Malicious Software (Malware) is a primary element of many cyber crimes and attacks, causing massive damage and financial losses to organizations. Accordingly, malware detection and classification has become a crucial security field resulting in various attempts from researchers to develop solutions including signature-based approaches to Artificial Intelligence (AI) models showing their efficacy in detecting malware. Yet, users still have reservations about AI models due to the ambiguity and mysteriousness of their decisions resulting from their black-box nature. To address this problem, this paper proposes to develop explainable AI models to classify the malware families robustly. The proposed method uses text classification of API call sequences generated by these families by considering two datasets. A weighted training methodology is used to solve the dataset imbalance problem. Subsequently, the method presents an eXplainable AI (XAI) approach to establish an understandable and interpretable relationship between the API call sequences and the Bidirectional Encoder Representations from Transformers (BERT) model decisions, which enhance the model accountability and usability by employing the Local Interpretable Model-Agnostic Explanation (LIME) and the Shapley Additive Explanations (SHAP) platforms. The results reveal that the BERT model outperforms its counterparts considering F1 score, Balanced Accuracy (BA), and Matthews correlation coefficient (MCC).

Tracheal intubation is a critical medical procedure involving the insertion of a tube into the trachea to maintain an open airway. While essential, this procedure carries significant risks, such as incorrect tube placement. Advances in visually guided intubation methods, like video laryngoscopy, have enhanced safety by enabling precise tracheal segmentation from endoscopic images. Our study introduces an innovative image enhancement technique for video endoscopy that significantly improves tracheal visibility and segmentation accuracy. This novel approach not only facilitates safer and more accurate intubation but also minimizes patient discomfort and procedural risks. Tested against the UoS Dataset and real patient data from thyroidectomy procedures, our method demonstrated superior performance, achieving a segmentation accuracy of $97 \%$, a precision of $94 \%$, and a recall of $99 \%$. Our tailored method is computationally efficient, making it suitable for implementation on edge devices like Arduino, thereby enhancing intubation safety and efficiency in various medical settings.

Abstract Manually labelling datasets for training violence detection systems is time-consuming, expensive, and labor-intensive. Mind wandering, boredom, and short attention span can also cause labelling errors. Moreover, collecting and distributing sensitive images containing violence has ethical implications. Automation is the future for labelling sensitive image datasets. Deep labeller is a two-stage Deep Learning (DL) method that uses pre-trained DL object detection methods on MS-COCO for automatic labelling. The Deep Labeller method labels violent and nonviolent images in WVD and USI. In stage 1, WVD generates weak labels using synthetic images. In stage 2, the Deep labeller method is retrained on weak labels. USI dataset is used to test our method on real-world violence. Deep labeller generated weak and strong labels with an IoU of 0.80036 in stage 1 and 0.95 in stage 2 on the WVD. Automatically generated labels. To test our method’s generalisation power, violent and nonviolent image labels on USI dataset had a mean IoU of 0.7450.

A substantial amount of research has been carried out in Explainable Artificial Intelligence (XAI) models, especially in those which explain the deep architectures of neural networks. A number of XAI approaches have been proposed to achieve trust in Artificial Intelligence (AI) models as well as provide explainability of specific decisions made within these models. Among these approaches, global interpretation methods have emerged as the prominent methods of explainability because they have the strength to explain every feature and the structure of the model. This survey attempts to provide a comprehensive review of global interpretation methods that completely explain the behaviour of the AI models. We present a taxonomy of the available global interpretations models and systematically highlight the critical features and algorithms that differentiate them from local as well as hybrid models of explainability. Through examples and case studies from the literature, we evaluate the strengths and weaknesses of the global interpretation models and assess challenges when these methods are put into practice. We conclude the paper by providing the future directions of research in how the existing challenges in global interpretation methods could be addressed and what values and opportunities could be realized by the resolution of these challenges.

