Claims:1. A hybrid image adaptive watermarking system (100) comprising:
an image sensor (102) configured to capture one or more images of interest and correspondingly generate a first set of signals ;
an encoder (106) operatively coupled to the image sensor and configured to:
extract a second from the first set of signals, wherein the second set of signals pertain to one or more segmented blocks associated with the one or more images of interest;
select at least one high entropy block from the one or more segmented blocks;
transform one or more wavelets associated with the at least one high entropy blocks, wherein the transforming facilitates obtaining high frequency coefficients and low frequency coefficients, and

embed a set of watermarked bits into a first set of wavelets from the one or more wavelets, wherein the first set of wavelets are associated with the low frequency coefficient, and wherein the embedded set of watermarked bits facilitate watermarking the one or more images.
2. The hybrid image adaptive watermarking system (100) as claimed in claim 1, wherein the system (100) includes a decoder (108) operatively coupled to the encoder (106), and wherein the decoder (108) is configured to:
receive the watermarked one or more images;
segment the one or more watermarked images into one or more blocks of pre-defined dimension;
select at least one high entropy block from the one or more segmented blocks;
transform one or more wavelets associated with the high entropy blocks, wherein the transforming facilitates obtaining high frequency coefficients and low frequency coefficients, and
extract the set of watermarked bits from the one or more wavelets, wherein the set of watermarked bits are extracted from the low frequency coefficients, and wherein the extracted set of watermarked bits facilitate decoding the watermarked one or more images.
3. The hybrid image adaptive watermarking system (100) as claimed in claim 1, wherein the encoder (106) is in communication with the decoder (108) through a communication module, and wherein the communication module facilitates transmitting the watermarked one or more images from the encoder (106) to the decoder (108).
4. The hybrid image adaptive watermarking system (100) as claimed in claim 1, wherein the system (100) include a printer (104) operatively coupled to the image sensor (102) and configured to print the captured one or more images of the interest.
5. The hybrid image adaptive watermarking system (100) as claimed in claim 1, wherein the image sensor (102) includes any or a combination of camera and scanner.
6. The hybrid image adaptive watermarking system (100) as claimed in claim 1, wherein the low frequency coefficients are configured with a Fast Walsh Hadamard Transform (FWHT), and wherein the FWHT coefficients are modeled using normal or Gaussian distribution.
7. The hybrid image adaptive watermarking system (100) as claimed in claim 6, wherein the FWHT coefficients are embedded with the set of watermark bits , and wherein the FWHT coefficients facilitates calculating hybrid strength factor (HSF).
8. A hybrid image adaptive watermarking method comprising steps of:
capturing by an image sensor (102), one or more images of interest and correspondingly generate a first set of signals ;
extracting by one or more processors of a controller (110) associated with an encoder (106) , a second from the first set of signals, wherein the second set of signals pertain to one or more segmented blocks associated with the one or more images of interest;
selecting by the one or more processors of the controller (110) associated with the encoder (106) , at least one high entropy block from the one or more segmented blocks;
sampling by the one or more processors of the controller (110) associated with the encoder (106) , one or more wavelets associated with the high entropy blocks, wherein the transforming facilitates obtaining high frequency coefficients and low frequency coefficients;
embedding by the controller (110) associated with the encoder (106), a set of watermarked bits into a first set of wavelets from the one or more wavelets, wherein the first set of wavelets are associated with the low frequency coefficients , and wherein the embedded set of watermarked bits facilitate watermarking of the one or more images;
receiving by the one or more processors of the controller (110) associated with a decoder (108), the watermarked one or more images;
segmenting by the one or more processors of the controller (110) associated with the decoder (108) , the watermarked one or more images into one or more blocks of pre-defined dimension;
selecting by the one or more processors of the controller (110) associated with the decoder (108), at least one high entropy block from the one or more segmented blocks;
transforming by the one or more processors of the controller (110) associated with the decoder (108), one or more wavelets associated with the high entropy blocks, wherein the transforming facilitates obtaining high frequency coefficients and low frequency coefficients, and
extracting by the one or more processors of the controller (110) associated with the decoder (108), the set of watermarked bits from the one or more wavelets, wherein the set of watermarked bits are extracted from the first set of wavelets from the one or more wavelets of the low frequency coefficients, and wherein the extracted set of watermarked bits facilitate decoding the watermarked one or more images.
