Image Processing Model Research Articles

Deep learning based processing framework for spatio-temporal analysis and classification of laser biospeckle data

Laser biospeckle is an advanced optical technique with the ability to non-destructively visualize various transient phenomenon via spatial and temporal statistics. However, accuracy of the existing image processing techniques used to process biospeckle data is hampered by various experimental and processing dependent factors. Therefore, in this work, a novel 3D convolution neural network (3D CNN) based deep learning (DL) architecture is developed for spatio-temporal analysis of biospeckle data in both qualitative and quantitative domains that effectively reduces errors introduced due to the influence of varying experimental parameters. Firstly, 3D CNN based image processing model is proposed for spatio-temporal analysis and classification of biospeckle data. Furthermore, a novel DL based numerical indexing strategy is developed for identification of level of activity in a sample. Finally, impact of varying experimental parameters on accuracy of the proposed technique is analyzed. In this direction, multiple experiments were performed to examine the effect of variation in input data parameters such as frame dimension, frame rate, number of frames, and background noise on accuracy of the trained model. Performance of the proposed model was analyzed and compared with respect to synthetic data generated by using rotating diffuser based simulation model. Robustness of the proposed strategy was also validated experimentally on practical data associated with identification of disease in seeds. Obtained results demonstrated that the proposed technique is accurate and can perform spatio-temporal classification and numerical indexing of the biospeckle data under varying experimental parameters.

Application of image processing technology based on hierarchical analysis in visual communication system

Abstract To address the problem of poor visual expression due to traditional methods’ poor image enhancement effect, this paper proposes an image processing model for visual communication of the human-computer interaction interface based on hierarchical analysis. The edge contour feature extraction method is used to extract the convenient information features of the HCI interface, and the cross-sectional information fusion technique is combined to realize the visual communication information enhancement processing of the HCI interface, extract the spatial multi-resolution feature amount of the visual communication image of the HCI interface, and realize the visual communication optimization design of the HCI interface. In the image processing model proposed in this paper, the traditional PCANet and computer vision methods are compared to test the effectiveness of the three image recognition methods. The recognition accuracy of the method proposed in this paper is 82.55%, 85.28%, 87.06%, and 85.87% for the four types of images, respectively; the recognition accuracy of PCANet is 75.53%, 76.48%, 81.26%, and 74.74%, respectively; and the recognition accuracy of computer vision method is 73.79%, 72.83%, 79.36%, and 73.71%. Comparing the data, it can be seen that the model in this paper can improve the fidelity of visual communication and the discriminative ability of interface output, which can greatly improve the performance of the graphical human-computer interaction interface.

A Novel Approach to Evaluate the Wear Behavior of CuO Doped Sintered Alumina Ceramics Using Image Processing Models

The present research describes the post wear SEM images of nano-CuO doped alumina ceramics in the light of three different image processing algorithms, viz. entropy analysis, Sobel edge detection techniques and entropy filtered image histogram analysis. The 2 wt% CuO doped sintered alumina has shown the best performance towards wearing due to maximum bulk density, hardness and fracture toughness. These materialistic properties are fitted to correlate with the lowest value of entropy and edge density index at the level of 2 wt% doping. The entropy filtered image histogram of 2 wt% doping is the closest to the Gaussian Bell shape distribution with the lowest skewness factor. These three-image computed methods validate their suitability in developing a real-life implementation for a possible wear resistance estimator.

CO-WOA: Novel Optimization Approach for Deep Learning Classification of Fish Image.

