Block Classification Research Articles

Improved Sparse 3D Transform-Domain Collaborative Filter for Screen Content Image Denoising

Screen content videos or images are widely used in applications such as screen sharing. Compressed screen content videos or images may have distortions or noises because of the quantization process. This paper proposes an improved sparse 3D transform-domain collaborative filter to enhance screen content image quality by block classification and block segmentation. Experimental results show that the proposed algorithm achieves a peak signal-to-noise ratio increase and subjective visual quality improvements for reconstructed screen content images.

Building block extraction and classification by means of aerial images fused with super-resolution reconstructed elevation data

The detailed three-dimensional modeling of buildings utilizing elevation data, such as those provided by light detection and ranging (LiDAR) airborne scanners, is increasingly demanded today. There are certain application requirements and available datasets to which any research effort has to be adapted. Our dataset includes aerial orthophotos, with a spatial resolution 20 cm, and a digital surface model generated from LiDAR, with a spatial resolution 1 m and an elevation resolution 20 cm, from an area of Athens, Greece. The aerial images are fused with LiDAR, and we classify these data with a multilayer feedforward neural network for building block extraction. The innovation of our approach lies in the preprocessing step in which the original LiDAR data are super-resolution (SR) reconstructed by means of a stochastic regularized technique before their fusion with the aerial images takes place. The Lorentzian estimator combined with the bilateral total variation regularization performs the SR reconstruction. We evaluate the performance of our approach against that of fusing unprocessed LiDAR data with aerial images. We present the classified images and the statistical measures confusion matrix, kappa coefficient, and overall accuracy. The results demonstrate that our approach predominates over that of fusing unprocessed LiDAR data with aerial images.

Cloud image watermarking: high quality data hiding and blind decoding scheme based on block truncation coding

Cloud computing is an Internet-based computing model that shares computing resources such as computers, servers, and storage. In future smart cities, new applications can take advantage of cloud computing; for example, a cloud-based home health-care system can provide immediate disease management by analyzing medical images. However, if the size of cloud data is large (e.g., medical images), their transition through the Internet is time consuming. Cloud data authentication is another problem that should be addressed. To address the aforementioned problems, this study presents a novel data hiding method based on the block truncation coding (BTC) image compression technique. This method has two advantages: reduces image size and increases security. This study also proposes a block classification scheme for determining smooth blocks, complex_1 blocks, and complex_2 blocks in an image. Secret data are embedded in these three block types using different approaches. To improve the quality of images without damaging the secret data, we propose a progressive data hiding strategy and integrating an iteration-based halftoning method into BTC. When decoding, the secret data are extracted without recalling the original image. According to experimental results, the proposed method outperforms existing methods in both embedding capacity and image quality evaluations.

Coronal Mass Ejections detection using multiple features based ensemble learning

Coronal Mass Ejection (CME) is a major solar activity that affects the earth, thus CMEs detection is of great importance for space weather forecast, disaster prevention and reduction. We model the detection of Coronal Mass Ejections (CMEs) as the classification of the brightest block in the current running difference image. Because CMEs usually correspond to the areas with high gray values or complex texture features, multiple features including gray features and texture features are extracted to represent the brightest block. And classifier is designed based on these features. Our method includes four steps: first, because the CMEs spread along the radial direction of the sun, in order to facilitate the analysis, the original coordinate is transformed into the polar coordinate; Secondly, because the typical appearance of the CMEs is bright or complex texture enhancement, we use the brightest block to represent the whole image; Thirdly, we extract the gray, texture and HOG features of the brightest gray blocks. Finally, we use the extracted features to design decision trees as the base classifiers, and AdaBoost is used to obtain the final ensemble classifier. As far as we know, this is the first time that the learning based classification framework is presented in the CMEs detection. Moreover, multiple feature fusion is first used to model the various CMEs. Experimental results show that the integration of multi-feature based detection algorithm proposed can achieve better detection results.

Efficient PVO-based reversible data hiding using multistage blocking and prediction accuracy matrix

In recent years, pixel value ordering based reversible data hiding has become a hot research topic for its high-fidelity. In this approach, only the maximum and minimum of pixel block are predicted and modified to embed data and the preservation of pixel values order guarantees the reversibility. So far, the optimal block size can only be exhaustively searched until Wang et al. propose the dynamic blocking strategy which enables the combination of two various-sized blocks. By further dividing flat block into four sub-blocks to retain larger embedding capacity, dynamic blocking can employ less high complexity blocks for a given embedding capacity. However, the lack of host image dependent automatic block classification mechanism still exposes the fact that their work is far from efficient and comprehensive. In this paper, to address this drawback and to better exploit image redundancy, a really efficient and more comprehensive blocking strategy namely multistage blocking is proposed. High efficiency lies in prediction accuracy matrix based thresholds determination, which enables infinitely extended multistage blocking in theory. The superiority of the proposed scheme is also experimentally verified.