Cognitive Radio Network (CRN) is considered as a viable solution on Internet of Vehicle (IoV) where objects equipped with cognition make decisions intelligently through the understanding of both social and physical worlds. However, the spectrum availability and data sharing/transferring among vehicles are critical improving services and driving safety metrics where the presence of Malicious Devices (MD) further degrade the network performance. Recently, a blockchain technique in CRN-based IoV has been introduced to prevent data alteration from these MD and allowing the vehicles to track both legal and illegal activities in the network. In this paper, we provide the security to IoV during spectrum sensing and information transmission using CRN by sensing the channels through a decision-making technique known as Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS), a technique that evokes the trust of its Cognitive Users (CU) by analyzing certain predefined attributes. Further, blockchain is maintained in the network to trace every activity of stored information. The proposed mechanism is validated rigorously against several security metrics using various spectrum sensing and security parameters against a baseline solution in IoV. Extensive simulations suggest that our proposed mechanism is approximately 70% more efficient in terms of malicious nodes identification and DoS threat against the baseline mechanism.

Vehicular ad hoc network (VANET), a novel technology, holds a paramount importance within the transportation domain due to its abilities to increase traffic efficiency and safety. Connected vehicles propagate sensitive information which must be shared with the neighbors in a secure environment. However, VANET may also include dishonest nodes such as man-in-the-middle (MiTM) attackers aiming to distribute and share malicious content with the vehicles, thus polluting the network with compromised information. In this regard, establishing trust among connected vehicles can increase security as every participating vehicle will generate and propagate authentic, accurate, and trusted content within the network. In this article, we propose a novel trust model, namely, MiTM attack resistance trust model in connected vehicles (MARINE), which identifies dishonest nodes performing MiTM attacks in an efficient way as well as revokes their credentials. Every node running MARINE system first establishes trust for the sender by performing multidimensional plausibility checks. Once the receiver verifies the trustworthiness of the sender, the received data are then evaluated both directly and indirectly. Extensive simulations are carried out to evaluate the performance and accuracy of MARINE rigorously across three MiTM attacker models and the benchmarked trust model. The simulation results show that for a network containing 35% of MiTM attackers, MARINE outperforms the state-of-the-art trust model by 15%, 18%, and 17% improvements in precision, recall, and F-score, respectively.

Vehicular Ad-hoc NETworks (VANET) have revolutionised the intelligent transportation systems. Indeed, they enable vehicles to communicate with each other and with the infrastructure, and they facilitate several vital applications in real-time. Several trust models have been proposed to ensure a secured VANET and the authenticity, integrity and reliability of information exchanged in the network. The concept of trust models is to introduce and implement trust explicitly in the vehicular nodes. In this paper, we propose a lightweight evaluation methodology to evaluate trust models, specifically designed for VANET. Our study focused on the three categories of VANET trust models (TMs): Entity-oriented Trust Models (ETM), Data oriented Trust Models (DTM) and Combined Trust Models (CTM). Our simulations evaluate the efficiency of the trust models and compare them against several trust related parameters: false positive rate, precision and accuracy level in detecting malicious nodes. Since the scope of this research work is to evaluate the performance of TMs under adversary conditions, we have considered on-off attacks which can act as man-in-the-middle to drop and delay transmitted packets.

Named Data Networking (NDN) is a promising candidate for future internet architecture. It is one of the implementations of the Information-Centric Networking (ICN) architectures where the focus is on the data rather than the owner of the data. While the data security is assured by definition, these networks are susceptible of various Denial of Service (DoS) attacks, mainly Interest Flooding Attacks (IFA). IFAs overwhelm an NDN router with a huge amount of interests (Data requests). Various solutions have been proposed in the literature to mitigate IFAs; however; these solutions do not make a difference between intentional and unintentional misbehavior due to the network congestion. In this paper, we propose a novel congestion-aware IFA detection and mitigation solution. We performed extensive simulations and the results clearly depict the efficiency of our proposal in detecting truly occurring IFA attacks.