Systems based on enhanced deep learning can replace the area's currently cumbersome and sluggish traditional approaches. Although it seems straightforward, classifying fish images is a complex procedure. In addition, the scientific study of population distribution and geographic patterns is important for advancing the field's present advancements. The goal of the proposed work is to identify the best performing strategy using cutting-edge computer vision, the Chaotic Oppositional Based Whale Optimization Algorithm (CO-WOA), and data mining techniques. Performance comparisons with leading models, such as Convolutional Neural Networks (CNN) and VGG-19, are made to confirm the applicability of the suggested method. The suggested feature extraction approach with Proposed Deep Learning Model was used in the research, yielding accuracy rates of 100%. The performance was also compared to cutting-edge image processing models with an accuracy of 98.48%, 98.58%, 99.04%, 98.44%, 99.18% and 99.63% such as Convolutional Neural Networks, ResNet150 V2, DenseNet, Visual Geometry Group-19, Inception V3, Xception. Using an empirical method leveraging artificial neural networks, the Proposed Deep Learning model was shown to be the best model.

Transforming Dental Caries Diagnosis Through Artificial Intelligence-Based Techniques.

Diagnosing dental caries plays a pivotal role in preventing and treating tooth decay. However, traditional methods of diagnosing caries often fall short in accuracy and efficiency. Despite the endorsement of radiography as a diagnostic tool, the identification of dental caries through radiographic images can be influenced by individual interpretation. Incorporating artificial intelligence (AI) into diagnosing dental caries holds significant promise, potentially enhancing the precision and efficiency of diagnoses. This review introduces the fundamental concepts of AI, including machine learning and deep learning algorithms, and emphasizes their relevance and potential contributions to the diagnosis of dental caries. It further explains the process of gathering and pre-processing radiography data for AI examination. Additionally, AI techniques for dental caries diagnosis are explored, focusing on image processing, analysis, and classification models for predicting caries risk and severity. Deep learning applications in dental caries diagnosis using convolutional neural networks are presented. Furthermore, the integration of AI systems into dental practice is discussed, including the challenges and considerations for implementation as well as ethical and legal aspects. The breadth of AI technologies and their prospective utility in clinical scenarios for diagnosing dental caries from dental radiographs is presented. This review outlines the advancements of AI and its potential in revolutionizing dental caries diagnosis, encouraging further research and development in this rapidly evolving field.

Water Quality Prediction using Image Processing and Machine Learning Models

Water Quality Prediction using Image Processing and Machine Learning Models

Effect of data size on tooth numbering performance via artificial intelligence using panoramic radiographs.

This study aims to investigate the effect of number of data on model performance, for the detection of tooth numbering problem on dental panoramic radiographs, with the help of image processing and deep learning algorithms. The data set consists of 3000 anonymous dental panoramic X-rays of adult individuals. Panoramic X-rays were labeled on the basis of 32 classes in line with the FDI tooth numbering system. In order to examine the relationship between the number of data used in image processing algorithms and model performance, four different datasets which include 1000, 1500, 2000 and 2500 panoramic X-rays, were used. The training of the models was carried out with the YOLOv4 algorithm and trained models were tested on a fixed test dataset with 500 data and compared based on F1 score, mAP, sensitivity,precision and recall metrics. The performance of the model increased as the number of data used during the training of the model increased. Therefore, the last model trained with 2500 data showed the highest success among all the trained models. Dataset size is important for dental enumeration, and large samples should be considered as more reliable.

Impulse Noise Suppression in Color Images Using Median Filter and Deep Learning

Abstract: Refining the quality of a noisy image is essential for many image applications. Various median filter variants have been introduced to suppress various noises, but they have their own limitations when detecting noise and restoring noise-free images. Denoising convolutional neural networks (DnCNNs), primarily developed for Gaussian noise removal, are influential nonlinear mapping models in image processing. After alterations in training data, they can be used to suppress other noise with outstanding results. This article suggests a frequency median filter method combined with deep learning for color images polluted by Salt and Pepper (SnP) noise. The analysis presented in this paper has primarily used a frequency median filter to suppress impulse noise wherein the restored value for the center pixel is evaluated by the frequency median rather than the traditional median. After which, the pretrained denoising convolutional neural network is hired to suppress the remaining noise and attain the output image finally. With a visual comparative study, simulation results on the taken test images show that the proposed method surpasses de-noising methods in terms of PSNR, SSIM, NMSE, Entropy, IEF, NCC, PCC and Running Time.

