Avinash G. Keskar

Copy move forgery detection using DWT and SIFT features

Powerful image editing tools like Adobe Photoshop etc. are very common these days. However due to such tools tampering of images has become very easy. Such tampering with digital images is known as image forgery. The most common type of digital image forgery is known as copy-move forgery wherein a part of image is cut/copied and pasted in another area of the same image. The aim behind this type of forgery may be to hide some particularly important details in the image. A method has been proposed to detect copy-move forgery in images. We have developed an algorithm of image-tamper detection based on the Discrete Wavelet Transform i.e. DWT. DWT is used for dimension reduction, which in turn increases the accuracy of results. First DWT is applied on a given image to decompose it into four parts LL, LH, HL, and HH. Since LL part contains most of the information, SIFT is applied on LL part only to extract the key features and find descriptor vector of these key features and then find similarities between various descriptor vectors to conclude that the given image is forged. This method allows us to detect whether image forgery has occurred or not and also localizes the forgery i.e. it tells us visually where the copy-move forgery has occurred.

A Copy Move Forgery Detection to Overcome Sustained Attacks Using Dyadic Wavelet Transform and SIFT Methods

In the present digital world integrity and trustworthiness of the digital images is an important issue. And most probably copy- move forgery is used to tamper the digital images. Thus as a solution to this problem, through this paper we proposes a unique and blind method for detecting copy-move forgery using dyadic wavelet transform DyWT in combination with scale invariant feature transform SIFT. First we applied DyWT on a given test image to decompose it into four sub-bands LL, LH, HL, HH. Out of these four sub-bands LL band contains most of the information we intended to apply SIFT on LL part only to extract the key features and using these key features we obtained descriptor vector and then went on finding similarities between various descriptors vector to come to a decision that there has been some copy-move tampering done to the given image. In this paper, we have done a comparative study based on the methods like a.DyWT b.DWT and SIFT c. DyWT and SIFT. Since DyWT is invariant to shift whereas discrete wavelet transform DWT is not, thus DyWT is more accurate in analysis of data. And it is shown that by using DyWT with SIFT we are able to extract more numbers of key points that are matched and thus able to detect copy-move forgery more efficiently.

Video encoding techniques based on 3D-DWT

This paper deals with the application of Spatial and Temporal DWT (Discrete Wavelet transform) on the videos. Here we will discuss about three mechanisms and their performance on videos at increased DWT level. In any video processing algorithm, memory is the major criteria. In these three mechanisms dynamic (automatic) DWT level selection and manual level selection is implemented. Here we will also discuss about implementation of different DWT level in spatial and temporal domain. In this paper Haar wavelet is taken as the reference as it has its inherent properties and ease of implementation.

Design of Eight Bit Novel Reversible Arithmetic and Logic Unit

Digital circuits made up of classical gates dissipate significant amount of energy as bits are erased during logic operations. Use of reversible logic gates to implement such circuits can significantly reduce the power consumed. This paper covers various aspects about reversible computing and reversible logic gates. Furthermore in this paper we have tried to design a reversible implementation of eight bit arithmetic and logic unit, optimal in terms of number of gates used and number of garbage outputs produced.

A copy-move image forgery detection based on speeded up robust feature transform and Wavelet Transforms

We are currently leaving in a pure digital world where all type of information is mostly stored in digital form. Thus storage of the information is no more a problem and the information can be easily passed on from one place to another in digital format. The big benefit however comes with the hidden loss and in this case it is the tampering of images and videos which has become a matter of serious concern in recent days because of the readily available software tools in the market like Photoshop etc. which can be used by a common person to tamper the image or video for hiding or changing the original contents. Thus for the aforementioned problem, we in this paper propose a series of algorithms which are combination of speeded-up robust feature transforms and Wavelet Transforms. In doing so we will first discuss Speeded-Up Robust Feature (SURF), SURF in combination with Discrete Wavelet Transform (DWT), SURF in combination with Dyadic Wavelet Transform (DyWT). These algorithms are different from the previously proposed algorithm in the manner that they are applied on the entire image to extract features rather than dividing the image into the blocks. From the results obtained we are able to conclude the proposed algorithms are better than their counterparts both in terms of computational complexity and invariance to scale and rotation and also for the combination of attacks.