9. The hybrid image adaptive watermarking method as claimed in claim 8, wherein the low frequency coefficients are configured with a Fast Walsh Hadamard Transform (FWHT), and wherein the FWHT coefficients are modeled using normal or Gaussian distribution.
10. The hybrid image adaptive watermarking method as claimed in claim 9, wherein the FWHT coefficients are embedded with the set of watermark bits, and wherein the FWHT coefficients facilitate calculating hybrid strength factor (HSF).

Description:TECHNICAL FIELD
[0001] The present disclosure relates generally to field of digital security. More particularly, the present disclosure provides a hybrid image adaptive watermarking system and method.

BACKGROUND
[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] Generally, image watermarking algorithms use a single watermark for copyright protection. A digital watermark is a confidential signal which can be hidden directly in a digital media such as, image, audio, video, etc. It is generally invisible and inseparable from the multimedia object and can be used to identify ownership and copyright. Desirably, a watermark should be robust, imperceptible and intolerant against changes in carrier signal under various intentional and unintentional attacks. The existing techniques have used various combinations of transforms to increase the robustness. Still approaches have failed to optimize trade-off between desirable robustness and imperceptibility.
[0004] There are various watermarking existing techniques for natural images, but limited solutions existed for image-adaptive watermarking approach. Also these solutions failed to achieve better Image Quality Assessment (IQA) parameters of watermarked images, with less security and robustness. Also, the existing solution does not prove combination of two transforms by using four hybrid strength factors and obtaining better performance parameters for image-adaptive approach.
[0005] There is a need to overcome above mentioned problem of prior art by bringing a solution that is robust and facilitates embedding watermark for images using a modifiable Hybrid Strength Factor (HSF). Also, the solution enables improving performance of the watermarked image with two transforms simultaneously.

OBJECTS OF THE PRESENT DISCLOSURE
[0006] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are as listed herein below.
[0007] It is an object of the present disclosure to provide a hybrid image adaptive watermarking system and method with two transforms simultaneously to improve performance of the watermarked image.
[0008] It is an object of the present disclosure to provide a hybrid image adaptive watermarking system and method where combination of Discrete Wavelet Transform (DWT) and Fast Walsh- Hadamard Transform (FWHT) facilitate enhancing imperceptibility and robustness of watermarked images.
[0009] It is an object of the present disclosure to provide a hybrid image adaptive watermarking system and method with statistical approach for watermark extraction using adjustable hybrid strength factors.
[0010] It is an object of the present disclosure to provide a hybrid image adaptive watermarking system and method that is robust, imperceptible and intolerant against changes in carrier signal under various intentional and unintentional attacks.

SUMMARY
[0011] The present disclosure relates generally to field of digital security. More particularly, the present disclosure provides a hybrid image adaptive watermarking system and method.
[0012] An aspect of the present disclosure pertains to an image adaptive watermarking system. The image adaptive watermarking system may include an image sensor, an encoder, and a decoder. The image sensor may be configured to capture one or more images of interest and correspondingly generate a first set of signals. The encoder may be operatively coupled to the image sensor and configured to extract a second from the first set of signals, where the second set of signals may pertain to one or more segmented blocks associated with the one or more images of interest. The encoder may be configured to select at least one high entropy block from the one or more segmented blocks, transform one or more wavelets associated with the at least one high entropy blocks, where the transforming may facilitate obtaining high frequency coefficients and low frequency coefficients. The encoder may be configured to embed a set of watermark bits into a first set of wavelets from the one or more wavelets, where the first set of wavelets may be associated with the low frequency coefficient, and where the embedded set of watermark bits facilitate watermarking of the one or more images.
[0013] In an aspect, the image adaptive watermarking system may include a decoder operatively coupled to the encoder, and where the decoder may be configured to receive the watermarked one or more images. The decoder may be configured to segment the one or more watermarked images into one or more blocks of pre-defined dimension, select at least one high entropy block from the one or more segmented blocks, transform one or more wavelets associated with the at least one high entropy block, where the transforming may facilitate obtaining high frequency coefficients and low frequency coefficients, and extract the set of watermarked bits from the one or more wavelets, where the set of watermark bits may be extracted from the low frequency coefficients, and where the extracted set of watermark bits facilitate decoding the watermarked one or more images.