Accuracy Improvement Based on Classic Neural Network: Voting, Restarting and Quantization

Since AlphaGo beat the world Go champion in 2016, which attracted wide attention, the neural network has become more and more popular in recent years, and people’s research on it has gradually improved and been applied in different fields. Today, artificial intelligence and machine learning have become an essential part of modern society and intelligent systems. We do image recognition, speech recognition, and visual learning, closely related to machine learning. However, in machine learning, unsatisfactory training results or even training failure is always encountered. Therefore, in machine learning, it is imperative to improve the accuracy of neural network training results. In this paper, speech recognition, image processing, MNIST, and other classical neural network models will be used to set the training parameters of the neural network better and improve the accuracy of training through voting, quantization, restart, and other methods. The part of research is aiming to find the relationship between restart numbers on the training process and the total extent of learning improvement. At the same time, several algorithms on utilizing these restart numbers are to be compared and selected. Finally, the conclusion is drawn that the more restart made in the training process with a convolutional neural network, the less profit on accuracy improvement we gain from restarting the process.

Research on Defect Detection Method of Nonwoven Fabric Mask Based on Machine Vision

During the production, transportation and storage of nonwoven fabric mask, there are many damages caused by human or nonhuman factors. Therefore, checking the defects of nonwoven fabric mask in a timely manner to ensure the reliability and integrity, which plays a positive role in the safe use of nonwoven fabric mask. At present, the wide application of machine vision technology provides a technical mean for the defect detection of nonwoven fabric mask. On the basis of the pre-treatment of the defect images, it can effectively simulate the contour fluctuation grading and gray value change of the defect images, which is helpful to realize the segmentation, classification and recognition of nonwoven fabric mask defect features. First, in order to accurately obtain the image information of the nonwoven fabric mask, the binocular vision calibration method of the defect detection system is discussed. On this basis, the defect detection mechanism of the nonwoven fabric mask is analyzed, and the model of image processing based on spatial domain and Hough transform is established, respectively. The original image of the nonwoven fabric mask is processed by region processing and edge extraction. Second, the defect detection algorithm of nonwoven fabric mask is established and the detection process is designed. Finally, a fast defect detection system for nonwoven fabric mask is designed, and the effectiveness of the detection method for nonwoven fabric mask is analyzed with an example. The results show that this detection method has positive engineering significance for improving the detection efficiency of defects in nonwoven fabric mask.

A Computer Vision-Based System for Recognition and Classification of Urdu Sign Language Dataset for Differently Abled People Using Artificial Intelligence

Communication between normal people and deaf people is the most difficult part of daily life worldwide. It is difficult for a normal person to understand a word from the deaf one in their daily routine. So, to communicate with deaf people, different countries developed different sign languages to make communication easy. In Pakistan, for deaf people, the government developed Urdu Sign Language to communicate with deaf people. Physical trainers and experts are difficult to provide everywhere in society, so we need such a computer/mobile-based system to convert the deaf sign symbol into voice and written alphabet that the normal person can easily get the intentions of the deaf one. In this paper, we provided an image processing and deep learning-based model for Urdu Sign Language. The proposed model is implemented in Python 3 and uses different image processing and machine techniques to capture the video and transform the symbols into voice and Urdu writing. First, we get a video from the deaf person, and then the model crops the frames into pictures. Then, the individual picture is recognized for the sign symbol such as if the deaf showed a symbol for one, then the model recognizes it and shows the letter which he/she wants to tell. Image processing techniques such as OpenCV are used for image recognition and classification while TensorFlow and linear regression are used for training the model to behave intelligently in the future. The results show that the proposed model increased accuracy from 80% to 97% and 100% accordingly. The accuracy of the previously available work was 80% when we implemented the algorithms, while with the proposed algorithm, when we used linear regression, we achieved the highest accuracy. Similarly, when we used the TensorFlow deep learning algorithm, we achieved 97% accuracy which was less than that of the linear regression model.