Analysis and monitoring of a high density traffic flow at T-intersection using statistical computer vision based approach

A reliable traffic flow monitoring and traffic analysis approach using computer vision techniques has been proposed in this paper. The exponential increase in traffic density at urban intersections in the past few decades has raised precious and challenging demands to computer vision algorithms and technological solutions. The focus of this paper is to suggest a statistical based approach to determine the traffic parameters at heavily crowded urban intersections. The algorithm in addition to accurate tracking and counting of freeway traffic also offers high efficiency for determining vehicle count at a high traffic density T-intersection. The system uses Intel Open CV library for image processing. The implementation of algorithm is done using C++. The real time video sequence is obtained from a stationary camera placed atop a high building overlooking the particular T intersection. This paper suggests a dynamic method where each vehicle at a T intersection is passed through a number of detection zones and the final count of vehicles is derived from a statistical equation.

A novel approach based on variance for local feature analysis of facial images

A low dimensional representation of sensory signals is a key for solving many of the computational problems encountered in high level vision. In this paper, a comparison of face recognition techniques using principal component analysis (PCA) is done with local feature analysis (LFA) and an alternate method based on variance for quickly finding the local feature points on face images is also proposed. The LFA method is an extension of the eigenfaces method and gives a low-dimensional output for face representation. Principal component analysis (PCA) that is used for dimensionality reduction in the eigenfaces technique leads to global outputs, which are non-topographic and are not biologically plausible. On the other hand, the local feature analysis (LFA) technique yields local, topographic outputs which are sparsely distributed. They are effectively low dimensional but retain all the characteristics of the global modes. Local representations are desirable since they offer robustness against variability due to changes in the localised regions of the objects. A strategy for recognising faces using LFA is also proposed and several results on reconstruction and recognition are given to compare the performance of the variance method with that of LFA and PCA.

Vehicle Classification and Communication Using Zigbee Protocol

The innovation in wireless technology is to support in the areas of Intelligent Transport System (ITS). Wireless technology can be used in Vehicle-to-Vehicle and vehicle-to-infrastructure in transport applications. ZigBee is the key protocol for sensor network applications because of the long battery life, low-cost for installation, eases maintenance and small footprint. ZigBee enables mesh networking which supports a wireless communication between many coordinators, routers and receivers in environments where multiple applications are being monitored. The mesh network is ideal and self configured, also automatically self correct and is typically used in the internet by telephone network companies. This paper is about the study of ZigBee protocol role, mainly in the interconnection of infrared sensor with vehicles and infrastructure for classification of vehicles and further communicating the information to other intersections.

Design of Dynamic Synapse Circuits with VLSI Design Approach

Dynamic properties of neural networks using dynamic neuron can be implemented with the analog dynamic synapse. The proposed circuit has few CMOS transistors but imitates well the dynamic properties of depressing synapses. Dynamical synapse increases the computational power of the neuronal network. An approach towards design of depressing synapse is presented in this paper towards achieving excitatory and inhibitory postsynaptic potential. This is achieved just by means of adjusting control voltages. In this paper a model of a depressing synapse circuit is presented. This synapse can be classified into excitatory and inhibitory synapse depending upon the charging and discharging of the membrane potential of the postsynaptic neuron. The addition of dynamic synapses to neural networks increases the computational power of such networks, especially in processing time-varying inputs. The network can be used in active pattern recognition based on extracted information about the firing frequency from input information.

Rough Set Approaches to Unsupervised Neural Network Based Pattern Classifier

Unsupervised neural network based pattern classification is a widely popular choice for many real time applications. Such applications always face challenges of processing data with lot of consistency, inconsistency, ambiguity or incompleteness. Hence to deal with such challenges a strong approximation tool is always needed. Rough set is one such tool and various approaches based on Rough set, if are applied to pure neural (unsupervised) pattern classifier can yield desired results like faster convergence, feature space reduction and improved classification accuracy. The application of such approaches at respective level of implementation of neural network based pattern classifier for two case studies are discussed here. Whereas more emphasis is given on the preprocessing level based approach used for feature space reduction.