[0014] In an aspect, the encoder may be in communication with the decoder through a communication module, and where the communication module may facilitate transmitting the watermarked one or more images from the encoder to the decoder.
[0015] In an aspect, the image adaptive watermarking system may include a printer operatively coupled to the image sensor and configured to print the captured one or more images of the interest.
[0016] In an aspect, the image sensor may include any or a combination of camera and scanner.
[0017] In an aspect, the low frequency coefficient may be configured with a Fast Walsh Hadamard Transform (FWHT), and where the FWHT coefficient may be modeled using normal or Gaussian distribution.
[0018] In an aspect, the FWHT coefficient may be embedded with the set of watermark bits, and where the FWHT coefficient may facilitate calculating hybrid strength factor (HSF).
[0019] Another aspect of the present disclosure pertains to an image adaptive watermarking method including steps of capturing by an image sensor, one or more images of interest and correspondingly generate a first set of signals. The method may include a step of extracting by one or more processors of a controller associated with an encoder, a second set of signals from the first set of signals, where the second set of signals may pertain to one or more segmented blocks associated with the one or more images of interest. The method may include a step of selecting by the one or more processors of the controller associated with the encoder, at least one high entropy block from the one or more segmented blocks, transforming by the one or more processors of the controller associated with the encoder, one or more wavelets associated with the at least one high entropy block, where the transforming may facilitate obtaining high frequency coefficients and low frequency coefficients. The method may include a step of embedding by the one or more processors of the controller associated with the encoder, a set of watermark bits into a first set of wavelets from the one or more wavelets, where the first set of wavelets may be associated with the low frequency coefficients, and where the embedded set of watermark bits facilitate watermarking of the one or more images. The method may include a step of receiving by the one or more processors of the controller associated with the decoder , the watermarked one or more images, segmenting by the one or more processors of the controller associated with the decoder , the watermarked one or more images into one or more blocks of pre-defined dimension, selecting by the one or more processors of the controller associated with the decoder, at least one high entropy block from the one or more segmented blocks, and transforming by the one or more processors of the controller associated with the decoder , one or more wavelets associated with the at least one high entropy block, where the transforming facilitates obtaining high frequency coefficients and low frequency coefficients. The method may include a step of extracting by the one or more processors of the controller associated with the decoder, the set of watermarked bits from the one or more wavelets, where the set of watermarked bits are extracted from the first set of wavelets from the one or more wavelets of the low frequency coefficients, and where the extracted set of watermark bits facilitate decoding watermarked one or more images.
[0020] In an aspect, the low frequency coefficient may be configured with a Fast Walsh Hadamard Transform (FWHT), and where the FWHT coefficient may be modeled using normal or Gaussian distribution.
[0021] In an aspect, the FWHT coefficient may be embedded with the set of watermark bits, and where the FWHT coefficient may facilitate calculating hybrid strength factor (HSF).

BRIEF DESCRIPTION OF THE DRAWINGS
[0022] The accompanying drawings are included to provide a further understanding of the present disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0023] The diagrams are for illustration only, which thus is not a limitation of the present disclosure, and wherein:
[0024] FIG. 1 illustrates a block diagram of proposed hybrid image adaptive watermarking system, in accordance with an embodiment of the present disclosure.
[0025] FIG. 2 illustrates exemplary functional components of controller of the proposed hybrid image adaptive watermarking system, in accordance with an embodiment of the present disclosure.
[0026] FIG. 3A illustrate an exemplary view of process of embedding watermark of the proposed hybrid image adaptive watermarking system, in accordance with an embodiment of the present disclosure.
[0027] FIG. 3B illustrate an exemplary view of process of decoding watermark of the proposed hybrid image adaptive watermarking system, in accordance with an embodiment of the present disclosure.
[0028] FIG. 4 illustrates a flow diagram illustrating a proposed hybrid image adaptive watermarking method, in accordance with embodiments of the present disclosure.

DETAIL DESCRIPTION
[0029] In the following description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent to one skilled in the art that embodiments of the present invention may be practiced without some of these specific details.
[0030] Embodiments of the present invention include various steps, which will be described below. The steps may be performed by hardware components or may be embodied in machine-executable instructions, which may be used to cause a general-purpose or special-purpose processor programmed with the instructions to perform the steps. Alternatively, steps may be performed by a combination of hardware, software, firmware and/or by human operators.
