Journal of Digital Image Processing and Computer Vision

Authors: Harpinder Singh, Sheetal Kalra, Sarabpreet Singh

Abstract: Cloud computing is still in its infancy in spite of gaining tremendous momentum recently. High security is one of the major obstacles for opening up the new era of the computing as a utility. As the sensitive applications and data are moved into the cloud data centers to runs on virtual computing resources in the form of virtual machine. It might be difficult to track data security issues in cloud computing environment. So this paper aims to highlights the main privacy, security and trust issues in cloud computing. In this manuscript it presents some existing classical encryption techniques for securing the data in cloud. This paper also proposes encryption decryption algorithms to address the security and privacy issue in cloud storage in order to protection on data in the cloud computing.

Author: Pawan Singh Shekhawat

Abstract: Watermarking technology insert ownership information in suitable form inside any media like audio, video, image etc, so that owner of the object will claim his/her ownership when anyone claims his/her false ownership on that object. Proposed work, proposes a new algorithm for watermark insertion and extraction named as “Non Blind DWT Based Multiplicative SVD Watermarking algorithm†which is new version of the algorithm proposed by Bhargava [8] in his paper “Digital Image Authentication System Based on Digital Watermarking†.In this paper he is utilizing additive approach for watermark embedding and extraction algorithm and proposed algorithm utilize the multiplicative approach also he embeds watermark in one sub-band i.e. approximation sub-band and proposed algorithm utilize all four sub-bands for watermark embedding.

Author: Sudam G. Pawar

Abstract: This paper presents basics of image processing approach and study of different image processing methods for painting still images and how this is useful to improve image resolution for both still as well as video images. This paper also presents how to improve the low resolution image patch with high resolution image patch. It also includes how one can erase unwanted title, name or translated language displays in video images by painting its pixels with desired color. This paper also describes basic building blocks of image processing sequence and image compression methods.

Author: Preeti P. Bhatt , M.D. Jarul Munshi  , Juhi Patel 

Abstract:  Digitization of handwritten document is important for better processing and storage. But people wish to have their own personal handwriting as font because Personal font style gives a personal touch and make the document more eye-catching. Font generation is a process of generation of a handwritten document-based writing characteristic which is specific to user’s writing style. In this paper comparative study of font generation techniques has been presented for different languages such as English, Bangla, and Chinese. We also compare different methods like RNN, a Macro structure model, LSTM etc. which were used for font generation in different languages. Different parameters have been considered for regenerating someone’s font like character glyph, character space and connection style.

Authors: Priyanka Jeswani, Manisha Kumari Rajoriya, Kanika Sharma

Abstract: In Internet world, there is a need for copyright protection of digital content. Even if it is a video files uploaded over websites. Watermarking algorithms have a basic requirement that the watermark should be imperceptible to avoid being detected and not cause visible distortion to the viewer. In this paper we aim to present a survey of two different techniques on digital image watermarking. Digital watermarking is used as a key solution to make the data transferring secure from illegal interferences. Digital watermark techniques are used in various areas such as copyright protection, broadcast monitoring and owner identification. In this paper we mainly discussed about two methods by frequency domain and spatial domain. In frequency domain such as DCT, DWT the watermark is inserted into transformed coefficients of image giving more information hiding capacity and more robustness against watermarking attacks. In spatial domain, watermark is inserted directly by modifying the pixel values of host image.

Author: Suchethana H C

Abstract: Visual cryptography is a cryptographic technique which allows visual information (pictures, text, etc.) to be encrypted in such a way that decryption becomes the job of the person to decrypt via sight reading. Visual Cryptography is a wide area of research used in data hiding, securing images, color imaging, multimedia and other such fields. Visual Cryptography comes in the field of data hiding used in cybercrime, file formats etc. This paper focuses on the application areas of visual cryptography about the most important application areas of visual cryptography. Visual cryptography can be used to protect biometric templates in which decryption does not require any complex computations. a secret image which is encoded into N shares printed on transparencies. The shares appear random and contain no decipherable information about the underlying secret image, however if any 2 of the shares are stacked on top of one another the secret image becomes decipherable by the human eye. Some challenges of visual cryptography example the contrast of the reconstructed image,perfect alinment of the transferencies are projected.

