Adaptive Image Thresholding Research Articles

Defect Detection of Electrical Insulating Materials Using Optically Excited Transient Thermography and Deep Autoencoder

This article presents an automatic and unsupervised internal damage detection technique for electrical insulating materials using optically excited transient thermography and a deep autoencoder (DAE). For this purpose, an optically excited thermography system is built, and the thermal images of the specimen surface during the cooling period are collected for the training of the DAE model. The reconstruction error of the DAE model is used as a feature to generate the feature image. The final binary detection image is obtained by applying adaptive threshold image segmentation. To avoid unwanted errors, small connected components and isolated pixels are removed as they may be falsely considered damages in the feature image. To improve the detection accuracy and reliability, the architecture and hyperparameters of the DAE network are optimized. The featured image and segmented image obtained using the DAE are compared with those obtained using three other traditional methods [manual time-domain image selection, frequency-domain feature analysis, and principal component analysis (PCA)]. Based on the defined evaluation metrics, the proposed DAE framework exhibits the best visual effects and the highest defect detection accuracy. The test results also show that this method is effective in detecting real composite insulators with air-gap defects under different detection interferences.

Multi-scale GAN with transformer for surface defect inspection of IC metal packages

Integrated circuit plays an important role in the information technology industry. Surface defect inspection of IC packages is an essential process in the IC packaging manufacturing. Here, an automatic optical inspection system is proposed based on semi-supervised deep learning for surface defect inspection of IC metal packages. Different from previous inspection methods, we propose an entirely multi-scale inspection framework to implement the evaluation of defects at multiple scales. To well capture the intrinsic patterns of qualified samples at multiple scales, an entirely multi-scale GAN with transformer is elaborately designed, which incorporates several novel modules. Specifically, multi-scale CNN encoder with a novel feature extraction scheme and a cross-scale feature fusion module is designed to sufficiently extract the features from the IC metal package image. Different from previous GAN models, a Swin Transformer decoder is designed to strengthen the modeling ability of the proposed GAN model. Also, several novel multi-scale inspection schemes, including multi-scale weight mask, multi-scale adaptive thresholding and multi-scale image patch-based defect evaluation, are proposed to suppress the reconstruction errors, highlight the potential defects and further evaluate them at multiple scales, respectively. Experimental results demonstrate the effectiveness and feasibility of the proposed multi-scale inspection framework, which achieves an excellent inspection performance of 0.70% error rate, 0.57% omission rate, 99.3% accuracy, 99.8% precision, 99.3% recall and 0.996 F-score with a reasonable speed of 70.9 FPS and is superior to the state-of-the-art semi-supervised deep learning inspection methods.

Microstructural and compaction characteristics of tropical black clay soil subgrade modified with lead-zinc mine tailings

Lead–Zinc Mine tailings (LZMT) are wastes generated after the extraction of lead and zinc from mined mineral ore, whose disposal mechanism is gradually becoming environmentally unfriendly. For effective recycling of LZMT, this present study utilized a combination of LZMT and Portland limestone cement (PLC) to improve the compaction and microstructural characteristics of tropical black clay soil (TBCS) for use in pavement design and construction. The LZMT and PLC were added to the expansive soil in varying proportions with mix ratios generated from Taguchi orthogonal array. The result obtained for the compaction characteristics showed that the maximum dry density (MDD) increased significantly when a combination of 20% LMZT and 4% PLC were blended with the expansive soil. The increase in the MDD was attributed to the formation of cementitious compounds. In addition, the optimum mix ratio obtained from the unconfined compressive strength of the TBCS, was used for the evaluation of the pore structure characteristics which included porosity, tortuosity and permeability. The result obtained from the analysis that was implemented with a combination of fractal geometry and Bradley and Roth adaptive thresholding image segmentation technique, indicates the possibility of a slight reduction in the strength properties of the modified soil due to its high level of porosity. Also, the permeability and tortuosity values obtained from the present study suggest a slight increase in the permeability of the modified soil-additive mixtures which may not be unconnected to the occurrence of pozzolanic reaction that resulted in the agglomeration and flocculation of the LZMT-PLC modified TBCS. Furthermore, microstructural analysis was executed on the modified TBCS and LZMT using Fourier transform infrared spectroscopy (FTIR) and scanning electron microscopy (SEM). The result from the FTIR analysis indicates the pozzolanic character of LZMT in the presence of Si–O and Al–O tension bond with the bonds around 1000 cm−1 wavenumber, while the SEM analysis reveals the formation of a cementitious compound in the modified expansive soil-LZMT-PLC mixture.

