K. R. Ramakrishnan

A DCT domain visible watermarking technique for images

The growth of computer networks has boosted the growth of the information technology sector to a greater extent. There is a trend to move from conventional libraries to digital libraries. In digital libraries images and text are made available through the Internet for scholarly research. At the same time care is taken to prevent the unauthorized use of the images commercially. In some cases the observer is encouraged to patronize the institution that owns the material. To satisfy both these needs simultaneously the owner needs to use visible watermarking. Visible watermarking is a type of digital watermarking used for protection of publicly available images. We describe a visible watermarking scheme that is applied into the host image in the DCT domain. A mathematical model has been developed for this purpose. We also propose a modification of the algorithm to make the watermark more robust.

Adaptive visible watermarking of images

Digital watermarks are emerging as a tool to provide copyright protection for high quality images and video. Though a lot of work has been done in the area of invisible watermarks, relatively less earlier work exists for visible watermarks. As a consensus on the various issues for invisible watermarks to be legally admissible eludes us, a visible watermark could serve as a deterrence to theft and also to provide instantaneous recognition of the owner or creator of an image. We propose a technique in which the location and strength of the watermark image to be embedded is varied in accordance with the underlying content of the image to be watermarked. We propose a new algorithm that classifies each block of 8/spl times/8 of pixels into one of 8 classes depending on the sensitivity of the block to distortion. We analyze the texture, edge and luminance information in the block for this purpose. The embedding process is automated and the bits are embedded in the DCT transform domain. Since the strength of the watermark in a block depends on the class to which the block belongs, the result is a pleasant and unobtrusively watermarked image irrespective of the type of image.

A dual watermarking technique for images

Digital watermarking is the technique in which a visible/invisible signal (watermark) is embedded in a multimedia document for copyright protection. In this paper, we propose a watermarking scheme called “dual watermarking”. Dual watermark is a combination of a visible watermark and an invisible watermark,

Content based watermarking of images

With the rapid growth of networked multimedia data systems, cop~-rightProtection of proprietary multimedia work has gained importance. Inw-ting a robust and invisible signal ( tLIafermar-k) that clearly identities the owner or the recipient is beginning to emerge as the solution. We present a novel invisible and robust. watermarking technique for images that can be e&ly extended for video data. Previous wat ermarking research have only partially used the results of the human visual system (Ht7S) studies done to evaluate the JPEG quantization table. This aiso does not provide a framework for the spatial domain water-marking methods. We propose a new w’ay of analyzing the noise sensitivity of wet-y pixel bzsed on the local region image content, such as tex%ure, edge and Iumimmce information. This results in a just rwticmhle distortion mzsk for the image to be watermarked. Then each bit of the watermark is .qmacl .~atially and shaped by a pseudo-noise sequence .mch that its amplitude is kept below the noise sensitivity of the pixel into which it is embedded. It. can be either embedded in the spatial domain or can be DCT coded to be embedded in the tramform domainExperimental results show that the resistant watermark is resistant to various attacks such as JF’EG compression. cropping, addition of noise and is perceptually invisible.

Recognition of human actions using motion history information extracted from the compressed video

Human motion analysis is a recent topic of interest among the computer vision and video processing community. Research in this area is motivated by its wide range of applications such as surveillance and monitoring systems. In this paper we describe a system for recognition of various human actions from compressed video based on motion history information. We introduce the notion of quantifying the motion involved, through what we call Motion Flow History (MFH). The encoded motion information readily available in the compressed MPEG stream is used to construct the coarse Motion History Image (MHI) and the corresponding MFH. The features extracted from the static MHI and MFH compactly characterize the spatio-temporal and motion vector information of the action. Since the features are extracted from the partially decoded sparse motion data, the computational load is minimized to a great extent. The extracted features are used to train the KNN, Neural network, SVM and the Bayes classifiers for recognizing a set of seven human actions. The performance of each feature set with respect to various classifiers are analyzed. q 2003 Elsevier B.V. All rights reserved.

Robust object tracking with background-weighted local kernels

Object tracking is critical to visual surveillance, activity analysis and event/gesture recognition. The major issues to be addressed in visual tracking are illumination changes, occlusion, appearance and scale variations. In this paper, we propose a weighted fragment based approach that tackles partial occlusion. The weights are derived from the difference between the fragment and background colors. Further, a fast and yet stable model updation method is described. We also demonstrate how edge information can be merged into the mean shift framework without having to use a joint histogram. This is used for tracking objects of varying sizes. Ideas presented here are computationally simple enough to be executed in real-time and can be directly extended to a multiple object tracking system.

A design methodology for selection and placement of sensors in multimedia surveillance systems

This paper addresses the problem of how to select the optimal number of sensors and how to determine their placement in a given monitored area for multimedia surveillance systems. We propose to solve this problem by obtaining a novel performance metric in terms of a probability measure for accomplishing the task as a function of set of sensors and their placement. This measure is then used to find the optimal set. The same measure can be used to analyze the degradation in system s performance with respect to the failure of various sensors. We also build a surveillance system using the optimal set of sensors obtained based on the proposed design methodology. Experimental results show the effectiveness of the proposed design methodology in selecting the optimal set of sensors and their placement.

On Resampling Detection and its Application to Detect Image Tampering

Usually digital image forgeries are created by copy-pasting a portion of an image onto some other image. While doing so, it is often necessary to resize the pasted portion of the image to suit the sampling grid of the host image. The resampling operation changes certain characteristics of the pasted portion, which when detected serves as a clue of tampering. In this paper, we present deterministic techniques to detect resampling, and localize the portion of the image that has been tampered with. Two of the techniques are in pixel domain and two others in frequency domain. We study the efficacy of our techniques against JPEG compression and subsequent resampling of the entire tampered image

Compressed domain action classification using HMM

Abstract This paper proposes three techniques of feature extraction for person independent action classification in compressed MPEG video. The features used are extracted from motion vectors, obtained by partial decoding of the MPEG video. The feature vectors are fed to Hidden Markov Model (HMM) for classification of actions. Totally seven actions were trained with distinct HMM for classification. Recognition results of more than 90% have been achieved. This work is significant in the context of emerging MPEG-7 standard for video indexing and retrieval.

Detection of edges from projections

In a number of applications of computerized tomography, the ultimate goal is to detect and characterize objects within a cross section. Detection of edges of different contrast regions yields the required information. The problem of detecting edges from projection data is addressed. It is shown that the class of linear edge detection operators used on images can be used for detection of edges directly from projection data. This not only reduces the computational burden but also avoids the difficulties of postprocessing a reconstructed image. This is accomplished by a convolution backprojection operation. For example, with the Marr-Hildreth edge detection operator, the filtering function that is to be used on the projection data is the Radon transform of the Laplacian of the 2-D Gaussian function which is combined with the reconstruction filter. Simulation results showing the efficacy of the proposed method and a comparison with edges detected from the reconstructed image are presented.