H. B. Kekre

Image retrieval using augmented block truncation coding techniques

With the tremendous growth of ICT (Information and Communication Technology), we are able to generate, store, share and transfer enormous amount of information. World Wide Web have further made is easy to access the information anytime, anywhere in the world. With the advent of high capacity communication links and storage devices even most of the information generated is of multimedia in nature. Images have major share in this information and the number of image achieves are growing with the jet speed Just having the tremendous amount of information is not useful unless we do not have the methodologies to effectively search the related data from it in minimum possible duration. The relativity of the image data is application specific. Here to search and retrieve the expected images from the database we need Content Based Image Retrieval (CBIR) system. CBIR extracts the features of query image and try to match them with the extracted features of images in the database. Then based on the similarity measures and threshold the best possible candidate matches are given as result. There have been many approaches to decide and extract the features of images in the database.n Binary truncation Coding based features is one of the CBIR methods proposed using color features of image. The approach basically considers red, green and blue planes of image together to compute feature vector. Here we have augmented this BTC based CBIR as BTC-RGB and Spatial BTC-RGB. In BTC-RGB feature vector is computed by considering red, green and blue planes of the image independently. While in Spatial BTC-RGB, the feature vector is composed of four parts. Each part is representing the features extracted from one of the four non overlapping quadrants of the image. The new proposed methods are tested on the 1000 images database and the results show that the precession is improved in BTC-RGB and is even better in Spatial BTC-RGB.

An Efficient Fast Algorithm to Generate Codebook for Vector Quantization

In this paper we present a very simple and yet effective algorithm to generate codebook. The algorithm uses sorting method to generate codebook and the codevectors are obtained by using median approach. The proposed algorithm was experimented on six different images each of size 512 x 512 and four different codebooks of sizes 128, 256, 512 and 1024 are generated. The proposed algorithm is found to be much faster than the LBG and KPE algorithm. The performance of this algorithm is better than LBG and KPE algorithms considering MSE, PSNR and execution time. The proposed algorithm gives less MSE as compared to the LBG for the codebooks of sizes 128, 256, 512 & 1024 respectively. It also gives higher PSNR as compared to LBG for the codebooks of various sizes.

Color Traits Transfer to Grayscale Images

Here we are presenting some novel techniques for squirting colors in grayscale images. The problem of coloring grayscale images has no exact solution. Here we are attempting to minimize the human efforts needed in manually coloring the grayscale images. We need human interaction only to find a reference color image, then the job of transferring color traits from reference color image to grayscale image is done by proposed techniques. In these techniques, the color palette is prepared using pixel windows of some degrees taken from reference color image. Then the grayscale image is divided into pixel windows with same degrees. For every window of grayscale image the palette is searched for equivalent color values, which could be used to color grayscale window. In the whole process the luminance values of reference color image and target grayscale image are only matched and based on best possible match the respective chromaticity values of color image are transferred to grayscale image. For palette preparation first we used RGB color space and then Kekres LUV color space[9]. Results with Kekres LUV color space were comparatively better. To improve the searching time through color palette the exhaustive and Kekres fast search are used.

Performance evaluation of pixel value differencing and Kekre's modified algorithm for information hiding in images

Steganography, derived from Greek, literally means covered writing. It includes a vast array of secret communications methods that conceal the messages very existence. These methods include invisible inks, microdots, character arrangement, digital signatures, covert channels, and spread spectrum communications. Pixel Value Differencing (PVD)[8] was proposed for gray scale images where two consecutive pixel pairs are formed and embedding capacity is decided based on difference in their values. This paper has extended PVD to 24 bit color images and also a new improved version of Least Significant Bit (LSB) method (Modified Kekres Algorithm) which is also applied on 24 bit color images. The proposed method is simple for implementation when compared to PVD method and yet achieves a high embedding capacity and good imperceptibility.

Increasing the Capacity of the Cover Audio Signal by Using Multiple LSBs for Information Hiding

— Steganography is an art and science of writing hidden messages in such a way that no one apart from the intended recipient knows the existence of the message. The maximum number of bits that can be used for LSB audio steganography without causing noticeable perceptual distortion to the host audio signal is 4 LSBs, if 16 bits per sample audio sequences are used. We propose 2 novel approaches of substitution technique of audio steganography that improves the capacity of cover audio for embedding additional data. Using these methods, message bits are embedded into multiple and variable LSBs. These methods utilizes up to 7 LSBs for embedding data. Results show that both these methods improve capacity of data hiding of cover audio by 35% to 70% as compared to the standard LSB algorithm with 4 LSBs used for data embedding. From subjective listening tests, it is seen that there is no noticeable difference between the cover audio signal and the stego audio signals obtained from the proposed methods. These novel approaches for increasing capacity show better results as compared to the existing approaches.