A new robust video watermarking algorithm based on SURF features and block classification

In this paper, we propose a robust block classification based semi-blind video watermarking algorithm using visual cryptography and SURF (Speed-Up Robust Features) features to enhance the robustness, stability, imperceptibility and real-time performance. A method of selecting the best frames in each shot and the best regions or blocks within best frames is proposed to avoid employing frame---by-frame method for generating owner's share in order to enhance robustness as well as reducing time complexity. In our method, Owner's share is generated using the classification of selected robust blocks within the chosen frames along with corresponding watermark information. In extraction process, the SURF features are employed to match the feature points of selected frames with all frames to detect selected frames. Moreover, we resynchronize the embedded regions from distorted video to original sequence using SURF feature points matching. Afterwards, based on these matched feature points, rotation and scaling parameters are estimated next, selected blocks are retrieved using side information being stored eventually, watermark information is reconstructed successfully. Selecting Best frames, best regions, and employing surf features make our method to be highly robust against various kinds of attacks including image processing attacks, geometrical attacks and temporal attacks. Experimental results confirm the superiority of our scheme in case of being applicable in the real world, enhancing robustness and exploiting idea imperceptibility, over previous related methods.

Fast‐efficient shape error concealment technique based on block classification

This study presents a fast-efficient error concealment method for recovering information related to shape. The proposed technique comprises block classification, edge direction interpolation and filtering interpolation. Missing blocks are classified into four categories: transparent, opaque, edge and isolated blocks. Most of the computation is spent on edge blocks and isolated blocks to maximise the cost and performance tradeoff. For the recovery of edge blocks, the edge slope is computed by referring to the nearest available block, from which the missing shape is interpolated parallel to the edge. Isolated blocks are dealt with using a cascade filter to approximate the actual shape. Experimental results show that the proposed method provides better cost performance in the restoration of shapes than that afforded by comparable algorithms, both in numerical parameters and the resulting shapes. The processing speed is approximately two to three times faster than previous methods and low computational load makes the proposed technique applicable to real-time MPEG-4 systems.

Selecting the maximum acceptable error in data minimising financial losses

Geological and grade models in the mining industry provide information that is used from the project phase until the short-term planning phase. Since model precision and accuracy depends strongly on data quality, data generation is subject to quality assurance and quality control (QA/QC) protocols that typically adopt error tolerance limits based on reference values. This paper proposes tolerance limits based on the relation between data acquisition costs and block misclassification rate sensitivity to data uncertainty. Using several scenarios generated by adding errors to sampled grades, approach applied to the Miraí bauxite deposit (Brazil) defined the optimum sampling error (measured by its CV) ranging within 6 and 15%. Moreover, sequential Gaussian simulation block classification performed better and was less sensitive to sampling uncertainty than ordinary kriging. The proposed approach results showed that sampling error optimisation is an opportunity to improve mine’s profitability that must be carefully investigated even in benchmark mines.

A simple computational framework for defect detection system with orthogonal polynomials transcoded coefficients

In this paper, a simple computational framework to propose a generic defect detection system based on orthogonal polynomials transcoded coefficients, with a statistical procedure is presented. Initially, the defective input image is partitioned into blocks and subjected to orthogonal polynomials transformation. The resulting coefficients are then applied with a modified lifting scheme, to produce transcoded coefficients with reduced block size. These coefficients are modeled as a probability distribution to propose a block classification scheme that classifies the block under investigation to have dominantly either texture or edge or smooth with total number of transcoded coefficients that are above the mean of the sample. With simple statistical procedure, we then introduce a new defect detection technique on each of these block classification result. The proposed defect detection technique employs homogeneity among variance of transcoded coefficients with Box’s M Test, and group distribution model to verify the presence of defect in texture and edge block respectively. By analyzing the magnitude of transcoded coefficients, defective blocks in a smooth region are identified. The proposed defect detection system, an application independent, is experimented with natural images and few measures are introduced with a simple Defect Measurement Matrix (DMM) to analyze the performance of the proposed system. The applicability of the proposed scheme is also extended to identify defects in fabrics.

