For Base papers and enquiry call

M.SENTHILKUMAR – +919500090804


IM01 Separable reversible encrypted data hiding in encrypted image using AES Algorithm and Lossy technique The field steganography is very much popular technique for sending secrete message and lots of research are going in it. To overcome the limitation of previous work we proposed separable and reversible encrypted data hiding in encrypted image using AES Algorithm and Lossy technique as solution. In this sender encrypt data and image separately using AES algorithm, hides encrypted data in encrypted image using LSB technique, system auto generate the all 3 respective keys. Sender sends the file through existing mail system. Receiver can perform operation as per respective keys like if he has only data hiding and image decryption key then he can only get the image in original form or if he have data hiding and data decryption key then he can get original data, system also provides protection for auto generated keys and system auto generate mail if user fail to perform any operation. 2013
IM02 Vertical-Edge-Based Car-License-Plate Detection Method This paper proposes a fast method for car-license-plate detection (CLPD) and presents three main contributions. The first contribution is that we propose a fast vertical edge detection algorithm (VEDA) based on the contrast between the grayscale values, which enhances the speed of the CLPD method. After binarizing the input image using adaptive thresholding (AT), an unwanted-line elimination algorithm (ULEA) is proposed to enhance the image, and then, the VEDA is applied. The second contribution is that our proposed CLPD method processes very-low-resolution images taken by a web camera. After the vertical edges have been detected by the VEDA, the desired plate details based on color information are highlighted. Then, the candidate region based on statistical and logical operations will be extracted. Finally, an LP is detected. The third contribution is that we compare the VEDA to the Sobel operator in terms of accuracy, algorithm complexity, and processing time. The results show accurate edge detection performance and faster processing than Sobel by five to nine times. In terms of complexity, a big-O-notation module is used and the following result is obtained: The VEDA has less complexity by K2 times, whereas K2 represents the mask size of Sobel. Results show that the computation time of the CLPD method is 47.7 ms, which meets the real-time requirements. 2013
IM03 Automatic retrival of MRI brain image using multiqueries system CBIR technique is becoming increasingly important in medical field in order to store, manage, and retrieve image data based on user query. Searching is done by means of matching the image features such as texture, shape or different combinations of them. Texture features play an important role in computer vision, image processing and pattern recognition. In this paper we introduce a novel method of using SVM (Support Vector machine) classifier followed by KNN (K-nearest neighbour) for CBIR using texture and shape feature. We propose a robust retrieval using a supervised classifier which concentrates on extracted features. Gray level co-occurance matrix algorithm is implemented to extract the texture features from images. The feature optimization is done on the extracted features to select best features out of it to train the classifier. The classification is performed on the dataset and it is classified into three categories such as normal, benign and malignant. The query image is classified by the classifier to a particular class and the relevant images are retrieved from the database. To improve accuracy to calculate the precision value and recall in relevant image. Furthermore no of tissues stage storage in database to get relevant image in different feature extraction method. 2013
IM04 Tissue density classification in mammographic images using local features In breast cancer cases, it is known that the ratio of correct diagnosis is affected by the breast tissue density. For this reason, automatic tissue density classification is an important process in diagnosis. In this work a method for classification of breast tissue density from mammographic images is proposed. The objective of the method is to determine which class, namely fatty, fatty-glandular and dense-glandular, the breast tissue belongs to. For this purpose, SIFT algorithm is used as the local feature extraction method, and LVQ algorithm is used for supervised classification. Test results on the MIAS dataset demonstrate that the code vectors corresponding to bag of SIFT features of each class can successfully model the breast tissue and the classification accuracy over 90% is achieved by LVQ. 2013
IM05 A novel detection approach using bio-inspired vision for enhanced object tracking in video Video surveillance systems play an important role in many civilian and military applications, for the purposes of security and surveillance. Object detection is an important component in a video surveillance system, used to identify possible objects of interest and to generate data for tracking and analysis purposes. A video surveillance system is presented here which incorporates a novel motion detection approach using a biologically inspired vision system, within a hardware solution, for enhanced object tracking performance. This method is compared with a traditional object detection approach. This initial investigation determined that the biological vision system is robust in detecting objects representative of actual ground truth values under various complex lighting conditions. The system has shown enhanced capability by reducing false track confirmation rates (at least one order of magnitude) and achieving high confirmation rates of objects of interest within independent video data sets. An effective tracking solution has been achieved through the implementation of the biologically-inspired vision system as an enhancement to object detection. 2013