Adaptive granulation Renyi rough entropy image thresholding method with nested optimization

The rough entropy based image thresholding algorithm can effectively deal with the uncertainty information in an image. Nevertheless, the existing rough entropy based thresholding methods have two limitations. One is that there is no generalized rough entropy definition. The other is that the granule size cannot be selected automatically in combination with the image information in the granulation process. In order to address these two problems, an adaptive granulation Renyi rough entropy image thresholding method with nested optimization is proposed in this paper. First, a definition of generalized rough entropy with parameter based on Renyi entropy form is proposed to describe the uncertainty information of complex images. Second, in order to select the granule size in combination with the specific image information, a granule size selection method is proposed by maximizing the uniformity of the segmented image regions. Finally, a nested optimization adaptive granulation Renyi rough entropy thresholding segmentation algorithm is proposed. In the experiments, the Renyi rough entropy is compared with the existing four rough entropy in image thresholding. The new parametric rough entropy can obtain better segmentation results than the other existing rough entropy. The novel adaptive granulation Renyi rough entropy thresholding segmentation algorithm is compared with the state-of-the-art image segmentation methods on several different image data sets, which verifies the effectiveness of the novel algorithm.

Parallel Approach of Adaptive Image Thresholding Algorithm on GPU

Image thresholding is used to segment an image into background and foreground using a given threshold. The threshold can be generated using a specific algorithm instead of a pre-defined value obtained from observation or experiment. However, the algorithm involves per pixel operation, histogram calculation, and iterative procedure to search the optimum threshold that is costly for high-resolution images. In this research, parallel implementations on GPU for three adaptive image thresholding methods, namely Otsu, ISODATA, and minimum cross-entropy, were proposed to optimize their computational times to deal with high-resolution images. The approach involves parallel reduction and parallel prefix sum (scan) techniques to optimize the calculation. The proposed approach was tested on various sizes of grayscale images. The result shows that the parallel implementation of three adaptive image thresholding methods on GPU achieves 4-6 speeds up compared to the CPU implementation, reducing the computational time significantly and effectively dealing with high-resolution images.

Adaptive Image Denoising Method Based on Diffusion Equation and Deep Learning

Effective noise removal has become a hot topic in image denoising research while preserving important details of an image. An adaptive threshold image denoising algorithm based on fitting diffusion is proposed. Firstly, the diffusion coefficient in the diffusion equation is improved, and the fitting diffusion coefficient is established to overcome the defects of texture detail loss and edge degradation caused by excessive diffusion intensity. Then, the threshold function is adaptively designed and improved so that it can automatically control the threshold of the function according to the maximum gray value of the image and the number of iterations, so as to further preserve the important details of the image such as edge and texture. A neural network is used to realize image denoising because of its good learning ability of image statistical characteristics, mainly by the diffusion equation and deep learning (CNN) algorithm as the foundation, focus on the effects of activation function of network optimization, using multiple feature extraction technology in-depth networks to study the characteristics of the input image richer, and how to better use the adaptive algorithm on the depth of diffusion equation and optimization backpropagation learning. The training speed of the model is accelerated and the convergence of the algorithm is improved. Combined with batch standardization and residual learning technology, the image denoising network model based on deep residual learning of the convolutional network is designed with better denoising performance. Finally, the algorithm is compared with other excellent denoising algorithms. From the comparison results, it can be seen that the improved denoising algorithm in this paper can also improve the detail restoration of denoised images without losing the sharpness. Moreover, it has better PSNR than other excellent denoising algorithms at different noise standard deviations. The PSNR of the new algorithm is greatly improved compared with the classical algorithm, which can effectively suppress the noise and protect the image edge and detail information.

