Accepted papers

  • Haptics-Human Interaction and Surface Simulation
    Kiran Kulkarni, Manoj Manvi, Deepti and Ashwini, B.V Bhoomaraddi College of Engineering and Technology, India
    Haptics is one of the strategic trending technologies in the world as per the famous GARTNER 2014-15 predictions. This makes it one of the leading technologies to be focused on in the field Engineering and Research studies. It Deals with the simulation of real-world experience using concepts such as augmented reality and virtuality and providing Force feedback to users about the physical properties and movements of virtual objects represented by a computer. Our proposed work aims at perceiving and simulating different surfaces or textures and further providing real-time experience of virtual objects or surfaces allowing the blind users to visualize and sense their surroundings much like bats or dolphins. The proposed work involves two main phases namely feature extraction and feature matching, involving design and development of two devices, a hand module and a puck scanner. In feature extraction process, features (intensity variations) are extracted from the surface constrictions and are recorded using sensors mounted on the hand module. Different pressures are applied and wide ranging responses are obtained which are stored in the Database. For Feature Matching, another module is designed which captures the image on the screen and further, the scanned image is processed and these features are matched with that of the database. Once the features are matched, The module is programmed such that typical frequencies are generated for different pixel values of the matched image and thus giving different vibrations through actuators creating virtual effect of the captured surface. This project would act as a virtual eye for the blind users.
  • DCT Based Multi-Focus Image Fusion Using Spatial Frequency
    Annette Maria John and Rini Ann Babu, VIT University, India
    Multi-focus image fusion aims at combining images captured with different focused levels to produce an image with better description of the scene. We took two images taken with the same camera but at different focus levels. Both images are divided into blocks. Spatial frequency of each block is calculated. Block wise comparison of spatial frequency of both the images are made. Finally fused image is obtained based on a decision map depending on spatial frequency comparison. Second method is that, the spatial frequency comparison is done on image blocks on which discrete cosine transformation is performed. Results of both the methods are analyzed by calculating the PSNR and MSE values. Simulation results shows that the discrete cosine transform (DCT)based image fusion is better.
  • Innovative Algorithm for the Detection of Thunderstorm
    Rini Ann Babu and A.K.Anilkumar, VIT University, India
    Thunderstorm is a sudden electrical shock as a result of the blaze of lightening with a spurious sound. The main aim of the work done here is to detect the thunderstorm in the satellite images. The satellite images is analysed by means of image segmentation. Here color based image segmentation is done. So the color based image segmentation is done by k-means clustering technique. Various methodologies like STP Model,MOM Model,CG Model,LM Model,QKP Model,DBD Model have been proposed but neither of them could provide accurate prediction. After the certain analysis using clustering and wavelet transform technique it is viewed to detect the thunderstorm in a particular satellite image by using the clustering technique.
  • Performance Evaluation of State of the Art Online Trackers
    Aneesh C, Guruprasad.M.Hegde and K P Soman, Amrita Vishwa Vidyapeetham, India
    The objective of the present work is to conduct a detailed study of the state of the art online trackers and to exploit the effective method to handle various challenges in the field of single object tracking. Even though there are a number of domain specific and more sophisticated tracking algorithms for specific applications such as face tracking, pedestrian tracking etc.. Tracking of generic objects are still remains as a challenging issue due to attributes such as scale change, occlusion, illumination variation, background clutters etc.At present, there isn°«t any single object tracking algorithm that can handle all these challenging attributes. So a detailed evaluation with a large number of sequences annotated with the above mentioned challenging attributes are required to identify a best performing tracker. In this paper most widely using adaptive tracking by detection methods are examined. This includes multiple instance learning tracker (MILT), structured output tracking with kernels (Struck), online adaboost tracker (OAB), real-time compressive tracker (CT), and fragment based tracker (F).Except fragment based tracker, the rest of the trackers are online. The overall performance of these discriminative and static model based trackers are examined over a large number of sequences. The sequences are categorized in to different subsets based upon nine different attributes and the ability of these online and offline trackers to handle various kinds of attributes are also examined. The quantitative results generated can be made useful for future research in the field of single object trackers.
  • Geometric Correction for Braille Document Images
    Padmavathi.S, Aishwarya.A.V and Iswaryah.S, Amrita Vishwa Vidyapeetham, India
    Braille system has been used by the visually impaired people for reading.The shortage of Braille books has caused a need for conversion of Braille to text. This paper addresses the geometric correction of a Braille document images. Due to the standard measurement of the Braille cells, identification of Braille characters could be achieved by simple cell overlapping procedure. The standard measurement varies in a scaled document and fitting of the cells become difficult if the document is tilted. This paper proposes a line fitting algorithm for identifying the tilt (skew) angle. The horizontal and vertical scale factor is identified based on the ratio of distance between characters to the distance between dots. These are used in geometric transformation matrix for correction. Rotation correction is done prior to scale correction. This process aids in increased accuracy. The results for various Braille documents are tabulated.