[0031] If the specification states a component or feature “may”, “can”, “could”, or “might” be included or have a characteristic, that particular component or feature is not required to be included or have the characteristic.
[0032] As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context clearly dictates otherwise.
[0033] While embodiments of the present invention have been illustrated and described, it will be clear that the invention is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the spirit and scope of the invention, as described in the claim.
[0034] The present disclosure relates generally to field of digital security. More particularly, the present disclosure provides a hybrid image adaptive watermarking system and method.
[0035] FIG. 1 illustrates a block diagram of proposed hybrid image adaptive watermarking system, in accordance with an embodiment of the present disclosure.
[0036] As illustrated in FIG. 1, the proposed image adaptive watermarking system (100) (also referred to as system (100), herein) can include an image sensor (102), a printer (104), an encoder (106), a decoder (108), and a controller (110). In an embodiment, the system (100) can facilitate hybrid image adaptive watermarking of one or more images of interest by embedding set of watermark bits and recovering watermarked one or more images. In another embodiment, the image sensor (102) can be operatively coupled to the printer (104) and the encoder (106). In yet another embodiment, the encoder (106) can be in communication with the decoder (108) through a communication module.
[0037] In an embodiment, the image sensor (102) can be configured to capture one or more images of interest and correspondingly generate a first set of signals. In an illustrative embodiment, the image sensor (102) can include any or a combination of scanner, camera, and the likes. In an illustrative embodiment, the images can be in digital form, where the first set of signals can be transmitted to the encoder (106). In another illustrative embodiment, the image sensor (102) can be configured to capture the one or more images of interest and generate the first set of signals, where the first set of signals can be transmitted to a printer (104).
[0038] In an embodiment, the printer (104) can be configured to print captured one or more images, where the captured one or more images are captured by the image sensor (102).
[0039] In an illustrative embodiment, the encoder (104) can be configured to extract a second from the first set of signals, where the second set of signals can pertain to one or more segmented blocks associated with the one or more images of interest. the encoder (104) can be configured to select at least one high entropy block from the one or more segmented blocks, transform one or more wavelets associated with the high entropy blocks, where the transforming facilitates obtaining high frequency coefficients and low frequency coefficients, and embed a set of watermarked bits into a first set of wavelets from the one or more wavelets, where the first set of wavelets can be associated with the low frequency coefficient, and where the embedded set of watermarked bits can facilitate watermarking the one or more images.
[0040] In an embodiment, the decoder (106) can be configured to receive the watermarked one or more images. The decoder (106) can be configured to segment the one or more watermarked images into one or more blocks of pre-defined dimension, where the pre-defined dimension of each of the one or more blocks can be 8×8, but not limited to the likes. In another embodiment, the decoder (106) can be configured to select at least one high entropy block from the one or more segmented blocks. The decoder (106) can be configured to sample one or more wavelets associated with the high entropy blocks, where the transforming can facilitate obtaining high frequency coefficients and low frequency coefficients. In yet another embodiment, the decoder (106) can be configured to extract the set of watermark bits from the one or more wavelets, where the set of watermark bits can be extracted from the low frequency coefficients, and where the extracted set of watermark bits can facilitate decrypting the watermarked one or more images.
[0041] In an illustrative embodiment, the controller (110) can be associated with the encoder (104) and the decoder (108), where the controller (110) can be operatively coupled to the encoder (104) and the decoder (106). In another illustrative embodiment, the controller (110) can be configured to segment the one or more images into one or more blocks of pre-defined dimension like 8×8 , but not limited to the likes. The controller (110) can be configured to select the at least one high entropy block from the one or more segmented blocks and transform the one or more wavelets associated with the at least one high entropy blocks through discrete wavelet transform (DWT), but not limited to the likes.
[0042] In an illustrative embodiment, the controller (110) can be configured with MATLAB, but not limited to the likes. In another illustrative embodiment, the controller (110) can be any or a combination of microprocessor, microcontroller, Intel(R) Core(TM ) i5 CPU Processor, Arduino Uno, At mega 328, other similar processing unit, and the likes.
