that enhances resilience against intentional and accidental modifications, such as compression, scaling, and noise, using robust metrics such as Normalized Cross-Correlation (NCC) and Bit Error Rate (BER) for effective watermark integrity.
[0012] Another object of the present invention is to provide enhanced security image watermarking system using pixel-based saliency map and histogram equalization that offers a secure, efficient, and visually unobtrusive watermarking technique that provides robust copyright protection for digital images while maintaining a low computational footprint.
[0013] The foregoing and other objects of the present invention will become readily apparent upon further review of the following detailed description of the embodiments as illustrated in the accompanying drawings.
SUMMARY OF THE INVENTION
[0014] The present invention relates to enhanced security image watermarking system using pixel-based saliency map and histogram equalization.
[0015] Nowadays, processing and transmitting data takes place mostly in the digital world. Copyright protection has grown to be a serious problem in cases of data augmentation or permitted reproduction. A common method to do this is digital watermarking. Here, a pixel-based saliency map is used along with histogram equalization and alpha blending to construct a spatial domain picture watermarking strategy. Using this method, a saliency map identifies lower visible portions of the input images and progressively inserts greater quantities of information based on histogram equalization data. Any alterations made outside those observable regions will be less obvious to viewers, since they are the product of saliency, which determines which parts of a picture are the most prominent from a visual standpoint. The use of the histogram approach makes it easier to find the places in an image where we may conceal our confidential information. According to the experimental outcomes and a fast analysis using several existing frameworks, our suggested technique not only makes the information transparent into the cover object but also offers superior resilience and concealing capability.
[0016] The specifics of our watermarking method are explained in this section. This suggested work's primary goal is to enhance the productivity of watermarking by addressing the trade-off between robustness and imperceptibility. But the spatial domain approaches are more practical because they offer less processing complexity, better perceptual quality, and greater concealing ability than the more reliable frequency domain methods. In this case, a saliency map is initially acquired for the formation of the concealing capacity map by determining the prominent areas of an image. To enhance the robustness of the algorithm, a histogram equalization technique is used that locates the hiding areas inside the images. Lastly, using the alpha blending approach, a watermark is added to the cover images.
[0017] While the invention has been described and shown with reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.
BRIEF DESCRIPTION OF DRAWINGS
[0018] So that the manner in which the above-recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may have been referred by embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments.
[0019] These and other features, benefits, and advantages of the present invention will become apparent by reference to the following text figure, with like reference numbers referring to like structures across the views, wherein:
[0020] FIGURE-1 Block diagram of watermark encoder.
[0021] FIGURE-2 Block diagram of watermark decoder.
[0022] FIGURE -3 Grayscale watermark.
[0023] Figure-4 Original Images.
[0024] Figure-5 Histogram of the image.
[0025] FIGURE-6 Saliency map of original images.
[0026] FIGURE-7 Capacity calculation maps of original images.
[0027] FIGURE-8 Watermarked images.
[0028] FIGURE. 9 Performance evaluations in terms of MSE.
[0029] FIGURE. 10 Performance evaluations in terms of PSNR.
[0030] FIGURE. 11 Performance evaluations in terms of UIQI.
[0031] FIGURE. 12 Performance evaluations in terms of SSIM.
[0032] FIGURE. 13 Performance evaluations in terms of NCC.
[0033] FIGURE. 14 Performance evaluation in terms of BER against different attack;
[0034] FIGURE. 15: Recovered watermark after different attacks.
DETAILED DESCRIPTION OF THE INVENTION
[0035] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and the detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claim.
[0036] As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one" and the word "plurality" means "one or more" unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers, or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
[0037] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase "comprising", it is understood that we also contemplate the same composition, element, or group of elements with transitional phrases "consisting of", "consisting", "selected from the group of consisting of, "including", or "is" preceding the recitation of the composition, element or group of elements and vice versa.
[0038] The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, several materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
[0039] The present invention relates to enhanced security image watermarking system using pixel-based saliency map and histogram equalization.
[0040] Nowadays, processing and transmitting data takes place mostly in the digital world. Copyright protection has grown to be a serious problem in cases of data augmentation or permitted reproduction. A common method to do this is digital watermarking. Here, a pixel-based saliency map is used along with histogram equalization and alpha blending to construct a spatial domain picture watermarking strategy. Using this method, a saliency map identifies lower visible portions of the input images and progressively inserts greater quantities of information based on histogram equalization data. Any alterations made outside those observable regions will be less obvious to viewers, since they are the product of saliency, which determines which parts of a picture are the most prominent from a visual standpoint. The use of the histogram approach makes it easier to find the places in an image where we may conceal our confidential information. According to the experimental outcomes and a fast analysis using several existing frameworks, our suggested technique not only makes the information transparent into the cover object but also offers superior resilience and concealing capability.
[0041] The specifics of our watermarking method are explained in this section. This suggested work's primary goal is to enhance the productivity of watermarking by addressing the trade-off between robustness and imperceptibility. But the spatial domain approaches are more practical because they offer less processing complexity, better perceptual quality, and greater concealing ability than the more reliable frequency domain methods. In this case, a saliency map is initially acquired for the formation of the concealing capacity map by determining the prominent areas of an image. To enhance the robustness of the algorithm, a histogram equalization technique is used that locates the hiding areas inside the images. Lastly, using the alpha blending approach, a watermark is added to the cover images.
[0042] At first, the watermark is inserted into the input image by applying a saliency map on the cover image, which fully utilizes the human visual system. Then a histogram equalization technique is applied to the input image to enhance the hiding capacity. A median value is determined between and and chooses those pixels whose . Determine the capacity of the pixels using saliency and histogram . Perform the encryption operation on the watermark and obtained . At the end embed the encrypted watermark to the original image using the alpha blending technique.
Algorithm 1 Pseudo code for watermark encode algorithm
Input- Gray scale Image, Watermark
Output- Watermarked Image
Step1- Read the gray scale cover image (I) of size .
Step2- Apply the Saliency Map(p) on the input image.
Step3- Employed the Histogram Equalization ) for the input image.
Step-4- Calculate the mean M(x) value between Max H(x) and Min H(x) [where

