Earticle

With the wealth of image data that is now becoming increasingly accessible through the advent of the world wide web and the proliferation of cheap, high quality digital cameras it is becoming ever more desirable to be able to automatically classify images into appropriate categories such that intelligent agents and other such intelligent software might make better informed decisions regarding them without a need for excessive human intervention. However, as with most Artificial Intelligence (A.I.) methods it is seen as necessary to take small steps towards your goal. With this in mind a method is proposed here to represent localised features using disjoint sub-images taken from several datasets of retinal images for their eventual use in an incremental learning system. A tile-based localised adaptive threshold selection method was taken for vessel segmentation based on separate colour components. Arteriole-venous differentiation was made possible by using the composite of these components and high quality fundal images. Performance was evaluated on the DRIVE and STARE datasets achieving average specificity of 0.9379 and sensitivity of 0.5924.

This paper presents a new model of a management system for large-scale buildings. Unlike previous systems for building management, the proposed system aims to deal with both static and dynamic spatial information in a single framework. For this purpose, 3D CAD, 3D GIS and image processing are integrated together. In the proposed system, the geometrical information of a building is managed by GIS using a database built from 3D CAD. Also, the dynamic spatial information (i.e., flow size of pedestrians) is obtained using image processing. We implemented a prototype version of the proposed system to a real environment and it showed promising results for a running system covering a wide area.

At July 2008, the nationwide DMB (Digital Multimedia Broadcasting) has got started. As DMB device's volume of sales has been over 12 million already, the development of rapidly changing network systems has increased the dangers of infringing the copyright of DMB contents. For solving this problem, we suggest that real-time encryption algorithm without additional expenses, and implemented that on PMP. We used the SEED algorithm for encryption. As the experimental result, we confirmed that the real-time encryption and decryption of DMB videos were working well. Also confirmed that recorded contents in PMP were not replayed in other devices, and also the contents recorded by other devices were not played in PMP. Suggested algorithms can be useful in the VOD, IPTV or cable TV.

Most commonly used face recognition algorithms are based on extraction of global features using eigenvalue decomposition of some relational matrix of image intensity values. Real time face recognition applications require a computationally efficient algorithm for eigenvalues generation. Fast principal component analysis (FPCA) is an algorithm for efficient generation of eigenvalues which improves the computational efficiency to O(n2) as compared to normal decomposition method which gives the solution in O(n3) time. In FPCA however, nonconvergence state can be resulted for high resolution images because in this case the number of Grams-Schmidt (GS) iterations for orthonormalization convergence may exceed the maximum limit. To overcome this problem we present a modified FPCA algorithm to generate eigenvalues for images including those at high resolution. An overall efficient face recognition scheme has also been proposed using the generated eigenvalues, which can work satisfactorily under varying image resolutions. The validity of the proposed system has been checked by varying the feature vectors and the training sets. The developed technique provides an efficient and a low error rate solution for high speed image recognition systems.

A lossless information hiding scheme based on neighboring correlation is proposed in this paper. The scheme hides secret information into gray-level images according to the correlation between neighboring pixels. The performance of the proposed scheme has been evaluated in terms of payload capacity, image distortion, as well as embedding rate, and the experimental results show that the proposed lossless information scheme is capable of providing a great payload capacity without causing noticeable distortion, and the embedding rate is quite high. In addition, the proposed scheme can completely restore the host image after secret data extraction.

Signature can be seen as an individual characteristic of a person which, if modeled with precision can be used for his/her validation. An automated signature verification technique saves valuable time and money. The paper is primarily focused on skilled forgery detection. It emphasizes on the extraction of the critical regions which are more prone to mistakes and matches them following a modular graph matching approach. The technique is robust and takes care of the inevitable intra- personal variations. The results show significant improvement over other approaches for detecting skilled forgery.