[0043] In an illustrative embodiment, the DWT on the at least one high entropy block can facilitate obtaining high frequency coefficients and the low frequency coefficients like Low Low (LL), Low High (LH), High Low (HL), and High High (HH). In another illustrative embodiment, the low frequency coefficients like LL can be configured with a Fast Walsh Hadamard Transform (FWHT), and where the FWHT coefficient can be modeled using normal or Gaussian distribution. In yet another illustrative embodiment, the FWHT coefficient can be embedded with the set of watermark bits, and where the FWHT coefficient can facilitate calculating hybrid strength factor (HSF).
[0044] In an illustrative embodiment, the FWHT coefficient (W) can be modeled using Normal (or Gaussian) distribution, and where the HSF can be calculated using transformed LL coefficient. In another illustrative embodiment, the controller (110) can be configured to embed the set of watermark bits into W coefficient and prepare side information for the low coefficients and the at least one high entropy block. The embedded set of watermark bits associated with the low coefficients can be configured with inverse DWT (IDWT) and inverse FWHT (IFWHT) and the one or more segmented blocks can be combined to obtain watermarked one or more images. The watermarked one or more images can be transmitted to the decoder (108).
[0045] In an illustrative embodiment, the controller (110) associated with the decoder (108) can be configured to receive the watermarked one or more images. The decoder (108) can be configured to segment the received watermarked one or more images into the one or more blocks of pre-defined dimension like 8×8 blocks. In another illustrative embodiment, the controller (110) can be configured to select the at least one high entropy block from the one or more segmented blocks, where the at least one high entropy blocks can be configured with DWT to obtain LL frequency coefficient, LH frequency coefficient, HL frequency coefficient and HH frequency coefficient respectively. The LL frequency coefficient can be configured with the FWHT, where the FWHT coefficient (W) can be modeled using Normal (or Gaussian) distribution parameters, but not limited to the likes. In yet another illustrative embodiment, statistical modeling of a Maximum likelihood decoder (ML) can facilitate extraction of the set of watermarked bits from the watermarked one or more images and enables decoding of the set of watermarked bits.
[0046] FIG. 2 illustrates exemplary functional components of controller of the proposed hybrid image adaptive watermarking system, in accordance with an embodiment of the present disclosure.
[0047] As illustrated in an embodiment, the controller (110) can include one or more processor(s) 202. The one or more processor(s) 202 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the one or more processor(s) 202 are configured to fetch and execute computer-readable instructions stored in a memory 204 of the controller (110). The memory 204 can store one or more computer-readable instructions or routines, which may be fetched and executed to create or share the data units over a network service. The memory 204 can include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the like.
[0048] In an embodiment, the controller (110) can also include an interface(s) 206. The interface(s) 206 may include a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) 306 may facilitate communication of the controller (110) with various devices coupled to the controller (110). The interface(s) 206 may also provide a communication pathway for one or more components of controller (110). Examples of such components include, but are not limited to, processing engine(s) 208 and data 210.
[0049] In an embodiment, the processing engine(s) 208 can be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) 208. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) 208 may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing engine(s) 208 may include a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) 208. In such examples, the controller (110) can include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to controller (110) and the processing resource. In other examples, the processing engine(s) 208 may be implemented by electronic circuitry. A database 210 can include data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) 208.
[0050] In an embodiment, the processing engine(s) 208 can include an extraction unit (212), a selection unit (214), a transforming unit (216), embedding unit (218), segmenting unit (220), other unit(s) (222). The other unit(s) (222) can implement functionalities that supplement applications or functions performed by the system (100) or the processing engine(s) (208).
[0051] The database (210) can include data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) (208).
[0052] It would be appreciated that units being described are only exemplary units and any other unit or sub-unit may be included as part of the system (100). These units too may be merged or divided into super- units or sub-units as may be configured.
[0053] As illustrated in FIG. 2, the controller (110) can be configured with an encoder (106) and a decoder (108), where the controller (110) can be configured to receive one or more captured images from an image sensor (102) in digital form. In an embodiment, the controller (110) can be configured to extract a second set of signals from a first set of signals with help of the extraction unit (212), where the first set of signals are generated by the image sensor (102). The second set of signals can pertain to one or more segmented blocks of predetermined dimension from the one or more captured images of interest. In another embodiment, the controller (110) can be configured to select at least one high entropy block from the one or more segmented blocks with help of the selection unit (214). The controller (110) can be configured to transform one or more wavelets associated with the at least one high entropy block with help of the transforming unit (216). In yet another embodiment, the controller (110) can be configured to embed a set of watermarked bits into a first set of wavelets from the one or more wavelets with help of the embedding unit (218).