IM06 Improved histogram bin shifting based reversible watermarking Reversible w atermarking constitutes a class of fragile digital watermarking techniques that find application in authentication of medical and military imagery. Reversible watermarking techniques ensure that after watermark extraction, the original cover image can be recovered from the watermarked image pixel-by-pixel. In this paper, we propose a novel reversible watermarking technique as an improved modification of the existing histogram bin shifting technique. We develop an optimal selection scheme for the “embedding point” (grayscale value of the pixels hosting the watermark), and take advantage of multiple zero frequency pixel values (if available) in the given image to embed the watermark. Experimental results for a set of images show that the adoption of these techniques improves the peak signal-to-noise ratio (PSNR) of the watermarked image compared to previously proposed histogram bin shifting techniques. 2013
IM07 Performance evaluation of traditional and adaptive lifting based wavelets with SPIHT for lossy image compression Nowadays wavelet transform has been one of the most effective transform means in the realm of image processing, especially the biorthogonal 9/7 wavelet filters proposed by Daubechies, which have good performance in image compression. Hence, in this paper an attempt has been made to analyse traditional and adaptive lifting based wavelet techniques for image compression. The original image is transformed using adaptive lifting based CDF 9/7 wavelet transform and traditional CDF 9/7 followed by it is compressed using Set Partitioning In Hierarchical Tree algorithm (SPIHT) and the performance was compared with the popular traditional CDF9/7 wavelet transform. The performance metric Peak Signal to Noise Ratio (PSNR) for the reconstructed image was computed. The proposed adaptive lifting algorithm give better performance than traditional CDF9/7 wavelet, the most popular wavelet transforms. Lifting allows us to incorporate adaptivity and nonlinear operators into the transform. The proposed methods efficiently represent the edges and appear promising for image compression. The proposed adaptive methods reduce edge artifacts and ringing and give improved PSNR of 4.69 to 6.09 dB than the traditional CDF 9/7 for edge dominated 2D images. 2013
IM08 Application of temperature compensated ultrasonic ranging for blind person and verification using MATLAB This paper contains a method to implement a mobility aid for blind person and also can be used in automatic robots, self-propelling vehicles in automated production factories etc. Model contains signal processing unit with PIC microcontroller which receives data from Ultrasonic sensor and Temperature sensor then processed it and delivers it to the computer using serial input/output port & gives alert to the blind person using voice processor with earphone. Paper contains temperature compensation method to reduce the error in measurement of distance using ultrasonic sensors. Signal processing unit contains PIC microcontroller which is used for interfacing between different sensors and computer. Then received data is verified using MATLAB. 2013
IM09 Detection and Classification of Apple Fruit Diseases Using Complete Local Binary Patterns Diseases in fruit cause devastating problem in economic losses and production in agricultural industry worldwide. In this paper, a solution for the detection and classification of apple fruit diseases is proposed and experimentally validated. The image processing based proposed approach is composed of the following main steps, in the first step K-Means clustering technique is used for the image segmentation, in the second step some state of the art features are extracted from the segmented image, and finally images are classified into one of the classes by using a Multi-class Support Vector Machine. Our experimental results express that the proposed solution can significantly support accurate detection and automatic classification of apple fruit diseases. The classification accuracy for the proposed solution is achieved up to 93%. 2013
IM10 Scene Text Detection via Connected Component Clustering and Nontext Filtering In this paper, we present a new scene text detection algorithm based on two machine learning classifiers: one allows us to generate candidate word regions and the other filters out nontext ones. To be precise, we extract connected components (CCs) in images by using the maximally stable extremal region algorithm. These extracted CCs are partitioned into clusters so that we can generate candidate regions. Unlike conventional methods relying on heuristic rules in clustering, we train an AdaBoost classifier that determines the adjacency relationship and cluster CCs by using their pairwise relations. Then we normalize candidate word regions and determine whether each region contains text or not. Since the scale, skew, and color of each candidate can be estimated from CCs, we develop a text/nontext classifier for normalized images. This classifier is based on multilayer perceptrons and we can control recall and precision rates with a single free parameter. Finally, we extend our approach to exploit multichannel information. Experimental results on ICDAR 2005 and 2011 robust reading competition datasets show that our method yields the state-of-the-art performance both in speed and accuracy. 2013