Defect Detection Based on Segmentation of Thermographic Images of Frequency Modulated Thermal Wave Imaging

To improve the usefulness of the data, the raw images acquired during non-destructive testing should be processed by image processing techniques. In this paper, by Frequency Modulated Thermal Wave Imaging, we use the image fusion technique to boost the detection capability of defects in a GFRP sample with 25 squared Teflon inserts of different sizes positioned at various depths. In applications such as detection, image segmentation is useful where it is difficult to process the entire image at a time. In this paper, Adaptive Thresholding Image segmentation is used to classify the delamination in Thermographic Images of Infrared Non-Destructive Research on images captured at two different times. Image fusion is later applied to segmented images. Image fusion is used to merge two or more pictures of a different focus and to provide the best picture quality. Fusion is carried out using the Basic Averaging Method here. Using Relative Foreground Area error, the performance of the proposed method is quantitatively assessed. The region and shape of an object are important parameters in the case of Non-Destructive Evaluation. Such parameters are contrasted with current methods of segmentation.

Image compression based on adaptive image thresholding by maximising Shannon or fuzzy entropy using teaching learning based optimisation

Image compression based on adaptive image thresholding by maximising Shannon or fuzzy entropy using teaching learning based optimisation

Image compression based on adaptive image thresholding by maximising Shannon or fuzzy entropy using teaching learning based optimisation

In this paper, teaching leaning based optimisation (TLBO) is used for maximising Shannon entropy or fuzzy entropy for effective image thresholding which leads to better image compression with higher peak signal to noise ratio (PSNR). The conventional multilevel thresholding methods are efficient when bi-level thresholding. However, they are computationally expensive extending to multilevel thresholding since they exhaustively search the optimal thresholds to optimise the objective functions. To overcome this drawback, a TLBO based multilevel image thresholding is proposed by maximising Shannon entropy or fuzzy entropy and results are compared with differential evolution, particle swarm optimisation and bat algorithm and proved better in standard deviation, PSNR, weighted PSNR and reconstructed image quality. The performance of the proposed algorithm is found better with fuzzy entropy compared to Shannon entropy.

Single-shot imaging of major species and OH mole fractions and temperature in non-premixed H2/N2 flames at elevated pressure

Simultaneous, single-shot imaging of all major species (N2, O2, H2, and H2O), OH, temperature, and mixture fraction is demonstrated for the first time in H2N2 non-premixed jet flames at 12 bar. The spatial distribution of mole fraction is obtained for the four major species by recording images of Raman scattering on four separate back-illuminated CCD cameras. The available field-of-view is 25(H) × 8(V) mm2. Temperature and mixture fraction are derived from Raman scattering images. Images of OH fluorescence intensity are recorded using OH-PLIF and are converted into OH mole fraction by calculating the Boltzmann population distribution and the quenching rate accurately for each pixel. Precision and accuracy are assessed by comparing 2-D Raman/OH-PLIF measurements in laminar flames to 1-D flame computations accounting for differential diffusion. Single-shot precision on N2, O2, H2, and temperature is better than 5%. It is better than 6% and 10% for H2O and OH, respectively. Accuracy lies within these values, except for H2O with 10%. Such good performance of Raman imaging is attributed to (a) the use of non-intensified CCD cameras, (b) wavelet adaptive thresholding (WATR) image denoising, (c) rejection of flame luminosity by a Pockels cell electro-optical shutter with 500 ns gating, and (d) elevated pressure that boosts the Raman signal intensity. Measurements in a turbulent flame (3.6N2:H2 by vol. and Re = 29,000) show that most of the flame's thermochemical structure is accurately captured by unity Lewis number computations, suggesting that effects of differential diffusion are less important above some Reynolds number. This is consistent with expectations and it engenders confidence in the Raman imaging technique. Because images of both mixture fraction and OH mole fraction are available, it is also possible to reconstruct a more accurate scalar dissipation rate by projection onto the 2-D flame front normal.

Adaptive vision-based detection of laser-material interaction for directed energy deposition

In-situ vision data acquisition, feature extraction, and analysis are ongoing challenges for quality assessment in directed energy deposition (DED). This work proposes a method for detecting target regions in the laser-material interaction zone based on a low-cost high-dynamic-range (HDR) vision sensor. Adaptive image thresholding, connected component analysis, and iterative energy minimization are used to identify target regions. The method is designed to be adaptive, in terms of obtaining parameters based on simple training data, and robust, in terms of feature detection performance subject to under-melt, conduction and keyhole melting mode phenomena. The performance of the proposed region detection scheme is quantitatively and qualitatively evaluated against annotated data. It was found that the True Positive Rate in detection was above 90%, while the False Detection Rate was less than 10%. Extensive experimental results show that the proposed scheme is able to detect and follow target regions under a variety of power levels and process conditions.