[0054] In an embodiment, the extraction unit (212) can be configured to receive the one or more captured images of interest from the image sensor (102) in digital form. The extraction unit (212) can be configured to extract the second set of signals in machine readable form or binary form and transmit the second set of signals to the selection unit. In an illustrative embodiment, the extraction unit (212) can facilitate extracting one or more segmented blocks of the pre-determined dimension like 8×8 blocks, but not limited to the likes from the one or more captured images of interest.
[0055] In an embodiment, the selection unit (214) can be configured to receive the one or more segmented blocks from the extraction unit (212) in machine readable form or digital form, where the selection unit (214) can facilitate selecting the at least one high entropy block from the one or more segmented blocks and also enable obtaining side information for the at least one high entropy block. In another embodiment, the selection unit (214) can be configured to transmit the selected at least one high entropy block to the transforming unit (216).
[0056] In an embodiment, the transforming unit (216) can be configured to transform the one or more wavelets associated with the high entropy blocks, where the transforming can facilitate obtaining high frequency coefficients and low frequency coefficients, where the high frequency coefficients and the low frequency coefficients can include Low Low (LL), Low High (LH), High Low (HL), and High High (HH). In an illustrative embodiment, the transforming can include discrete wavelet transform (DWT), where the DWT can facilitate selecting low frequency coefficients, and where the low frequency coefficients like LL can be configured with Fast Walsh Hadamard Transform (FWHT). In an illustrative embodiment, the transforming unit (216) can be configured to transmit the transformed one or more wavelets to the other unit(s) (222), where the other unit(s) (222) can include a calculation unit, combination unit and the likes.
[0057] In an illustrative embodiment, the calculation unit can be configured to receive the transformed one or more wavelets and facilitate calculation of mean and variance of the low frequency coefficient and hybrid strength factor (HSF).
[0058] In an embodiment, the embedding unit (218) can be configured to embed the set of watermarked bits into the first set of wavelets from the one or more wavelets, where the first set of wavelets can pertain to low frequency coefficients. In another embodiment, the embedded set of watermark can be transformed through inverse (DWT) and inverse (FWHT) and after the inverse transforming, the embedded set of watermarked bits can be transmitted to the combination unit.
[0059] In an illustrative embodiment, the combination unit can be configured to combine the one or more segmented blocks of the pre-determined dimension and facilitate obtaining watermarked one or more images.
[0060] In an embodiment, the watermarked one or more images can be received by the controller (110) associated with the decoder (106), where the controller (110) can be configured to segment the watermarked one or more images into one or more blocks of pre-defined dimension with help of the segmenting unit (220). In another embodiment, the controller (110) associated with the decoder (106) can be configured to select at least one high entropy block from the one or more segmented blocks with help of the selection unit (216). In yet another embodiment, the controller (110) associated with the decoder (106) can be configured to transform one or more wavelets associated with the at least one high entropy block with help of the transforming unit (218), where the transforming facilitates obtaining high frequency coefficients and low frequency coefficients. The controller (110) associated with the decoder (106) can be configured to extract the set of watermarked bits from the one or more wavelets with help of the extraction unit (212).
[0061] In an illustrative embodiment, the segmenting unit (220) can be configured to receive the watermarked one or more images from the encoder (104) in digital form, where the segmenting unit (220) can be configured to segment the watermarked one or more images into one or more blocks of the pre-defined dimension like 8×8 blocks. In another illustrative embodiment, the segmented one or more blocks can be transmitted to the selection unit (214) in machine readable form or binary form.
[0062] In an illustrative embodiment, the selection unit (214) can be configured to receive the one or more segmented blocks from the segmenting unit (220) and facilitate selecting at least one high entropy block from the one or more segmented blocks, where the selected at least one high entropy block can be transmitted to the transforming unit (216). In another illustrative embodiment, the transforming unit (216) can be configured to transform the one or more wavelets associated with the at least one high entropy block, where the transforming can facilitate obtaining high frequency coefficients and low frequency coefficients like Low Low (LL), Low High (LH), High Low (HL), and High High (HH), but not limited to the likes.