Authors: Jeena Johnson, Josna Jose

Abstract: This paper focuses on different kinds of image encryption and decryption technique. In addition focuses on the image encryption technique. There are various techniques which are discovered from time to time to encrypt and decrypt the image to make more secure. Video surveillance system are becoming omnipresent. Visual surveillance has emerged as an effective technology for public security, privacy has become an issue of great concern in the transmission and distribution of surveillance video. Various encryption methods and scrambling methods are used to protect the facial biometric components and also various method are to be used facial biometric verification. The main intension of this paper is functionality of image encryption and decryption techniques mainly present the FFL scheme for verify the facial biometric components.

Authors: Venkatarao Rampay, Ch. Satyanarayana

Abstract: Face is generally considered as the reference frame of mind. Therefore, to estimate the feeling of the mind, many authors have considered the emotions from the facial expressions into consideration to identify the state of mind of an individual. Hence in this article we proposed a methodology for automatic age estimation based on Local Binary Pattern (LBP) and Grey Level Co- Occurrence Matrix (GLCM). The facial features are extracted using LBP and GLCM and these features are given as input’s to the Support Vector Machine (SVM) for age estimation. The experimentation on proposed method is carried out using FG-NET database and Mean Absolute Error (MAE) is calculated to compare the proposed method with state-of-the-art algorithms. Finally, the proposed methodology demonstrates the classification accuracy above 88%.

 

Author: Shankar N. Dandare

Abstract: Fault detection and isolation has gained growing importance for vehicle safety and reliability. In this paper Fault Detection in a Four Stroke (FS) motor Cycle engine has been proposed. Primary objective of this paper is to propose a smart as well as robust method for Fault Detection (FD) in automobile engines by using the Artificial Neural Network (ANN) based classifiers, which is able to detect the multiple faults in an incipient stage. Novelty of this proposed system is to reduce requirement of multiple sensors to a single sensor in order to detect multiple faults.

Authors: Preetam Kumar Chourasiya, Amit Tripathi,  Manish Singh, Narendra Nagar

Abstract: In this paper we discussed about the ability to identify different faces than machines. So face detection plays major role in face recognition, facial expression recognition, head-pose estimation, human-computer interaction, etc. Face detection is a computer technology that determines the location and size of human face in arbitrary (digital) image. This paper presents all comprehension and critical survey of algorithms through which face detection is possible. This document gives formatting instructions for authors preparing papers for publication in the Proceedings of an International Journal.

Author: A. Aafiya Thahaseen

Abstract: Image based password schemes are constructed to authenticate users. Graphical passwords are composed with images and sketches with human memory for visual information. Improved password memorability and strength against guessing attacks are the key benefits of graphical password schemes. Graphical passwords are classified into three main categories. They are recall, recognition and cued-recall methods. Recall based graphical password systems are draw metric systems. Recognition based systems, also known as cogno metric systems or search metric systems. Cued recall systems typically require that users remember and target specific locations within an image. Graphical passwords and Captcha schemes are integrated to perform the user authentication with improved security mechanism. Captcha as graphical passwords (CaRP) is a graphical password scheme used for user authentication. Online guessing attacks, relay attacks and shoulder surfing attacks are handled in CaRP. CaRP is click-based graphical passwords where a sequence of clicks on an image is used to derive a password. Dynamic captcha challenge image is used for each login attempt in CaRP. Text Captcha and image-recognition Captcha are used in CaRP scheme. Text CaRP scheme constructs the password by clicking the right character sequence on CaRP images. CaRP schemes can be classified into two categories recognition based CaRP and recognition-recall based CaRP. Recognition-based CaRP seems to have access to an infinite number of different visual objects. Recognition-recall based CaRP requires recognizing an image and using the recognized objects as cues to enter a password. Recognition-recall combines the tasks of both recognition and cued-recall. Password information is transferred and verified using hash codes. Secure channels between clients and the authentication server through Transport Layer Security (TLS). The system is improved with distribution analysis and transmission security features. Pattern based attacks are handled with Color and Spatial patterns. Pixel colors in click points are considered in the color pattern analysis model. Pixel location patterns are considered in the spatial pattern analysis model.