Frontal view gait recognition for people identification has been carried out using single RGB, stereo RGB, Kinect 1.0, and Doppler radar. However, existing methods based on these camera technologies suffer from several problems. Therefore, we propose a four-part method for frontal view gait recognition based on the fusion of multiple features acquired from a Time-of-Flight (ToF) camera. We have developed a gait data set captured by a ToF camera. The data set includes two sessions recorded seven months apart, with 46 and 33 subjects, respectively, each with six walks with five covariates. The four-part method includes: a new human silhouette extraction algorithm that reduces the multiple reflection problem experienced by ToF cameras; a frame selection method based on a new gait cycle detection algorithm; four new gait image representations; and a novel fusion classifier. Rigorous experiments are carried out to compare the proposed method with state-of-the-art methods. The results show distinct improvements over recognition rates for all covariates. The proposed method outperforms all major existing approaches for all covariates and results in 66.1% and 81.0% Rank 1 and Rank 5 recognition rates, respectively, in overall covariates, compared with a best state-of-the-art method performance of 35.7% and 57.7%.

A rich model-based motion vector (MV) steganalysis benefiting from both temporal and spatial correlations of MVs is proposed in this paper. The proposed steganalysis method has a substantially superior detection accuracy than the previous methods, even the targeted ones. The improvement in detection accuracy lies in several novel approaches introduced in this paper. First, it is shown that there is a strong correlation, not only spatially but also temporally, among neighbouring MVs for longer distances. Therefore, temporal MV dependency alongside the spatial dependency is utilized for rigorous MV steganalysis. Second, unlike the filters previously used, which were heuristically designed against a specific MV steganography, a diverse set of many filters, which can capture aberrations introduced by various MV steganography methods is used. The variety and also the number of the filter kernels are substantially more than that of used in the previous ones. Besides that, filters up to fifth order are employed whereas the previous methods use at most second order filters. As a result of these, the proposed system captures various decorrelations in a wide spatio-temporal range and provides a better cover model. The proposed method is tested against the most prominent MV steganalysis and steganography methods. To the best knowledge of the authors, the experiments section has the most comprehensive tests in MV steganalysis field, including five stego and seven steganalysis methods. Test results show that the proposed method yields around 20% detection accuracy increase in low payloads and 5% in higher payloads.

We propose a spatio-temporal rich model of motion vector planes as a part of a full steganalytic system against motion vector based steganography. Superior detection accuracy of the rich model over the previous methods has been lately demonstrated for digital images in both spatial and DCT domain. It has not been heretofore used for detection of motion vector steganography. We also introduced a transformation so as to extend the feature set with temporal residuals. We carried out the tests along with most recent motion vector steganalysis and steganography methods. Test results show that the proposed model delivers an outstanding performance compared to the previous methods.

While video surveillance systems have become ubiquitous in our daily life, this has also brought some serious privacy concerns. Therefore, recent research in this area has included a focus on privacy region protection. Existing video scrambling techniques are being applied to specific regions of interest in a video while the background is left unchanged. In this paper, a new method involving the encryption of intra prediction modes (IPM) is proposed for privacy region protection without drift error in I frames. Compared with a previous technique that uses encryption of IPM, the proposed method offers savings in the bitrate overhead. To enhance the scrambling effect for the privacy region, the proposed method can support the combination of IPM with encryption of the sign bits of nonzero quantized transform coefficients in the privacy region. Experimental results and analysis based on H.264/AVC were carried out and verify the effectiveness of the proposed method.

In this paper, a novel partial encryption method for video encoding is proposed. For video compression based on block transforms, two zig-zag scan orders can be used which provide similar compression performance. The proposed method involves randomly selecting one of these two scan orders. In addition, the sign bit of the DC coefficients can be flipped randomly and when employed with the proposed method provides a much better scrambling effect. In comparison to previous work in this area, experimental results based on H.264/AVC show that the proposed method can scramble the video with very minimal impact on the compression performance.

