1. Source Camera Identification:
It is observed that imaging sensors inside a camera introduce sensor pattern noise (SPN) in the captured images. This SPN is generated due to the variation in the sensitivity of image sensors when exposed to light. This variation arises because of impurities in silicon wafers and imperfections introduced during the manufacturing process. Hence, all images taken by same device are overlaid by a specific sensor pattern noise. This sensor noise pattern acts as a unique and intrinsic fingerprint of the acquisition device. In this project, we have implemented and
compared of two source camera identification methods [1][2]. Both of these methods use the sensor pattern noise in identification. Only difference is that in second method[2] the extracted noise residual from sample images is enhanced to suppress the scene details. For each threshold value in range [-1, 1], the TPR of second method is always greater than that of first one and FPR is always lesser than that of first one. Hence, the ROC performance of second method is better than that of first method [1].
For more details mail to us at matlabprojects.in@gmail.com
[1]. J. Lukáš, J. Fridrich, and M.Goljan, “Digital camera identification from sensor pattern noise,” IEEE Transaction on Information Forensics and Security, vol. 1, no. 2, pp. 205–214, Jun. 2006.
[2].C.-T. Li, “Source camera identification using enhanced sensor pattern noise,”IEEE Transaction on Information Forensics and Security, vol. 5, no. 2, pp. 280–287, Jun. 2010.
2. Copy-Move Forgery Detection:
Digital image forensics (also called passive-blind image forensics), is a form of image analysis for finding out the condition of an image without relying on pre-registration or pre-embedded information. Because of the great challenge of the problem and lack of any apriori knowledge, the research should start with analyzing several simple forgery types, such as the copy-paste forgery in this project. In this project, we have implemented a blind forensics approach based on DWT (Discrete Wavelet Transform) and SVD (Singular Value Decomposition) to detect the copy-move forgery. The experimental results demonstrate that this approach can not only decrease computational complexity, but also localize the duplicated regions accurately even when the image was highly compressed or edge processed.
For more details mail to us at matlabprojects.in@gmail.com
3. Digital Image Watermarking:With the rapid growth of network multimedia systems and other numerical technologies, images, audio, text and video can be more easily produced, processed as well as stored by digital devices in recent years. To conceal data in transmitting message for copyright protection the secret is very important. Various Digital Watermarking Techniques are developed to protect the secret data. In this project we will implement a digital watermarking technique which is based on DWT, DCT and SVD. DWT has excellent spatial localization, frequency spread and multi-resolution characteristics. DCT & SVD based watermarking techniques offer compression. These desirable properties are used in this combined watermarking technique. Compared with DWT-DCT, DCT SVD, DWT-SVD based watermarking techniques; experimental results show that this algorithm is robust to various attacks such as JPEG compression, cropping, rotation, and noise.
For more details mail to us at matlabprojects.in@gmail.com
4. Digital Image Compression:
The aim of Image compression is to minimize the amount of memory needed to represent an image. Images generally require a large number of bits for their representation, and if the image needs to be transmitted or stored, it is very difficult to do so without reducing the number of bits for their representation. The problem of transmitting or storing an image affects all of us daily. TV and fax machines are both examples of image transimission, and digital video players of image storage. Image compression using DCT (Discrete Cosine Transform) in JPEG standard had been a popular technique before JPEG2000 standard came up in which DWT (Discrete Wavelet Transform) is used. For saving bandwidth of transmission, the storage requirement and in turn the cost, other more efficient compression and coding techniques are reported. Singular Value Decomposition (SVD) was also initially explored for image compression. In this project we will implement an image compression technique which is based on DWT, DCT and SVD. Compared with DWT-DCT, DCT SVD, DWT-SVD based compression techniques; experimental results show that this algorithm have higher compression ratio with optimum PSNR for optimum image quality.
For more details mail to us at matlabprojects.in@gmail.com
5. Digital Image Denoising:
Removal of noise is an important step in the image restoration process, but denoising of image remains a challenging problem in recent research associate with image processing. Denoising is used to remove the noise from corrupted image, while retaining the edges and other detailed features as much as possible. This noise gets introduced during acquisition, transmission & reception and storage & retrieval processes. In the implementation of this project, first the noisy image is decomposed by wavelet transform. After this, by using thresholding shrink decomposed images and apply adaptive wiener filter to decomposed images. Finally denoised image is obtained by using inverse wavelet transform. Experimental results on several test images are compared with Wiener Filtering. Experimental results show that this technique removes noise significantly & outperforms Wiener filtering most of the time.
For more details mail to us at matlabprojects.in@gmail.com
6. Digital Image Enhancement:
Principle objective of Image enhancement is to process an image so that result is more suitable than original image for specific application. Digital image enhancement techniques provide a multitude of choices for improving the visual quality of images. Appropriate choice of such techniques is greatly influenced by the imaging modality, task at hand and viewing conditions. The project focuses on spatial domain techniques for image enhancement, with particular reference to point processing methods and histogram processing.
For more details mail to us at matlabprojects.in@gmail.com