Authors: Vishakha Mishra, Rupali Gupta, Anshul Bhatia, Sankalp Malhotra, Krishan Kumar

Abstract: A new color image encryption algorithm based on DNA (Deoxyribonucleic acid) sequence addition operation is presented. Firstly, three DNA sequence matrices are obtained by encoding the original color image which can be converted into three matrices R, G and B. Secondly, we use the chaotic sequences generated by Chen’s hyper-chaotic maps to scramble the locations of elements from three DNA sequence matrices, and then divide three DNA sequence matrices into some equal blocks respectively. Thirdly, we add these blocks by using DNA sequence addition operation and Chen’s hyper-chaotic maps. At last, by decoding the DNA sequence matrices and recombining the three channels R, G and B, we get the encrypted color image. The simulation results and security analysis show that our algorithm not only has good encryption effect, but also has the ability of resisting exhaustive attack, statistical attack and differential attack.

Authors: Tany Thomas, Ammu Appukuttan, Haritha Melvin, Linda Sara Mathew, Chaitanya C

Abstract: Automatic Speech Recognition has been a subject of intensive research for the last many decades. It is the process of converting a speech signal to a set of words, by means of an algorithm implemented as a computer program. The goal of this project is to develop a Formal Malyalam Speech to Text Converter for the Malayalam language. The main components of Automatic Speech Recognition system are feature extraction, training and recognition. Feed forwarding technique is used as a front-end to extract acoustic features from the input signal. Resilient Propagation Algorithm is used to train the Artificial Neural Network (ANN) for classification and recognition purpose. The developed system is integrated to open Office Writer. Different applications include malayalam voice search, user friendly editor for visually challenged people, and so on.

Authors: Abhinand R K, Afsal A Azeez, Nikhin Raj K K, Eldo P Elias, Jisha P Abraham, Joby George

Abstract: Video streaming has become the leading contributor to the explosive growth of Internet traffic. As a key system parameter of video apps, cache threshold plays an important role in regulating the downloading behavior of a system, and directly affects the efficacy of video streaming. In this paper, we first conduct a series of well designed experiments to understand the mechanism of cache management in the OS and investigate the impact of cache threshold on the performance of video streaming. The experiments show that the current static configuration of cache thresholds in the OS cannot well balance the tradeoff between cost incurred by unconsumed content and user quality of experience. To achieve cost-effective video streaming, this paper further proposes a control-theoretic cache management algorithm called smart cache with adaptive thresholding (SCAT), which can intelligently tune cache thresholds to satisfy user preferences. The complexity of cache management and optimization can be decreased extensively by the SCAT strategy, facilitating its easy integration with the OS kernel codes. Finally, we implement and evaluate our proposed scheme on the real platform and the experimental results verify that our proposed scheme achieves significant gain over other alternative approaches. Compared to the default scheme, SCAT achieves over40% reduction of unconsumed content cost.