The heterogeneous computing revolution continues unabated. Yet despite the vast number of naïve users in possession of bespoke software hoping to embrace the opportunities that this revolution has wrought, few approaches proposed in current literature can guide such users in these efforts. The most appropriate choice would appear to be a (semi-)automating compiler. However, these typically target a single device-type and demand the unguided use of directives. Consequently, they are of little use when naïve users are seeking answers to more fundamental questions, such as: which fragments of a program can/should be parallelized, which device should each fragment target, and what speedup will be attained. To this end, this paper expands on previous work and proposes Paralysis - an extensible guidance environment, tiered for varying programmer competencies with support for static and dynamic analysis techniques. At the highest level, guided user experiences are paramount. At the lowest level, underlying functionality is exposed as a set of plug-ins, ensuring longevity. A partial prototype, built atop the Cetus infrastructure, is described. It is used to analyze two serial programs for CUDA execution - the DFT and the Box Blur Filter. Speedups of 15x and 22x are achieved on the basis of the analysis.

Recently, two fast selective encryption methods for context-adaptive variable length coding and context-adaptive binary arithmetic coding in H.264/AVC were proposed by Shahid In this paper, it was demonstrated that these two methods are not as efficient as only encrypting the sign bits of nonzero coefficients. Experimental results showed that without encrypting the sign bits of nonzero coefficients, these two methods can not provide a perceptual scrambling effect. If a much stronger scrambling effect is required, intra prediction modes, and the sign bits of motion vectors can be encrypted together with the sign bits of nonzero coefficients. For practical applications, the required encryption scheme should be customized according to a user's specified requirement on the perceptual scrambling effect and the computational cost. Thus, a tunable encryption scheme combining these three methods is proposed for H.264/AVC. To simplify its implementation and reduce the computational cost, a simple control mechanism is proposed to adjust the control factors. Experimental results show that this scheme can provide different scrambling levels by adjusting three control factors with no or very little impact on the compression performance. The proposed scheme can run in real-time and its computational cost is minimal. The security of the proposed scheme is also discussed. It is secure against the replacement attack when all three control factors are set to one.

Blind steganalysis of JPEG images is addressed by modeling the correlations among the DCT coefficients usingK-variate (K≥ 2) p.d.f. estimates (p.d.f.s) constructed by means of Markov random field (MRF) cliques. The reasoning of using high variate p.d.f.s together with MRF cliques for image steganalysis is explained via a classical detection problem. Although our approach has many improvements over the current state-of-the-art, it suffers from the high dimensionality and the sparseness of the high variate p.d.f.s. The dimensionality problem as well as the sparseness problem are solved heuristically by means of dimensionality reduction and feature selection algorithms. The detection accuracy of the proposed method(s) is evaluated over Memon's (30.000 images) and Goljan's (1912 images) image sets. It is shown that practically applicable steganalysis systems are possible with a suitable dimensionality reduction technique and these systems can provide, in general, improved detection accuracy over the current state-of-the-art. Experimental results also justify this assertion.

Privacy region protection in video surveillance systems is an active topic at present. In previous research, a binary mask mechanism has been developed to indicate the privacy region; however this incurs a significant bitrate overhead. In this paper, an adaptive binary mask is proposed to represent the privacy region. In a practical privacy region protection application, in which the privacy region typically occupies less than half of the overall frame and is rectangular or approximately rectangular, the proposed adaptive binary mask can effectively reduce the bitrate overhead. The proposed method can also be easily applied to the FMO mechanism of H.264/AVC, providing both error resilience and a lower bitrate overhead.

In this paper we present a novel method based on singular value decomposition (SVD) for forensic analysis of digital images. We show that image tampering distorts linear dependencies of image rows/columns and derived features can be accurate enough to detect image manipulations and digital forgeries. Extensive experiments show that the proposed approach can outperform the counterparts in the literature.