Computational Model for Image Processing in the Minds of People with Visual Agnosia using Fuzzy Cognitive Map

Computational Model for Image Processing in the Minds of People with Visual Agnosia using Fuzzy Cognitive Map

One-shot learning Batak Toba character recognition using siamese neural network

Siamese neural network (SINN) is an image processing model that compares the scores of two patterns. The SINN algorithm is a combination of the use of the double convolutional neural network (CNN) algorithm. By combined SINN with a one-shot learning algorithm, we can build an image model without requiring thousands of images for training. The test results from the SINN algorithm and one-shot learning show that this process was successful in matching the two data but was unable to produce labels from the data being tested. Because of this, the researcher decided to continue the implementation process using the CNN algorithm combined with single shot detection (SSD). By using a dataset of 5000, the recognition and translation of the Toba Batak script was successful. The percentage of average accuracy results from CNN and SSD in recognizing Toba Batak characters is 84.08% for single characters and 74.13% for mixed characters. While the percentage of average accuracy results for testing the breadth first search algorithm is 75.725%.

Comparison of edge detection operators in digital image processing

The Internet has been developed so far, computer has developed rapidly, and the use of computer for image processing has been widely used in all walks of life, the use of MATLAB for image processing has become a hot topic today. Image processing can find the information it wants in many images repeatedly compressed on the network, and restore information to a certain extent. Edge processing step is included in various digital image processing models. So Edge processing is particularly important for image processing. Common edge detection algorithms include Prewitt, Sobel, Canny, and so on. Choosing a more appropriate and effective operator becomes particularly important for processing the image. The three operators are processed by grayscale, binarization, edge detection of different operators, and the final results are compared. Gaussian white noise is added to compare the white noise interference ability of the three operators. Finally, the Canny operator works better.

What about the Latent Space? The Need for Latent Feature Saliency Detection in Deep Time Series Classification

Saliency methods are designed to provide explainability for deep image processing models by assigning feature-wise importance scores and thus detecting informative regions in the input images. Recently, these methods have been widely adapted to the time series domain, aiming to identify important temporal regions in a time series. This paper extends our former work on identifying the systematic failure of such methods in the time series domain to produce relevant results when informative patterns are based on underlying latent information rather than temporal regions. First, we both visually and quantitatively assess the quality of explanations provided by multiple state-of-the-art saliency methods, including Integrated Gradients, Deep-Lift, Kernel SHAP, and Lime using univariate simulated time series data with temporal or latent patterns. In addition, to emphasize the severity of the latent feature saliency detection problem, we also run experiments on a real-world predictive maintenance dataset with known latent patterns. We identify Integrated Gradients, Deep-Lift, and the input-cell attention mechanism as potential candidates for refinement to yield latent saliency scores. Finally, we provide recommendations on using saliency methods for time series classification and suggest a guideline for developing latent saliency methods for time series.

Deep learning modified neural networks with chicken swarm optimization-based lungs disease detection and severity classification

Many people around the world are affected by pulmonary disease as well as asthma, pneumonia, lung cancer, and tuberculosis. All of these conditions have one thing in common: airway obstruction. Lung illnesses are a worldwide issue in which chronic obstructive pulmonary disease, pneumonia, asthma, tuberculosis, and fibrosis are few of the most common. An accurate diagnosis of a lung problem is essential, and it has been pursued by many researchers using image processing and machine learning models. Multiple deep learning methods are used to predict lung disease; these include convolutional neural networks, vanilla neural networks, visual geometry group-based neural networks, and the capsule network. Medical data are scarce, so diagnosing pulmonary diseases using chest x-ray pictures from datasets with less than 1000 samples is considered to address the problem. Three deep learning multiple neural networks (DLMNNs) were generated using the chicken swarm optimization (CSO) approach, for which transfer learning was applied to evaluate the performance of each. First, we created an algorithm for segmenting CXR images, and then we compared it with other classification systems. Our results were compared with those of other methods using publicly available data from the Shenzhen and Montgomery lung datasets. However, our technique has a lower number of trainable parameters compared with the best-performing models trained on the Montgomery dataset. The DLMNN-CSO virtually matched the best performance on the Shenzhen dataset, although it was computationally less expensive than the other models. DLMNN-CSO’s validation loss was 0.4, whereas the validation loss for CNN, VDSNet, VGG, and DBN was 0.9, 0.8, 0.6, and 0.5, respectively.