Step-5 -Select the pixels from original image Where .
Step 6-Determine the capacity C using Saliency map(p) and .
Step 7- Read the gray scale watermark image (W) of size .
Step 8- Encrypt the watermark image (W) to .

Where is represent the encrypted watermark image and represent the cover image.
Step-9- Embed the encrypted watermark image to original image according to the capacity C using alpha blending.

[0043] Watermarks can be extracted with the help of the above decoder system. At first, the decoder system determines the capacity of the original input image as described during the watermark embedding procedure. Then perform the reverse alpha blending technique on the watermarked image ( ) according to the capacity of the selected pixel from the original image to obtain an encrypted watermark ( ). At the end, decrypt the watermark image to obtain the original watermark .
Algorithm 2 Pseudo code for watermark Decode algorithm
Input- Gray scale Image, Watermarked Image
Output- Watermark
Step1- Read the gray scale cover image (I) of size .
Step2- Apply the Saliency Map(p) on the input image.
Step3- Employed the Histogram Equalization ) for the input image.
Step-4- Calculate the mean M(x) value between Max H(x) and Min H(x) [where

Step-5 -Select the pixels from original image Where .
Step 6-Determine the capacity C using Saliency map(p) and .
Step 7- Read the watermarked image .
Step 8- Apply reverse alpha blending technique on Watermarked image ( ) according to the capacity of the selected pixel from original image I.

Step-9- Decrypt the watermark image to W.