This paper is concerned with the universal (blind) image steganalysis problem and introduces a novel method to detect especially spatial domain steganographic methods. The proposed steganalyzer models linear dependencies of image rows/columns in local neighborhoods using singular value decomposition transform and employs content independency provided by a Wiener filtering process. Experimental results show that the novel method has superior performance when compared with its counterparts in terms of spatial domain steganography. Experiments also demonstrate the reasonable ability of the method to detect discrete cosine transform-based steganography as well as the perturbation quantization method.

In this paper, a new blind and readable H.264 compressed domain watermarking scheme is proposed in which the embedding/extracting is performed using the syntactic elements of the compressed bit stream. As a result, it is not necessary to fully decode a compressed video stream both in the embedding and extracting processes. The method also presents an inexpensive spatiotemporal analysis that selects the appropriate submacroblocks for embedding, increasing watermark robustness while reducing its impact on visual quality. Meanwhile, the proposed method prevents bit-rate increase and restricts it within an acceptable limit by selecting appropriate quantized residuals for watermark insertion. Regarding watermarking demands such as imperceptibility, bit-rate control, and appropriate level of security, a priority matrix is defined which can be adjusted based on the application requirements. The resulted flexibility expands the usability of the proposed method.

A change detection framework which fuses both spatial and temporal data using fuzzy if-then rules is presented. Temporal data is used on a per-pixel basis to monitor the sequence for changes by employing a fuzzy codebook model. Spatial data is gathered using a fuzzy multithresholding algorithm that decomposes the RGB color space into three color pair histograms. This system is found to be robust to noise and allows the algorithm to process successfully even when the underlying sequences result in under-segmentation of the spatial data.

This paper introduces a novel universal steganalysis method in order to attack especially spatial domain steganographic algorithms. The basic idea behind the proposed method is twofold: The first is the capability of modeling linear dependencies of image rows/columns in local neighborhoods and the second is the normalization of different energy levels for different images. This idea is simply realized with integrating the logarithms of singular values calculated over image sub blocks resulting to a novel staganalyser, named as "LogSv". We consider three popular spatial domain steganographic algorithms; LSB, Hide4pgp, Steghide, five DCT domain steganographic algorithms; F5, Outguess, JP Hide&Seek, MB1, MB2 and PQ. Performance of the proposed method is compared with the state-of-the-art steganalysers.

Palmprint trait is emerging as a new and practical biometric solution and a few systems using full palmprints have been proposed. However, partial palmprints left at scenes of crime have not yet been exploited to recognize and find crime suspects. In this paper, a modified well known algorithm, referred to as modified phase only correlation (MPOC) is proposed to match poor quality (degraded) partial palmprints left by suspects at crime scenes against a full palmprint registered in a template database. Instead of using the conventional peak as the matching score between two palmprint images, the ratio of the conventional peak to the highest peak in the outside-lobe correlation plane is employed. Experiments were conducted on a generated database of 800 partial palmprints having an area less than 25% of that of the full palmprint images from which blurred and degraded images were created by adding an intense synthetic Gaussian noise. The results show that the proposed method yields high recognition performance thus demonstrating its ability to tackle the problem of identifying low quality partial palmprint images giving an equal error rate (EER) less than 0.4%.

This paper presents a singular value decomposition (SVD) based steganalysis technique to determine the watermarking method used to embed a watermark in an image. The detection is carried out in three steps. First, the proposed technique determines whether an image under consideration contains a watermark. If a watermark is detected, the embedding domain is revealed. Finally, the exact watermarking algorithm is named. The idea behind the method is that when the image is watermarked, relative and strict linear dependencies of rows/columns will differ from the original image and this can be modeled by the analysis of SVD. By using SVD, several features for the classification of the original and watermarked images are defined. The classification operation including both a linear and a SVM classifier is performed with a feature selection algorithm, which serves to reduce the number of features and to increase the detection performance. The performance of the proposed technique is promising and simulation results indicate that the chosen features can reliably detect the watermarking domain as well as the watermarking method.