IM11 Superpixel Classification Based Optic Disc and Optic Cup Segmentation for Glaucoma Screening Glaucoma is a chronic eye disease that leads to vision loss. As it cannot be cured, detecting the disease in time is important. Current tests using intraocular pressure (IOP) are not sensitive enough for population based glaucoma screening. Optic nerve head assessment in retinal fundus images is both more promising and superior. This paper proposes optic disc and optic cup segmentation using superpixel classification for glaucoma screening. In optic disc segmentation, histograms, and center surround statistics are used to classify each superpixel as disc or non-disc. A self-assessment reliability score is computed to evaluate the quality of the automated optic disc segmentation. For optic cup segmentation, in addition to the histograms and center surround statistics, the location information is also included into the feature space to boost the performance. The proposed segmentation methods have been evaluated in a database of 650 images with optic disc and optic cup boundaries manually marked by trained professionals. Experimental results show an average overlapping error of 9.5% and 24.1% in optic disc and optic cup segmentation, respectively. The results also show an increase in overlapping error as the reliability score is reduced, which justifies the effectiveness of the self-assessment. The segmented optic disc and optic cup are then used to compute the cup to disc ratio for glaucoma screening. Our proposed method achieves areas under curve of 0.800 and 0.822 in two data sets, which is higher than other methods. The methods can be used for segmentation and glaucoma screening. The self-assessment will be used as an indicator of cases with large errors and enhance the clinical deployment of the automatic segmentation and screening. 2013
IM12 Colour and texture feature-based image retrieval by using hadamard matrix in discrete wavelet transform Image retrieval is one of the most applicable image processing techniques, which has been used extensively. Feature extraction is one of the most important procedures used for interpretation and indexing images in content-based image retrieval systems. Effective storage, indexing and managing a large number of image collections is a critical challenge in computer systems. There are many proposed methods to overcome these problems. However, the rate of accurate image retrieval and speed of retrieval is still an interesting field of research. In this study, the authors propose a new method based on combination of Hadamard matrix and discrete wavelet transform (HDWT) in hue-min-max-difference colour space. An average normalised rank and combination of precision and recall are considered as metrics to evaluate and compare the proposed method against different methods. The obtained results show that the use of HDWT provides better performance in comparison with Haar discrete wavelet transform, colour layout descriptor, dominant colour descriptor and scalable colour descriptor, Padua point and histogram intersection. 2013
IM13 Novel iris segmentation and recognition system for human identification The richness and apparent stability of the iris texture make it a robust biometric trait for personal authentication. The performance of an automated iris recognition system is affected by the accuracy of the segmentation process used to localize the iris structure. In case of wrong segmentation, wrong features will be extracted and hence, may lead to false identification results. Most of the authors propose Circular Hough Transform to localize the boundary of IRIS. But the problem with this technique is its high consumption of time and memory. It also requires a precise estimated range of the boundary and it fails to localize the IRIS if the correct estimation is not provided. The proposed technique follows a basic strategy and obtains the major boundaries, by using canny edge detector. Features have been extracted using Curvelets Transform; Principal Component Analysis is then used to reduce the dimension of the features. Then SVM has been used as classifier. The implementation of recognition method has shown encouraging results. 2013
IM14  Real-time intelligent alarm system of driver fatigue based on video sequences Developing intelligent systems to prevent car accidents can be very effective in minimizing accident death toll. One of the factors which play an important role in accidents is the human errors including driving fatigue relying on new smart techniques; this paper detects the signs of fatigue and sleepiness in the face of the person at the time of driving. The proposed system is based on three separate algorithms. In this model, the person’s face is filmed by a camera in the first step by receiving 15fps video sequence. Then, the images are transformed from RGB space into YCbCr and HSV spaces. The face area is separated from other parts and highly accurate HDP is achieved. That the eyes are open or closed in a specific time interval is determined by focusing on thresholding and equations concerning the symmetry of human faces a finally using K-means Clustering, the frequency of yawning is identified. The proposed system has been implemented on four different video sequences with average accuracy of 93.18% and detection rate (DR) of 92.71% out of total 35000 image frames. High accuracy in segmentation, low error rate and quick processing of input data distinguishes this system from similar ones. This system can minimize the number of accidents caused by drivers’ fatigue. 2013