Search results

This paper aims to improve the performance of approximate multiplier in terms of peak signal to noise ratio (PSNR) and quality of the image.

The paper proposes an approximate circuit for 4:2 compressor, which shows a significant amount of improvement in performance metrics than that of the existing designs. This paper also reports a hybrid architecture for the Dadda multiplier, which incorporates proposed 4:2 compressor circuit as a basic building block.

Hybrid Dadda multiplier architecture is used in a median filter for image de-noising application and achieved 20% more PSNR than that of the best available designs.

The proposed 4:2 compressor improves the error metrics of a Hybrid Dadda multiplier.

Pervasive health-care computing applications in medical field provide better diagnosis of various organs such as brain, spinal card, heart, lungs and so on. The purpose of this study is to find brain tumor diagnosis using Machine learning (ML) and Deep Learning(DL) techniques. The brain diagnosis process is an important task to medical research which is the most prominent step for providing the treatment to patient. Therefore, it is important to have high accuracy of diagnosis rate so that patients easily get treatment from medical consult. There are many earlier investigations on this research work to diagnose brain diseases. Moreover, it is necessary to improve the performance measures using deep and ML approaches.

In this paper, various brain disorders diagnosis applications are differentiated through following implemented techniques. These techniques are computed through segment and classify the brain magnetic resonance imaging or computerized tomography images clearly. The adaptive median, convolution neural network, gradient boosting machine learning (GBML) and improved support vector machine health-care applications are the advance methods used to extract the hidden features and providing the medical information for diagnosis. The proposed design is implemented on Python 3.7.8 software for simulation analysis.

This research is getting more help for investigators, diagnosis centers and doctors. In each and every model, performance measures are to be taken for estimating the application performance. The measures such as accuracy, sensitivity, recall, F1 score, peak-to-signal noise ratio and correlation coefficient have been estimated using proposed methodology. moreover these metrics are providing high improvement compared to earlier models.

The implemented deep and ML designs get outperformance the methodologies and proving good application successive score.

This paper aims to overview the current status of development and application of digital image processing technology used for the yarn hairiness evaluation.

Digital image processing technology is one of the new methods used for the yarn detection, which can be used for the digital characterization and objective evaluation of yarn appearance. The comparison between the traditional detection methods and this new developed method was made and analyzed.

Compared with the traditional methods, image-based methods have the advantages of being objective, fast and accurate. Therefore, it was proved that digital image processing techniques should be a new trend in terms of the yarn appearance evaluation.

This paper aims to explore a new wavelet adaptive threshold de-noising method to resolve the shortcomings of wavelet hard-threshold method and wavelet soft-threshold method, which are usually used in gear fault diagnosis.

A new threshold function and a new determined method of threshold for each layer are proposed. The principle and the implementation of the algorithm are given. The simulated signal and the measured gear fault signal are analyzed, and the obtained results are compared with those from wavelet soft-threshold method, wavelet hard-threshold method and wavelet modulus maximum method.

The presented wavelet adaptive threshold method overcomes the defects of the traditional wavelet threshold method, and it can effectively eliminate the noise hidden in the gear fault signal at different decomposition scales. It provides more accurate information for the further fault diagnosis.

A new threshold function is adopted and the multi-resolution unbiased risk estimation is used to determine the adaptive threshold, which overcomes the defect of the traditional wavelet method.

An image contrast enhancement is one of the most important low‐level image pre‐processing tasks required by the vision‐based advanced driver assistance systems (ADAS). This paper seeks to address this important issue keeping the real time constraints in focus, which is especially vital for the ADAS.

The approach is based on a paradigm of nonlinear‐coupled oscillators in image processing. Each layer of the colored images is treated as an independent grayscale image and is processed separately by the paradigm. The pixels with the lowest and the highest gray levels are chosen and their difference is enhanced to span all the gray levels in an image over the entire gray level range, i.e. [0 1]. This operation enhances the contrast in each layer and the enhanced layers are finally combined to produce a color image of a much improved quality.

The approach performs robust contrast enhancement as compared to other approaches available in the relevant literature. Generally, other approaches do need a new setting of parameters for every new image to perform its task, i.e. contrast enhancement. These approaches are not useful for real‐time applications such as ADAS. Whereas, the proposed approach presented in this paper performs contrast enhancement for different images under the same setting of parameters, hence giving rise to the robustness in the system. The unique setting of parameters is derived through a bifurcation analysis explained in the paper.

The proposed approach is novel in different aspects. First, the proposed paradigm comprises of coupled differential equations, and therefore, offers a continuous model as opposed to other approaches in the relevant literature. This continuity in the model is an inherent feature of the proposed approach, which could be useful in realizing real‐time image processing with an analog implemented circuit of the approach. Furthermore, a novel framework combining coupled oscillatory paradigm and cellular neural network is also possible to achieve ultra‐fast solution in image contrast enhancement.