Block Classification and Transmission of Compressed Image with Bit Allocation and Unequal Error Protection

Block Classification and Transmission of Compressed Image with Bit Allocation and Unequal Error Protection

Detection of Cardiac Abnormalities from Multilead ECG using Multiscale Phase Alternation Features

The cardiac activities such as the depolarization and the relaxation of atria and ventricles are observed in electrocardiogram (ECG). The changes in the morphological features of ECG are the symptoms of particular heart pathology. It is a cumbersome task for medical experts to visually identify any subtle changes in the morphological features during 24 hours of ECG recording. Therefore, the automated analysis of ECG signal is a need for accurate detection of cardiac abnormalities. In this paper, a novel method for automated detection of cardiac abnormalities from multilead ECG is proposed. The method uses multiscale phase alternation (PA) features of multilead ECG and two classifiers, k-nearest neighbor (KNN) and fuzzy KNN for classification of bundle branch block (BBB), myocardial infarction (MI), heart muscle defect (HMD) and healthy control (HC). The dual tree complex wavelet transform (DTCWT) is used to decompose the ECG signal of each lead into complex wavelet coefficients at different scales. The phase of the complex wavelet coefficients is computed and the PA values at each wavelet scale are used as features for detection and classification of cardiac abnormalities. A publicly available multilead ECG database (PTB database) is used for testing of the proposed method. The experimental results show that, the proposed multiscale PA features and the fuzzy KNN classifier have better performance for detection of cardiac abnormalities with sensitivity values of 78.12 %, 80.90 % and 94.31 % for BBB, HMD and MI classes. The sensitivity value of proposed method for MI class is compared with the state-of-art techniques from multilead ECG.

FPGA implementation of cost-effective robust Canny edge detection algorithm

Implementation of Canny edge detection algorithm significantly outperforms the existing edge detection techniques in many computer vision algorithms. However, Canny edge detection algorithm is complex, time-consuming process with high hardware cost. To overcome these issues, a novel Canny edge detection algorithm is proposed in block level to detect edges without any loss. It uses sobel operator, approximation methods to compute gradient magnitude and orientation for replacing complex operations with reduced hardware cost, existing non-maximum suppression, block classification for adaptive thresholding and existing hysteresis thresholding. Pipelining is introduced to reduce latency. The proposed algorithm is implemented on Xilinx Virtex-5 FPGA and it provides better performance compared to frame-level Canny edge detection algorithm. The synthesized architecture reduces execution time by 6.8 % and utilizes less resource to detect edges of 512 × 512 image compared to existing distributed Canny edge detection algorithm.

TBM–Block Interaction during TBM Tunneling in Rock Masses: Block Classification and Identification

A new block-classification method for tunnel construction using a tunnel-boring machine (TBM) to capture the geometrical and mechanical transformation of rock blocks in the course of TBM excavation is proposed in this paper. The machine–block interaction is interpreted by dividing the joint blocks into blocks influenced by TBM excavation and blocks uninfluenced by TBM excavation. The influenced blocks are categorized further as contacting or noncontacting blocks according to whether they are in contact with the TBM. The contacting blocks include the front block, the corner block, and the rear block, based on the spatial location of blocks with respect to the cutterhead. Different types of blocks have distinct kinematic and mechanical characteristics. The sizes and shapes evolve, and the categories may be changed for rock blocks during excavation. The identification algorithms for influenced blocks and three types of contacting blocks are presented. Finally, a simple example considering a double-shield TBM tunnel excavation is used to illustrate the effectiveness of the new block-classification approach to guide TBM tunneling. The new classification approach will be helpful in evaluating the block removability and the possibility of cutterhead clogging and to shield blockage during tunneling with a TBM.

A novel data-hiding and compression scheme based on block classification of SMVQ indices

This paper presents a novel, reversible, data hiding and compression scheme that hides secret data into an SMVQ-compressed image and obtains reversibility of the reconstructed SMVQ indices. The SMVQ indices are divided into index block sized 2×2, and four indices in each index-block are processed simultaneously. Fifteen types and four cases are defined for data embedding. Four index values in the sequence are considered together to find a corresponding case and type. Then, the pre-determined number of secret bits is embedded into each index block based on to which case or type of index block the secret bits belong. By processing a block of indices simultaneously, the proposed scheme obtains high embedding capacity, high embedding rate, and low compression rate. In addition, three different configurations, i.e., normal hiding, under hiding, and over hiding schemes, are used to achieve better improvement of the proposed scheme than several previous applications. As shown in the experimental results, the proposed scheme obtains greater efficiency than various existing schemes in terms of embedding capacity, embedding rate, and compression rate.

Detection, Reconstruction and Segmentation of Chronic Wounds Using Kinect v2 Sensor

The advent of inexpensive RGB-D sensors pioneered by the original Kinect sensor, has paved the way for a lot of innovations in computer and robot vision applications. In this article, we propose a system which uses the new Kinect v2 sensor in a medical application for the purpose of detection, 3D reconstruction and segmentation of chronic wounds. Wound detection is based on a per block classification of wound tissue using colour histograms and nearest neighbour approach. The 3D reconstruction is similar to KinectFusion where ICP is used for determining rigid body transformation. Colour enhanced TSDF is applied for scene fusion, while the Marching cubes algorithm is used for creating the surface mesh. The wound contour is extracted by a segmentation procedure which is driven by geometrical and visual properties of the surface. Apart from the segmentation procedure, the entire system is implemented in CUDA which enables real-time operation. The end result of the developed system is a precise 3D coloured model of the segmented wound, and its measurable properties including perimeter, area and volume, which can be used for determining a correct therapy and treatment of chronic wounds. All experiments were conducted on a medical wound care model.