Sampling by Difference as a Method of Applying the Sampling Kantorovich Model in Digital Image Processing

In this paper, the connections between the Sampling Kantorovich model and the sampling process are highlighted and exploited. Based on the theoretical framework of the Sampling Kantorovich operators, a sampling paradigm, here named Sampling Kantorovich by Difference (SKD), is introduced. In line of principle, SKD allows for overcoming the technical limitation due to the fact that the resolution of a signal/image is strictly connected with the size of the used sensors. We analyze the paradigm in the case of a simulated super resolution type problem. The same mathematical model, being extendable to other signal reconstruction procedures, suggests a theoretical way for new technical solutions in the sampling procedures.

Analysis of the activated sludge composition using artificial neural networks

The object of research is electron microscopic images of activated sludge, which were used to train a convolutional neural network. An important task of the process of biological wastewater treatment is the prompt determination of quantitative and qualitative changes in activated sludge, as well as the assessment of the impact of the identified changes on the efficiency of the treatment. Microscopic examination, which is a traditional tool for controlling the quality of the water-sludge mixture, does not allow to quickly detect the deterioration of the activated sludge, which can lead to its degradation, and in difficult cases – to the death of the sludge. Violation of the microbiological composition of sludge leads to improper formation of flocs, violation of the process of formation of flakes, filamentous or sludge swelling, toxicity, etc. The combination of artificial intelligence methods with existing methods of quality control of activated sludge will increase the reliability and validity of the assessment of the quality of biological treatment. A proposed methodology for analyzing the state of activated sludge using convolutional neural networks. For the purpose of training the network, images of activated sludge were prepared, which were classified into two categories – «flocs» and «bacteria with microorganisms». There are 4 subcategories in the «flocks» category: size, shape, structure, edge of the floc; in the category «bacteria with microorganisms» there are 2 subcategories: «individual bacteria and microorganisms» and «colonies». Data sets of 250, 500 and 1000 images were created for each category. The task of learning the image processing model and the criteria for evaluating the success of learning are formulated. The task of training the network was to find such a recognition function that, with a given degree of accuracy, approximates the unknown recognition function over the entire domain of its definition. The accuracy of image recognition is chosen as a learning success criterion. The model training results show that the image recognition accuracy reaches 99.98 %, and the training quality is affected by the sample size and training duration. The trained model can be used as a fast and efficient tool to detect problems with activated sludge.

Development and Evaluation of Urolithiasis Detection Technology Based on a Multimethod Algorithm.

In this paper, we propose an optimal ureter stone detection model utilizing multiple artificial intelligence technologies. Specifically, the proposed model of urinary tract stone detection merges an artificial intelligence model and an image processing model, resulting in a multimethod approach. We propose an optimal urinary tract stone detection algorithm based on artificial intelligence technology. This method was intended to increase the accuracy of urinary tract stone detection by combining deep learning technology (Fast R-CNN) and image processing technology (Watershed). As a result of deriving the confusion matrix, the sensitivity and specificity of urinary tract stone detection were calculated to be 0.90 and 0.91, and the accuracy for their position was 0.84. This value was higher than 0.8, which is the standard for accuracy. This finding confirmed that accurate guidance to the stones area was possible when the developed platform was used to support actual surgery. The performance evaluation of the method proposed herein indicated that it can effectively play an auxiliary role in diagnostic decision-making with a clinically acceptable range of safety. In particular, in the case of ambush stones or urinary stones accompanying ureter polyps, the value that could be obtained through combination therapy based on diagnostic assistance could be evaluated.

Hybrid image processing model: a base for smart emergency applications

Hybrid image processing model: a base for smart emergency applications