Surveillance is the emerging concept in the current technology, as it plays a vital role in monitoring keen activities at the nooks and corner of the world. Among which moving object identifying and tracking by means of computer vision techniques is the major part in surveillance. If we consider moving object detection in video analysis is the initial step among the various computer applications. The main drawbacks of the existing object tracking method is a time-consuming approach if the video contains a high volume of information. There arise certain issues in choosing the optimum tracking technique for this huge volume of data. Further, the situation becomes worse when the tracked object varies orientation over time and also it is difficult to predict multiple objects at the same time. In order to overcome these issues here, we have intended to propose an effective method for object detection and movement tracking. In this paper, we proposed robust video object detection and tracking technique. The proposed technique is divided into three phases namely detection phase, tracking phase and evaluation phase in which detection phase contains Foreground segmentation and Noise reduction. Mixture of Adaptive Gaussian (MoAG) model is proposed to achieve the efficient foreground segmentation. In addition to it the fuzzy morphological filter model is implemented for removing the noise present in the foreground segmented frames. Moving object tracking is achieved by the blob detection which comes under tracking phase. Finally, the evaluation phase has feature extraction and classification. Texture based and quality based features are extracted from the processed frames which is given for classification. For classification we are using J48 ie, decision tree based classifier. The performance of the proposed technique is analyzed with existing techniques k-NN and MLP in terms of precision, recall, f-measure and ROC.

The purpose of this paper is to find an efficient fabric defect detection algorithm by means of exploring the sparsity characteristics of main local binary pattern (MLBP) extracted from the original fabric texture.

In the proposed algorithm, original LBP features are extracted from the fabric texture to be detected, and MLBP are selected by occurrence probability. Second, a dictionary is established with MLBP atoms which can sparsely represent all the LBP. Then, the value of the gray-scale difference between gray level of neighborhood pixels and the central pixel, and the mean of the difference which has the same MLBP feature are calculated. And then, the defect-contained image is reconstructed as normal texture image. Finally, the residual is calculated between reconstructed and original images, and a simple threshold segmentation method can divide the residual image, and the defective region is detected.

The experiment result shows that the fabric texture can be more efficiently reconstructed, and the proposed method achieves better defect detection performance. Moreover, it offers empirical insights about how to exploit the sparsity of one certain feature, e.g. LBP.

Because of the selected research approach, the results may lack generalizability in chambray. Therefore, researchers are encouraged to test the proposed propositions further.

In this paper, a novel fabric defect detection method which extracts the sparsity of MLBP features is proposed.

Image Processing is an emerging field that is used to extract information from images. In recent years, this field has received immense attention from researchers, especially in the research domains of object detection, Biomedical Imaging and Semantic segmentation. In this study, a bibliometric analysis of publications related to image processing in the Science Expanded Index Extended (SCI-Expanded) has been performed. Several parameters have been analyzed such as annual scientific production, citations per article, most cited documents, top 20 articles, most relevant authors, authors evaluation using y-index, top and most relevant sources (journals) and hot topics.

The Bibliographic data has been extracted from the Web of Science which is well known and the world's top database of bibliographic citations of multidisciplinary areas that covers the various journals of computer science, engineering, medical and social sciences.

The research work in image processing is meager in the past decade, however, from 2014 to 2019, it increases dramatically. Recently, the IEEE Access journal is the most relevant source with an average of 115 publications per year. The USA is most productive and its publications are highly cited while China comes in second place. Image Segmentation, Feature Extraction and Medical Image Processing are hot topics in recent years. The National Natural Science Foundation of China provides 8% of all funds for Image Processing. As Image Processing is now becoming one of the most critical fields, the research productivity has enhanced during the past five years and more work is done while the era of 2005–2013 was the area with the least amount of work in this area.

This research is novel in this regard that no previous research focuses on Bibliometric Analysis in the Image Processing domain, which is one of the hot research areas in computer science and engineering.

The purpose of this paper is to select the optimal feature parameters to further improve the identification accuracy of cashmere and wool.

To increase the accuracy, the authors put forward a method selecting optimal parameters based on the fusion of morphological feature and texture feature. The first step is to acquire the fiber diameter measured by the central axis algorithm. The second step is to acquire the optimal texture feature parameters. This step is mainly achieved by using the variance of secondary statistics of these two texture features to get four statistics and then finding the impact factors of gray level co-occurrence matrix relying on the relationship between the secondary statistic values and the pixel pitch. Finally, the five-dimensional feature vectors extracted from the sample image are fed into the fisher classifier.

The improvement of identification accuracy can be achieved by determining the optimal feature parameters and fusing two texture features. The average identification accuracy is 96.713% in this paper, which is very helpful to improve the efficiency of detector in the textile industry.

In this paper, a novel identification method which extracts the optimal feature parameter is proposed.

The purpose of this paper is to develop a novel and systematic framework for bridge inspection and management to improve the efficiency in current practice.

A new framework that implements camera-based unmanned aerial systems (UASs) with computer vision algorithms to collect and process inspection data, and Bridge Information Modeling (BrIM) to store and manage all related inspection information is proposed. An illustrative case study was performed using the proposed framework to test its feasibility and efficiency.

The test results of the proposed framework on an existing bridge verified that: high-resolution images captured by an UAS enable to visually identify different types of defects, and detect cracks automatically using computer vision algorithms, the use of BrIM enable assigning defect information on individual model elements, manage all bridge data in a single model across the bridge life cycle. The evaluation by bridge inspectors from 12 states across the USA demonstrated that all of the identified problems, except for being subjective, can be improved using the proposed framework.

The proposed framework enables to: collect and document accurate bridge inspection data, reduce the number of site visits and avoid data overload and facilitate a more efficient, cost-effective and safer bridge inspection process.

This paper contributes a novel and systematic framework for the collection and integration of inspection data for bridge inspection and management. The findings from the case study suggest that the proposed framework should help improve current bridge inspection and management practice. Furthermore, the difficulties experienced during the implementation are evaluated, which should be helpful for improving the efficiency and the degree of automation of the proposed framework further.