Error concealment for the transmission of H.264/AVC-compressed 3D video in color plus depth format

An error concealment method for the transmission of 3D video in color/depth dual stream format (i.e., separately encoded) is proposed. We consider frame losses of color or depth along error-prone channels. Based on motion vector extrapolation from previous decoded frames, lost frames can be reconstructed. Specifically, the received information of one kind (color or depth) is intensively used when recovering a lost frame of the other kind. Our contributions come from classification of blocks into different kinds for different processing, joint color/depth matching, and shape-adaptive motion compensation. According to experiments, our proposed method, against traditional MV extrapolation (for color) and MV sharing (for depth) schemes, has shown distinctive gains in both color and depth. Our algorithm is effective in retaining integrity and smoothness of object boundaries, which is important to view synthesis for 3D display.

High capacity data hiding for binary image based on block classification

Data hiding is a technique by which secret data can be delivered securely by embedding it into a cover multimedia document. In this paper, a high capacity data hiding scheme based on block classification is proposed for binary images. In the proposed scheme, the block classification process determines complex regions in the image used for embedding secret data. For each block in the complex region of the image, some secret bits are embedded by lightly modifying few pixels to minimize an embedding distortion. On the receiver side, the secret bits can be then extracted without requiring the original image. Experimental results demonstrated that the proposed scheme obtained a high embedding capacity while maintaining a low distortion. In addition, when compared with previous schemes for binary images, the proposed scheme improved the embedding capacity significantly with the same level of embedding distortion.

A decision-support tool for the control of urban noise pollution.

Improving the quality of life is increasingly seen as an important urban planning goal. In order to reach it, various tools are being developed to mitigate the negative impacts of human activities on society. This paper develops a methodology for quantifying the population's exposure to noise, by proposing a classification of urban blocks. Taking into account the vehicular flow and traffic composition of the surroundings of urban blocks, we generated a noise map by applying a computational simulation. The urban blocks were classified according to their noise range and then the population was estimated for each urban block, by a process which was based on the census tract and the constructed area of the blocks. The acoustical classes of urban blocks and the number of inhabitants per block were compared, so that the population exposed to noise levels above 65 dB(A) could be estimated, which is the highest limit established by legislation. As a result, we developed a map of the study area, so that urban blocks that should be priority targets for noise mitigation actions can be quickly identified.

Learning discriminant DCT coefficients driven block descriptor for digital dropout detection system in degraded archived media

Digitization of old archived media is of great importance to preserve the originality of medium in terms of historical record as well as the means to quality improvement for reproduction purposes. However, digitization increases the exposure of the media to digital dropout error, thus presenting a significant degradation in perceptual quality of the converted video sequences. A numbers of mechanisms were investigated in the past to make these converted media more robust against digital dropout errors. Nevertheless, these techniques achieved little success, forcing manual quality check to assure standard quality. This paper presents an automatic solution to this problem based on discriminant DCT coefficients. Here, the idea is to build a block classification model by learning discriminant DCT coefficients first and utilize these coefficients along with an weighted neighborhood sampling strategy to formulate discriminant block descriptor so that within-class difference of the block features is minimized and between-class difference is maximized. This spatial detection is free from motion computation; thus performs accurately in presence of pathological motion (PM) and fast moving objects. Finally, the proposed method is compared against the existing methods to demonstrate improved detection accuracy using real degraded video archives.

Fractal image coding algorithm using particle swarm optimisation and hybrid quadtree partition scheme

In this study, a novel fractal image coding algorithm using particle swarm optimisation (PSO) and hybrid quadtree partition (QP) scheme is proposed. A method called PSO strategy based on range block classification (PSO-RC) is presented instead of utilising the PSO method in the whole range pool. This new idea can enhance the compression ratio significantly and speed up the encoder. Moreover, a PSO-RC hybrid QP (PSO-RCQP) scheme is adopted in order to improve the quality of the retrieved image further. Firstly, the range blocks are divided into two categories based on the standard deviation feature. Secondly, the range blocks are encoded using either the PSO approach or storing the average pixel values directly. Thirdly, the range blocks with large matching errors when using PSO scheme employ the proposed QP method. The simulation results show that the proposed algorithm can obtain good quality and higher compression ratio other than shorten the encoding time.