This paper presents a new approach for palmprint recognition using a combined Fisher linear discriminant (FLD) and Gabor Wavelet responses. Gabor wavelets have properties of being more robust to image illuminations, small translations, limited rotations and having a superior feature representation in both spatial and frequency domains. On the other hand, FLD seeks those projections that are efficient for data discrimination and produces well separated classes in low-dimensional subspaces. The new combined method involves convolving a palmprint image with a series of Gabor wavelets at different scales and rotations before extracting features from the resulting Gabor filtered images. Linear discriminant analysis is then applied to the feature vectors for dimension reduction as well as class separability. Experiments show that the proposed method yields a high classification rate even when using a simple classifier when compared with other popular approaches reported in the literature.

A motion detection framework is presented that integrates spatial and temporal data by decomposition of the feature space. Temporal data is employed to monitor frame changes on a per-pixel basis, whilst the spatial data is used to provide region-based segmentation of image frames. The thresholded difference image from the change detection is then fused with the segmented image. It is found that this framework greatly improves robustness to noise, while retaining and, in some cases, improving the sensitivity to regions of interest. Further, the decomposition reduces the time required to run due to the reduction in computational complexity.

Segmentation is one of the first and most integral pre-processing steps for any fingerprint recognition system. It is used to identify the region of interest within an image. Performance of segmentation algorithms is dependent on the type of features and threshold values selected. In this paper we propose a robust segmentation algorithm which utilizes the strength of Harris corners for segmentation. The algorithm employs dynamic thresholding and simple binary operations to provide highly accurate segmentation of the image. Experimental results prove that the algorithm provides very accurate segmentation even for low quality images.

This letter proposes an efficient extension of the set partitioning embedded block (SPECK) algorithm to lossless multispectral image coding. Such a wavelet-based coder is widely referred to in the literature, especially for lossless image coding, and is considered to be one of the most efficient techniques exhibiting very low computational complexity when compared with other state-of-the-art coders. The modification proposed in this letter is simple and provides significant improvement over the conventional SPECK. The key idea is to join each group of two consecutive wavelet-transformed spectral bands during the SPECK coding since they show high similarities with respect to insignificant sets at the same locations. Simulation results, carried out on a number of test images, demonstrate that this grouping procedure considerably saves on the bit budget for encoding the multispectral images.

In this paper, the compression of multispectral images is addressed. Such 3-D data are characterized by a high correlation across the spectral components. The efficiency of the state-of-the-art wavelet-based coder 3-D SPIHT is considered. Although the 3-D SPIHT algorithm provides the obvious way to process a multispectral image as a volumetric block and, consequently, maintain the attractive properties exhibited in 2-D (excellent performance, low complexity, and embeddedness of the bit-stream), its 3-D trees structure is shown to be not adequately suited for 3-D wavelet transformed (DWT) multispectral images. The fact that each parent has eight children in the 3-D structure considerably increases the list of insignificant sets (LIS) and the list of insignificant pixels (LIP) since the partitioning of any set produces eight subsets which will be processed similarly during the sorting pass. Thus, a significant portion from the overall bit-budget is wastedly spent to sort insignificant information. Through an investigation based on results analysis, we demonstrate that a straightforward 2-D SPIHT technique, when suitably adjusted to maintain the rate scalability and carried out in the 3-D DWT domain, overcomes this weakness. In addition, a new SPIHT-based scalable multispectral image compression algorithm is used in the initial iterations to exploit the redundancies within each group of two consecutive spectral bands. Numerical experiments on a number of multispectral images have shown that the proposed scheme provides significant improvements over related works.