  • Image Compression Based Upon Wavelet Transform and a Statistical Threshold
    Ahmed A.Nashat and N.M.Hussain Hassan, Fayoum University, Egypt
    Discrete Wavelet Transform, (DWT), is known to be one of the best compression techniques. It provides a mathematical way of encoding information in such a way that it is layered according to level of detail. In this paper, we used Haar wavelets as the basis of transformation functions. Haar wavelet transformation is composed of a sequence of low pass and high pass filters, known as filter bank. The redundancy of the DWT detail coefficients are reduced through thresholding and further through Huffman encoding. The proposed threshold algorithm is based upon the statistics of the DWT coefficients. The quality of the compressed images has been evaluated using some factors like Compression Ratio, (CR), and Peak Signal to Noise Ratio, (PSNR). Experimental results demonstrate that the proposed technique provides sufficient higher compression ratio compared to other compression thresholding techniques.
  • A Review: Medical Image Watermarking
    Manjot Kaur, Guru Nanak Dev University, India
    In this modern era exchange of medical images between hospitals has become a common practice. Huge amount of medical images are generated everyday. Medical images are exchanged via unsecure network i.e internet, so there may be chances of changing medical image data either intentionally by intruders or unintentionally due to channel noise. This result in wrong diagnosis of a patient which can even lead to death of a person. As a result of this, there in requirement of medical image watermarking (MIW) which provide safe exchange of medical reports. This paper aim to provide very useful survey on medical image watermarking and offer a clear view to interested researchers.
  • Gaussian Kernel Based Fuzzy C-Means Clustering Algorithm for Image Segmentation
    Rehna Kalam, Ciza Thomas and M Abdul Rahiman, Kerala University, India
    Image Processing Is An Important Research Area In Computer Vision. Clustering Is An Unsupervised Study. Clustering Can Also Be Used For Image Segmentation. There Exist So Many Methods For Image Segmentation. Image Segmentation Plays An Important Role In Image Analysis.It Is One Of The First And The Most Important Tasks In Image Analysis And Computer Vision. This Proposed System Presents A Variation Of Fuzzy C-Means Algorithm That Provides Image Clustering. The Kernel Fuzzy C-Means Clustering Algorithm (Kfcm) Is Derived From The Fuzzy C-Means Clustering Algorithm(Fcm).The Kfcm Algorithm That Provides Image Clustering And Improves Accuracy Significantly Compared With Classical Fuzzy C-Means Algorithm. The New Algorithm Is Called Gaussian Kernel Based Fuzzy C-Means Clustering Algorithm (Gkfcm)The Major Characteristic Of Gkfcm Is The Use Of A Fuzzy Clustering Approach ,Aiming To Guarantee Noise Insensitiveness And Image Detail Preservation.. The Objective Of The Work Is To Cluster The Low Intensity In Homogeneity Area From The Noisy Images, Using The Clustering Method, Segmenting That Portion Separately Using Content Level Set Approach. The Purpose Of Designing This System Is To Produce Better Segmentation Results For Images Corrupted By Noise, So That It Can Be Useful In Various Fields Like Medical Image Analysis, Such As Tumor Detection, Study Of Anatomical Structure, And Treatment Planning.
  • Electronic Music Synthesis and Audio Effects Processing
    Karthik K M, Shashank Ashar and Preethi J Seegehalli, PES University, India
    Music is a gratifying part of the life of a plethora of people in the world. The application of various signal processing techniques in the field of music has paved way to °∆Music Technology°«. Music technology has changed the way music is created, composed, stored and analysed. A user friendly easy to use GUI is proposed to be designed on MATLAB to facilitate creation of music using specially synthesized virtual digital musical instruments. The creation of music is proposed to be achieved using Physical Modelling Techniques. In addition to composing various patterns using the instrument models, inclusion of various sound effects using Audio Signal Processing techniques is also proposed.
  • Blind Color Image Deconvolution in YUV Space
    Roshan Jameer Patan and Madhuparna Chakraborty, NIT Agartala, India
    This paper presents the framework to address blind image deconvolution process in YUV colour space. Various techniques had been employed for regular RGB colour images, here we extend the work for the YUV colour spaces. Apart from RGB colour space, YUV colour space has uncorrelated channels. The Luminous channel has no correlation with the other two Chroma channels. This motivates to propose a 3-D Laplacian operator Q for the YUV colour space. The restoration process is performed based on single-input single-output (SISO) mode. Alternating minimization is used to restore both image and the blur jointly. Good performance is observed for photographically blurred images, with no prior knowledge of the blur operator.