[0063] In an illustrative embodiment, the transforming unit (216) can transform the one or more wavelets through the DWT, and enable selecting the low frequency coefficients like LL, but not limited to the likes, and where the low frequency coefficients can be configured with the FWHT. In another illustrative embodiment, the transforming unit (216) can be configured to transmit the FWHT sampled one or more wavelets to the extraction unit (212). In yet another illustrative embodiment, the extraction unit (212) can be configured to receive the FWHT sampled one or more wavelets, where the extraction unit (212) can be configured to extract the set of watermarked bits from the one or more wavelets, where the set of watermarked bits can be extracted from the low frequency coefficients, and where the extracted set of watermarked bits can facilitate decoding the watermarked one or more images.
[0064] In an illustrative embodiment, the extraction of the set of watermarked bits can be done with help of maximum likelihood decoder, but not limited to the likes.
[0065] In an illustrative embodiment, the controller (108) associated with the encoder (106) and the decoder (108) can be same, where the controller (108) can include one or more processing engines (208), where the one or more processing engines (208) associated with the encoder (106) and the decoder (108) can be different.
[0066] FIG. 3A illustrate an exemplary view of process of embedding watermark of the proposed hybrid image adaptive watermarking system, in accordance with an embodiment of the present disclosure.
[0067] As illustrated in FIG. 3A, the one or more images of interest captured by an image sensor (102) can be transmitted to a controller (110) associated with an encoder (106) as shown in block (302). In an embodiment, the controller (110) associated with the encoder (106) can be configured to segment the one or more images of interest into one or more blocks of pre-defined size like 8×8 blocks as shown in block (304). The controller (110) associated with the encoder (106) can be configured to select at least one high entropy block from the one or more segmented blocks as shown in block (306). In another embodiment, the controller (110) can be configured to transform the selected at least one high entropy block with discrete wavelet transform (DWT) as shown in block (308) and facilitate obtaining high frequency coefficients and low frequency coefficients , where the low frequency coefficients are selected and configured with Fast Walsh-Hadamard Transform (FWHT) as shown in block (310) and (312), where the controller (110) associated with the encoder (106) can be configured to calculate means and variance of low frequency coefficients and hybrid strength factor (HSF) as shown in block (316) and (318).
[0068] In an illustrative embodiment, the controller (110) associated with the encoder (106) can be configured to embed a set of watermarked bits as shown in block (314). The controller (110) associated with the encoder (106) can be configured to perform inverse FWHT and inverse DWT as shown in block (320) and (322) and facilitate combining the one or more segmented blocks of pre-defined size like 8×8 blocks, but not limited to the likes as shown in block (324) and enable obtaining watermarked one or more images as shown in block (326). In another illustrative embodiment, the controller (110) associated with the encoder (106) can be configured to obtain side information as shown in block (342), after the selection of the at least one high entropy block from the one or more segmented blocks as shown in block (306). The controller (110) associated with the encoder (106) can be configured to obtain side information as shown in block (342) after calculating the mean and variance of the low frequency coefficients as shown in block (316).
[0069] FIG. 3B illustrate an exemplary view of process of decoding watermark of the proposed hybrid image adaptive watermarking system , in accordance with an embodiment of the present disclosure.
[0070] As illustrated in FIG. 3B, the watermarked one or more images can be transmitted to the controller (110) associated with the decoder (108) from the controller (110) associated with the encoder (106). In an embodiment, the controller (110) associated with the decoder (108) can be configured to segment the watermarked one or more images into one or more blocks of pre-defined dimension like 8×8 blocks, but not limited to the likes as shown in block (328). In another embodiment, the controller (110) associated with the decoder (108) can be configured to select at least one high entropy block from the one or more segmented blocks as shown in block (330).