This paper presents an investigation on the optimum detection of multiplicative watermarks based on statistical behaviour of image contents in the transform domain. In recent works, the problem of watermark detection is viewed as a binary decision where the observation is the possibly watermarked transformed coefficients. Indeed, the detector verifies whether the watermark presented to its input is actually embedded in the input image (hypothesis HI) or not (hypothesis HQ). Such a detection scheme relies on the Neyman-Pearson criterion to derive a decision threshold by minimising the probability of missed detection with respect to a given probability of false alarm. Previous works approximate the probability density function (pdf) of the observation when hypothesis HQ holds by the pdf when hypothesis of having no watermark embedded in the input image is in force by assuming that the watermark strength is weak to some extent. However, the weakness of the watermark does fulfil the requirement on the robustness. Moreover, from the viewpoint of the decision theory, the smaller the embedding depth, the worse the watermark detection. This paper describes the drawback behind this approximation in the general case and proposes an efficient solution closer to the theoretical derivation. To validate the proposed technique, we consider a special case in which the Laplace statistical model is used.

This paper proposes an adaptive blind image watermarking technique based on wavelet transform using a random sequence of real numbers. First, the image is decomposed into non overlapping blocks. Then, each block is classified as uniform or non uniform by using a JND-based classifier. The strength of the embedded watermark into the high subband coefficients of each transformed block depends upon the nature of the block according to its classification. The Neyman-Pearson criterion is used to derive the detection rule. Unlike the embedding process, the detection does not require any classification of blocs. This adaptive approach has been assessed on various standard images and compared with a similar watermarking technique (H. Inoue et al., 1999). The results have shown an obvious improvement in terms of robustness against different manipulations and a better ability of detection

We propose an efficient extension of set partitioning in hierarchical trees (SPIHT) for very low bit-rate wavelet based color image coding. Since the chrominance components I and Q in the YIQ format are sufficiently less significant in terms of energy compared to the luminance component, the trees within each chrominance plane are joined together in the list of insignificant sets (LIS) according to a virtual relationship parent-descendants specific to the chrominance components. For generating a fully embedded bit stream similar to SPIHT, the proposed method improves the performance of the color SPIHT based scheme, especially for very low bit rate.

This paper addresses the problem of automatic segmentation of nuclei in histopathological images. A novel method, inspired from active contour models is proposed. An evolutionary based approach, which guarantees convergence to global minimum energies has been used to solve the combinatorial optimization problem of snakes. The computational complexity, often associated with evolutionary approaches, has been reduced by short cutting the natural evolution step by means of replacing standard mutation with an oriented stochastic mutation process. Results have shown the efficiency of this method both in terms of accuracy and fast computation.

Grey level co-occurrence matrix (GLCM), one of the best known tool for texture analysis, estimates image properties related to second-order statistics. These image properties commonly known as Haralick texture features can be used for image classification, image segmentation, and remote sensing applications. However, their computations are highly intensive especially for very large images such as medical ones. Therefore, methods to accelerate their computations are highly desired. This paper proposes the use of reconfigurable hardware to accelerate the calculation of GLCM and Haralick texture features. The performances of the proposed co-processor are then assessed and compared against a microprocessor based solution.

The paper is concerned with the development of an unsupervised segmentation algorithm for multispectral images. Due to the high dimensionality of these images, the underlining motivation of this work is on how to build up a robust unsupervised segmentation algorithm with acceptable computational complexity. After an initial approximate segmentation using the EM algorithm, a cost function associated to each pixel is proposed. This function includes a term that measures how close the pixel at hand is to the region's distribution centroids, and another term that measures the local homogeneity in the pixel's neighborhood. In addition, an edge progression technique is used to re-label pixels optimally. Extensive experiments have been carried out on many multispectral images and quantitative results have shown the efficiency of the approach.

An improved segmentation algorithm is proposed, which implements the MAP estimation of the label field using a Constraint Satisfaction Neural Network (CSNN). It uses the advantages of stochastic relaxation with those of Gauss-Markov Random Field (GMRF) models. The performance of the algorithm is compared vis-a-vis alternate relaxation schemes using both synthetic and real images.