Authors: P.Nagaraju, Dr.A.Subramanyam 

Abstract: Future high resolution instruments planned by ISRO for space remote sensing will have higher data rates as a result of planned improvements in resolution and dynamic range. Limited transmission capability mandates higher compression ratio for such missions. Differential Pulse Code Modulation (DPCM) is prediction based image compression technique (10:7) successfully used in Resourcesat-2 mission. An effort has been made to develop low complex image compression techniques with higher compression ratio while maintaining similar/better radiometric performance. Adaptive DPCM (ADPCM) is another prediction based image compression technique, which has been used by other space agencies with proprietary algorithms. Custom ADPCM techniques with multiple quantizers are developed with compression ratio of 10:6 and 10:5. Developed low complex ADPCM techniques are unique w.r.t. predictor selection. Developed techniques are evaluated for both low and high contrast images.

Authors: Rabinarayan Panigrahi, Manini Monalisa Pradhan, Dibyashree Panda, Devasis Pradhan

Abstract: Digital watermarking is an important issue for the copyright protection and ownership authentication in multimedia applications. We implement the watermarking algorithm using frequency domain technique by using DCT (Discrete Cosine Transform) on images. Here, the invisible watermarking is used to protect copyrights of multimedia contents. The invisible watermarks are new technologies which could solve the problem of enforcing the copyright protection is required for ownership identification as well as hidden information can also be identified. Where, the watermark is invisible to the human eye. Also, the authenticity of the information in the image can be obtained by comparing the watermarked image with the original image.

Authors: Prof. Karimella Vikram, Dr. Soundara Rajan

Abstract: 

The objective of this paper is to estimate a high resolution medical image from a single noisy low resolution image with the help of given database of high and low resolution image patch pairs. Initially a total variation (TV) method which helps in removing noise effectively while preserving edge information is adopted. Further de-noising and super resolution is performed on every image patch. For each TV denoised low-resolution patch, its high-resolution version is estimated based on finding a nonnegative sparse linear representation of the TV denoised patch over the low-resolution patches from the database, where the coefficients of the representation strongly depend on the similarity between the TV denoised patch and the sample patches in the database. The problem of finding the nonnegative sparse linear representation is modelled as a nonnegative quadratic programming problem. The proposed method is especially useful for the case of noise-corrupted and low-resolution image

Authors- P.Tamil Mathi , Dr. L. Latha

Abstract- 

The role of fire detection is to identify fire in a timely manner. Practically automatic fire detection using image processing techniques characterizes one of the significant aspects of any fire avoidance earlier. In current fire detection systems exact location of fire, manual work such as physical inspection of fire pose a serious threat to timely detection of fire. To overcome this standard approach must be developed. Detection of fire using image and video is effective than using sensors.
A computer vision based approach for detecting the presence of fire in video is presented here. The contributions for the fire detection may be an image or a video but the input as a video is quite complex process but provides good result. The fire is detected using spatio temporal flame modeling and analysis of dynamic textures. Extraction of features such as color consistency, spatial wavelet, spatio-temporal analysis, temporal analysis is by spatio temporal flame modeling. RGB color model is used for calculating color consistency and 2DWT for calculating wavelet in space. In wavelet analysis the image is divided into sub-images (LL, LH, HL, and HH). The main feature of fire, the flickering property is identified using temporal analysis. These features are combined with features of texture analysis which includes LDS and codebook is formed which are then classified using SVM classifier. This approach performs better than other fire detection system with high true positives and less true negatives.

Authors: Dipali Wankhade, Mahesh Ingle

This paper gives a presentation of the structure for model based inpainting. It first presents an analysis of an inpainting on a coarse variant of the data picture, then various leveled superdetermination calculations are utilized to recover points of interest on the missing territories.
It is a simpler method of low-determination inpainting of pictures compared to highdetermination ones, hence preferable. The advantages can be observed with regards to both, the computational multifaceted feature of the picture, as well as improvement in its visual quality. In any case, to simplify the process of setting parameters for the inpainting strategy, the low-determination info picture is inpainted a few times with some distinctive arrangements. Results are effectively consolidated with a loopy conviction proliferation, and subtle elements are recovered by a single picture super-determination calculation. Exploratory results in connection with picture alteration and surface amalgamation show the
viability of the proposed technique.