Wavelet coefficients segmentation for locally adaptive threshold image denoising method

Wavelet coefficients segmentation for locally adaptive threshold image denoising method

Optic cup segmentation using adaptive threshold and morphological image processing

Glaucoma is a chronic optic neuropathy. It was predicted that people with bilateral blindness caused by glaucoma will increase each year. Hence, computer-aided diagnosis of glaucoma was proposed to assist ophthalmologist to conduct a fast and accurate glaucoma screening. One of the ocular examination in screening is optic nerve examination called disc damage likelihood scale (DDLS). It is important to find the optic disc and the optic cup to determine the narrowest width of the neuroretinal rim when using DDLS. To find the optic cup, this study proposed a segmentation scheme consisting of pre-process, segmentation, convex hull and morphological opening operation. In pre-process the blood vessel was removed to make the segmentation process of the optic cup easier. The segmentation process was done by using an adaptive thresholding followed by morphological image processing such as convex hull, opening and erosion. This algorithm was applied on Magrabia dataset and attained accuracy, specificity and sensitivity of 99.50%, 99.75% and 75.19% respectively.

Application of Adaptive Threshold Image Segmentation Algorithm in Orthopedic CT Imaging

Objective: To explore the application and analysis of image segmentation in the rehabilitation of patients with bone trauma during orthopedic nursing. Methods: Sixty patients with orthopedic trauma in our hospital were enrolled. The patients were divided into observation group and control group by four weeks. The control group was the traditional observation image, and the observation group was analyzed by image segmentation technology. Therefore, the two groups of patients are provided with nursing treatment, and finally, the progress of bone trauma recovery is periodically observed. Results: The degree of recovery in the observation group was 43% in the four-week period and 30% in the control group. It can be seen that the adaptive threshold algorithm makes orthopedic care more effective in image segmentation. Discussion: In medical imaging technology, different imaging devices can provide a variety of voxel information. The bone morphology information provided by CT images can make orthopedic care more targeted. Conclusion: Image segmentation technology provides a reliable predictive treatment solution in the nursing work, which solves the actual problem of the patient in the injury and the disease, so that the patient can recover faster. However, the expected research results of medical imaging technology research have guiding significance for the doctor's clinical diagnosis and preoperative and postoperative planning.

Automatic detection of Plasmodium parasites from microscopic blood images.

Malaria is caused by Plasmodium parasite. It is transmitted by female Anopheles bite. Thick and thin blood smears of the patient are manually examined by an expert pathologist with the help of a microscope to diagnose the disease. Such expert pathologists may not be available in many parts of the world due to poor health facilities. Moreover, manual inspection requires full concentration of the pathologist and it is a tedious and time consuming way to detect the malaria. Therefore, development of automated systems is momentous for a quick and reliable detection of malaria. It can reduce the false negative rate and it can help in detecting the disease at early stages where it can be cured effectively. In this paper, we present a computer aided design to automatically detect malarial parasite from microscopic blood images. The proposed method uses bilateral filtering to remove the noise and enhance the image quality. Adaptive thresholding and morphological image processing algorithms are used to detect the malaria parasites inside individual cell. To measure the efficiency of the proposed algorithm, we have tested our method on a NIH Malaria dataset and also compared the results with existing similar methods. Our method achieved the detection accuracy of more than 91% outperforming the competing methods. The results show that the proposed algorithm is reliable and can be of great assistance to the pathologists and hematologists for accurate malaria parasite detection.