[0044] The robustness, imperceptibility, and information concealment criteria are used in this section to describe the system's outcomes. Also, the efficiency of the proposed strategy is assessed utilizing various cutting-edge methodologies.
[0045] This method makes use of the USC-SIPI image database , a collection of basic grayscale images with a resolution of 256×256 from a common image library and a single 20 20 grayscale watermark in to taste the efficiency of the anticipated algorithm. The input images and the watermark image are shown in Figures 3 and 4. For the convenience of demonstration and confirmation of the effectiveness of the suggested strategy, there are five sample images are included in this work. To improve the ability of concealment capacity of each image, the high-range pixel values of each original grayscale image are identified by the histogram, which is shown in Figure-5. To generate the saliency map for the original grayscale images, the saliency locations were found using the approach developed in (van de Weijer et al., 2006) are mentioned in Figure 6.
[0046] The saliency map and histogram equalization approach, which was developed and is displayed in Figure 7, are used to assess the data hiding ability for every pixel in the original image. In that figure, the gray shade depicts the concealing capability of an image. Lastly, in Figure 8 we have indicated the watermarked images. Using alpha blending, the watermark is added to the original grayscale images according to the capacity evaluation. The quality of the original picture is degraded as a result of the insertion, this quality loss is measured using a variety of widely used quality criteria to assess the imperceptibility of the embedded watermarks. A bar chart, as shown below, was used to make comparisons of the original grayscale image with its corresponding watermarked image.
[0047] MSE- The MSE (Mean Square Error) value of the recommended strategy for several images is shown by the figure-9. From the given chart, it can be seen that the Mean Square Error results vary from 0.38 to 0.58, supporting a decreased probability of quality loss and providing superior results.
[0048] PSNR- For each image in the suggested technique, Figure 10 shows the PSNR (Peak Signal to Noise Ratio) value. The PSNR variation between the initial and watermarked images is between 50 and 52 dB, demonstrating that our approach has therefore acquired a greater degree of imperceptibility.
[0049] QIUI- The differences between the various original and associated watermark pictures are shown in Figure 11. The mentioned picture illustrates how all UIQI (Universal Image Quality Index) results for the suggested procedure are close to 1 (0.9997275 to 0.9999927), which represents the best outcome or the least amount of difference between the original and watermarked photos.
[0050] SSIM- The structural similarities between the watermarked and original images are fairly comparable in typical conditions, and the maximum amount of SSIM (Structural Similarity Index Measure) is 1 for both images. The structural similarity between the original image and each watermarked image for the suggested method is shown in Figure 12. In every image, the current scheme's two values are approaching one, which stands for the superiority of the recommended method.
[0051] The recommended strategy's robustness to several planned and accidental attacks, including Noise Addition, JPEG Compression, Rotation, Scaling, Translation, and others, is assessed. The outcome of the suggested strategy is generated by assessing the value of commonly used quality metrics like Bit Error Rate (BER) and Normalized Cross-Correlation (NCC) using bar charts.
[0052] NCC- The robustness of the framework is usually at an effective level if the NCC value is equal to 0.75 or above . Figure 13 shows the images' NCC values. It shows that the suggested technique produces high-quality NCC results for all photos with NCC values greater than 0.75.
[0053] BER- The bit error rate for the suggested technique is shown in Figure -14 and ranges from 0.11 to 0.52. The outcomes show that the suggested approach offers good protection against various attacks on the watermarked image.
[0054] The encrypted watermarks that have been retrieved using the suggested technique from various signal processing assaults are shown in Figure 15.
[0055] By comparing the average of five separate images, the proposed method compares it to earlier approaches. Other methods do not employ the same pictures, although having grayscale appearances in common. The watermark is kept up and is used to show the ratio so that all average results may be compared. It is evident by comparing the results of the recommended methodology to those of other methods that it obtained the best PSNR value while having a decent capacity. As a result, the recommended strategy is more undetectable and better at concealment.
[0056] Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the 5 embodiments shown along with the accompanying drawings but is to be providing the broadest scope consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention and appended claims. , Claims:CLAIMS
We Claim:
1) A digital image watermarking system using a pixel-based saliency map and histogram equalization to enhance security and robustness, the system comprises a saliency map applied to an original grayscale image to identify low-visibility areas for watermark embedding, ensuring the embedded watermark is imperceptible.
2) The system as claimed in claim 1, wherein histogram equalization is employed to determine high-value pixels within the image for improved watermark concealment capacity, further enhancing the imperceptibility and robustness of the watermark.
3) A method for embedding a digital watermark in an image, the method comprising the steps of: applying histogram equalization to identify areas with high concealment capacity, applying alpha blending to embed an encrypted watermark in the identified regions, and creating a watermarked image that resists distortion from various transformations.
4) The system as claimed in claim 1, wherein the embedded watermark quality is evaluated using a combination of Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM), ensuring low perceptual degradation with PSNR values between 50 and 52 dB and SSIM values close to 1.
5) The system as claimed in claim 1, wherein the watermarked image is resilient to intentional and accidental modifications, including noise addition, compression, and geometric transformations, achieving robust watermark integrity through high Normalized Cross-Correlation (NCC) values above 0.75 and low Bit Error Rate (BER) values between 0.11 and 0.52.

Documents