[0071] In an illustrative embodiment, the controller (110) associated with the decoder (108) can be configured to transform one or more wavelets associated with the at least one high entropy blocks, where the transforming facilitate obtaining high frequency coefficients and low frequency coefficients , were the transforming can be done through Discrete Wavelet Transform (DWT) as shown in block (332), and where the controller (110) associated with the decoder (108) can facilitate selecting the low frequency coefficients as shown in block (334), where the low frequency coefficients can be configured with Fast Walsh-Hadamard Transform (FWHT) as shown in block (336). In another illustrative embodiment, the controller (110) associated with the decoder (108) can be configured to extract a set of watermarked bits from the one or more wavelets, where the set of watermarked bits can be extracted from the low frequency coefficients, where the extracted set of watermarked bits can facilitate decoding the watermarked one or more images, and where the extraction of the set of watermarked bits can be done using maximum likelihood (ML) decoder , but not limited to the likes as shown in block (338) and (340). In yet another illustrative embodiment, the controller (110) associated with the decoder (108) can be configured to transmit side information as shown in block (342) while selecting of the at least one high entropy block from the one or more segmented blocks as shown in block (330) and to the ML decoder while extracting the set of watermarked bits as shown in block (338).
[0072] FIG. 4 illustrates a flow diagram illustrating a proposed hybrid image adaptive watermarking method, in accordance with embodiments of the present disclosure.
[0073] As illustrated in FIG. 4, the method can include a step (402) of capturing by an image sensor, one or more images of interest and correspondingly generate a first set of signals.
[0074] In an embodiment, the method can include a step (404) of extracting by one or more processors of a controller associated with an encoder (106) , a second from the first set of signals, where the second set of signals can pertain to one or more segmented blocks associated with the one or more images of interest.
[0075] In an embodiment, the method can include a step (406) of selecting by the one or more processors of the controller (110) associated with the encoder (106) at least one high entropy block from the one or more segmented blocks.
[0076] In an embodiment, the method can include a step (408) of transforming by the one or more processors of the controller (110) , one or more wavelets associated with the at least one high entropy block, where the transforming can facilitate obtaining high frequency coefficients and low frequency coefficients.
[0077] In an embodiment, the method can include a step (410) of embedding by the one or more processors of the controller (110), a set of watermarked bits into a first set of wavelets from the one or more wavelets, where the first set of wavelets can be associated with the low frequency coefficients, and where the embedded set of watermarked bits can facilitate watermarking of the one or more images.
[0078] In an embodiment, the method can include a step (412) of receiving by the one or more processors of the controller (110) associated with a decoder (108), the watermarked one or more images.
[0079] In an embodiment, the method can include a step (414) of segmenting by the one or more processors of the controller (110) associated with the decoder (108), the watermarked one or more images into one or more blocks of pre-defined dimension.
[0080] In an embodiment, the method can include a step (416) of selecting by the one or more processors of the controller (110) associated with the decoder (108), at least one high entropy block from the one or more segmented blocks.
[0081] In an embodiment, the method can include a step (418) of transforming by the one or more processors of the controller associated with the decoder (108) , one or more wavelets associated with the at least one high entropy block, where the transformation can facilitate obtaining high frequency coefficients and low frequency coefficients.
[0082] In an embodiment, the method can include a step (420) of extracting by the by one or more processors of the controller associated with the decoder, the set of watermarked bits from the one or more wavelets, where the set of watermarked bits can be extracted from the first set of wavelets from the one or more wavelets of the low frequency coefficients, and where the extracted set of watermarked bits can facilitate decoding the watermarked one or more images.
[0083] As used herein, and unless the context dictates otherwise, the term "coupled to" is intended to include both direct coupling (in which two elements that are coupled to each other contact each other) and indirect coupling (in which at least one additional element is located between the two elements). Therefore, the terms "coupled to" and "coupled with" are used synonymously. Within the context of this document terms "coupled to" and "coupled with" are also used euphemistically to mean “communicatively coupled with” over a network, where two or more devices are able to exchange data with each other over the network, possibly via one or more intermediary device.
[0084] It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, ` components, or steps that are not expressly referenced.
[0085] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.

ADVANTAGES OF THE PRESENT DISCLOSURE
[0086] The present disclosure provides a hybrid image adaptive watermarking system and method with two transforms simultaneously to improve performance of the watermarked image.
[0087] The present disclosure provides a hybrid image adaptive watermarking system and method where combination of Discrete Wavelet Transform (DWT) and Fast Walsh Hadamard Transform (FWHT) facilitate enhancing imperceptibility and robustness of watermarked images.
[0088] The present disclosure provides a hybrid image adaptive watermarking system and method with statistical approach for watermark extraction using adjustable hybrid strength factors.
[0089] The present disclosure provides a hybrid image adaptive watermarking system and method that is robust, imperceptible and intolerant against changes in carrier signal under various intentional and unintentional attacks.