Identification of multi-spectral palmprints using energy compaction by Hybrid wavelet

Orthogonal Transforms and Wavelets can be used to extract features of a biometric in frequency domain. They also exhibit the property of energy compaction which can be used to select few coefficients as features of an image. Here we make use of a Hybrid wavelet, generated by using Kronecker product of two existing orthogonal transforms, Walsh and DCT to identify multi-spectral palmprints. A threshold energy value is chosen to select all coefficients whose total energy is above that value. One-to-many identification on a large database containing 3 sets of 6000 multi-spectral palmprint images from 500 different palms is used to validate the performance of the proposed method and matching accuracy in terms of genuine acceptance ratio of 99.979% using score level fusion has been obtained. Hence this method can significantly improve the identification rates for palmprint images.

Finger-Knuckle-Print Region of Interest Segmentation Using Gradient Field Orientation & Coherence

Finger-knuckle-print is one of the emerging biometric traits. The region of interest is the area where the maximum information is centered, for a finger knuckle it is the area surrounding the knuckle region. A good system needs this region of interest as input for the feature vector extraction. In this method we present a novel approach for segmentation of Region of interest (ROI) of a finger-knuckle-print using gradient field orientation & its local field strength. This approach is fast and gives good results in case of shift in finger-knuckle-placement (translational shift).

A new multi-resolution hybrid wavelet for analysis and image compression

Most of the current image- and video-related applications require higher resolution of images and higher data rates during transmission, better compression techniques are constantly being sought after. This paper proposes a new and unique hybrid wavelet technique which has been used for image analysis and compression. The proposed hybrid wavelet combines the properties of existing orthogonal transforms in the most desirable way and also provides for multi-resolution analysis. These wavelets have unique properties that they can be generated for various sizes and types by using different component transforms and varying the number of components at each level of resolution. These hybrid wavelets have been applied to various standard images like Lena (512 × 512), Cameraman (256 × 256) and the values of peak signal to noise ratio (PSNR) obtained are compared with those obtained using some standard existing compression techniques. Considerable improvement in the values of PSNR, as much as 5.95 dB higher than the standard methods, has been observed, which shows that hybrid wavelet gives better compression. Images of various sizes like Scenery (200 × 200), Fruit (375 × 375) and Barbara (112 × 224) have also been compressed using these wavelets to demonstrate their use for different sizes and shapes.

Analysis of an asymmetric polling system

Abstract Polling models are used extensively in the field of operations research to analyze the performance of a variety of systems that can be viewed as a distributed queuing system served by a single server and to evaluate their operational characteristics. In the context of computer communication, a Local Area Network (LAN) with controlled access on a single transmission media can be viewed as such a polling system in which queues are being served in cyclic order. In this article, a LAN with reverse round robin scheduling for channel arbitration, called M-net [1], is modeled as a discrete time Markov chain representing an asymmetric polling system. Expressions for its performance measures like average channel utilization, mean and variance of delay and blocking probability at a station are derived. For a system of M stations, the solution complexity is of the order of 2 2( M −1) The analysis approach is applicable to both round robin and reverse round robin systems. Finally, performance measures of such a system are compared with that of Expressnet, as a representative example of round robin system. It is found that at lower arrival rates, the performance of M-net is comparable to that of Expressnet. However, with increasing values of arrival rates, M-net outperforms Expressnet. The analysis presented is applicable to the class of systems in operations research that can be viewed as multiple single buffer queues served by a server in round robin or reverse round robin fashion.

'Color to Gray and back' using normalization of color components with Cosine, Haar and Walsh Wavelet

The paper shows performance comparison of three proposed methods with orthogonal wavelet alias Cosine, Haar & Walsh wavelet using Normalization for Color to Gray and Back. The color information of the image is embedded into its gray scale version using wavelet and normalization method. Instead of using the original color image for storage and transmission, gray image (Gray scale version with embedded color information) can be used, resulting into better bandwidth or storage utilization. Among three algorithms considered the second algorithm give better performance as compared to first and third algorithm. In our experimental results second algorithm for DCT wavelet using Normalization gives better performance in Color to gray and Back w.r.t all other wavelet transforms in method 1, method 2 and method 3. The intent is to achieve compression of 1/3 and to print color images with black and white printers and to be able to recover the color information as and when required. Keywords- Color Embedding, Color-to-Gray Conversion, Transforms, Wavelets Normalization , Compression.