Noar and Shamir presented the concept of visual cryptography. Many researches following it go down the same track: to expand the secret pixels to blocks. As a result, the size of the secret image becomes larger, and the quality of the expanded secret image becomes worse. In order to prevent the pixels from expanding, Yang has proposed his probability-based visual secret sharing scheme, where the concept of probability is employed to pick out pixels from the black or white sets. In this paper, we shall propose a new scheme that is a modified version of Yang’s scheme. Our experimental results show that we can obtain better recovered image quality with high contrast.

The EMD method proposed by Zhang and Wang fully exploited modification directions. Modifications in different directions were used to represent different secret data. According to the experimental results, the highest capacity was demonstrated in the 5-ary notational system, where only one secret digit is embedded for each two pixels. But this is an inefficient method because it can be hidden more secret data without revealing to the human visual system. To improve an embedding capacity, Chang et al. proposed two-stage EMD method, Lee et al. restricted to 8-ary embedding for the EMD method, and also Lee et al. segmented the pair of cover data into two parts to embed higher secret data. But still have a room for hiding more secret data. This paper proposes an improved method of the EMD method to hide more secret data while maintaining a high PSNR value. The proposed method can embed secret bit on every pixel of cover data. The experimental results demonstrate that the proposed method has a high capacity and good visual quality.

A new parameter estimation method for linear chirp signal is proposed. This method utilizes the Discrete Fractional Fourier Transform (DFRFT) along with Bowtie Chirplet Transform to estimate the amplitude and phase parameters of multi-component chirp signals. DFRFT is used for estimating amplitude parameter whereas the chirp rate and initial frequency are estimated using Chirplet Transform. Performance of the proposed method in noise is analyzed by Monte-Carlo simulation for different Signal to Noise Ratio (SNR). Good performance was achieved at SNR as low as -10 dB.

Edge detection plays an important role in digital image processing. Based on the non-decimated wavelet which is shift invariant, in this paper, we develop a new edge detection technique using Hidden Markov Chain (HMC) model. With this proposed model (NWHMC), each wavelet coefficient contains a hidden state, herein, we adopt Laplacian model and Gaussian model to represent the information of the state “big” and the state “small”. The model can be trained by EM algorithm, and then we employ Viterbi algorithm to reveal the hidden state of each coefficient according to MAP estimation. The detecting results of several images are provided to evaluate the algorithm. In addition, the algorithm can be applied to noisy images efficiently.

Usually, the video based object tracking deal with non-stationary image stream that changes over time. Robust and Real time moving object tracking is a problematic issue in computer vision research area. Most of the existing algorithms are able to track only in predefined and well controlled environment. Some cases, they don’t consider non-linearity problem. In our paper, we develop such a system which considers color information, distance transform (DT) based shape information and also nonlinearity. Particle filtering has been proven very successful for non-gaussian and non-linear estimation problems. We examine the difficulties of video based tracking and step by step we analyze these issues. In our first approach, we develop the color based particle filter tracker that relies on the deterministic search of window, whose color content matches a reference histogram model. A simple HSV histogram-based color model is used to develop this observation system. Secondly, we describe a new approach for moving object tracking with particle filter by shape information. The shape similarity between a template and estimated regions in the video scene is measured by their normalized cross-correlation of distance transformed images. Our observation system of particle filter is based on shape from distance transformed edge features. Template is created instantly by selecting any object from the video scene by a rectangle. Finally, in this paper we illustrate how our system is improved by using both these two cues with non linearity.

In this paper, a new oblivious fragile watermarking using discrete cosine transform is proposed. It is inspired by Wong's public key watermarking scheme proposed in 1998 and aims to improve its vulnerability towards possible attacks indicated by Barreto and Holliman. Instead of making use of contextual information and making it an inter-block dependent scheme, as suggested by Barreto, we adopt another approach to retain its blockwise independent property. Our scheme can avoid the conditions necessary for such attacks to be feasible. Furthermore, our scheme extracts the inherent image features and embeds them into this image as the watermark. This relieves users from having to maintain a database of watermarks from various sources. Experimental results show that the watermark insertion procedure has little effect on the visual quality of the watermarked image. They also show our scheme can locate the modifications made to the watermarked image, including image scaling, cropping, geometric distortion, pixel value changes, etc.