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

The presented work is part of the H2020 project SWEEPER with the overall goal to develop a sweet pepper harvesting robot for use in greenhouses. As part of the solution, visual servoing is used to direct the manipulator towards the fruit. This requires accurate and stable fruit detection based on video images. To segment an image into background and foreground, thresholding techniques are commonly used. The varying illumination conditions in the unstructured greenhouse environment often cause shadows and overexposure. Furthermore, the color of the fruits to be harvested varies over the season. All this makes it sub-optimal to use fixed pre-selected thresholds. In this paper we suggest an adaptive image-dependent thresholding method. A variant of reinforcement learning (RL) is used with a reward function that computes the similarity between the segmented image and the labeled image to give feedback for action selection. The RL-based approach requires less computational resources than exhaustive search, which is used as a benchmark, and results in higher performance compared to a Lipschitzian based optimization approach. The proposed method also requires fewer labeled images compared to other methods. Several exploration-exploitation strategies are compared, and the results indicate that the Decaying Epsilon-Greedy algorithm gives highest performance for this task. The highest performance with the Epsilon-Greedy algorithm ( ϵ = 0.7) reached 87% of the performance achieved by exhaustive search, with 50% fewer iterations than the benchmark. The performance increased to 91.5% using Decaying Epsilon-Greedy algorithm, with 73% less number of iterations than the benchmark.

Image Denoising Analysis Using Adaptive Subband Thresholding and Wavelet Packet

In image processing, removal of noise without blurring the image edges is a difficult problem. Aiming at orthogonal wavelet transform and traditional thresholds shortage, a new adaptive threshold image de-noising method which is based on wavelet packet transform, decomposition level and sub band coefficients is proposed. The image is decomposed into the low frequency part and high frequency part by using wavelet packet transform and the wavelet packet tree coefficients are processed with soft threshold by using the level dependent adaptive threshold. The proposed method describes a new method for suppression of noise in image by fusing the wavelet Packet (WP) transform (WPT) along with optimal wavelet basis (OWB) (WPTOWB) for image decomposition. Shannon entropy is implemented to produce the optimal wavelet basis function. Then, for each wavelet subband, an adaptive threshold value to which a multiplying factor (α) is included making the threshold value dependent on decomposition level and subband’s statistical parameters are estimated. From the experiment result, we see that compared with traditional methods, this method can not only effectively eliminate noise, but can also well keep original images information and the quality after image de-noising.

A metal artifact reduction method for a dental CT based on adaptive local thresholding and prior image generation.

BackgroundMetal artifacts appearing as streaks and shadows often compromise readability of computed tomography (CT) images. Particularly in a dental CT in which high resolution imaging is crucial for precise preparation of dental implants or orthodontic devices, reduction of metal artifacts is very important. However, metal artifact reduction algorithms developed for a general medical CT may not work well in a dental CT since teeth themselves also have high attenuation coefficients.MethodsTo reduce metal artifacts in dental CT images, we made prior images by weighted summation of two images: one, a streak-reduced image reconstructed from the metal-region-modified projection data, and the other a metal-free image reconstructed from the original projection data followed by metal region deletion. To make the streak-reduced image, we precisely segmented the metal region based on adaptive local thresholding, and then, we modified the metal region on the projection data using linear interpolation. We made forward projection of the prior image to make the prior projection data. We replaced the pixel values at the metal region in the original projection data with the ones taken from the prior projection data, and then, we finally reconstructed images from the replaced projection data. To validate the proposed method, we made computational simulations and also we made experiments on teeth phantoms using a micro-CT. We compared the results with the ones obtained by the fusion prior-based metal artifact reduction (FP-MAR) method.ResultsIn the simulation studies using a bilateral prostheses phantom and a dental phantom, the proposed method showed a performance similar to the FP-MAR method in terms of the edge profile and the structural similarity index when an optimal global threshold was chosen for the FP-MAR method. In the imaging studies of teeth phantoms, the proposed method showed a better performance than the FP-MAR method in reducing the streak artifacts without introducing any contrast anomaly.ConclusionsThe simulation and experimental imaging studies suggest that the proposed method can be used for reducing metal artifacts in dental CT images.

A visual consistent adaptive image thresholding method

Image thresholding method is an important preprocessing step in many applications of image processing. In this paper, we present a visual consistent adaptive image thresholding method, by combining the thresholding process with the characteristics of human visual system. In the proposed algorithm, we first roughly classify the image pixels into two categories. Then two sub-images are constructed to retain the essential information of the original image. For each sub-image, a corresponding global optimal threshold is calculated by optimizing an objective function. Finally, a visual consistent binary image is produced by combining the results from the previous steps with the information of pixels in each category. The proposed method has been tested on some different images, and the results are also compared with a number of known algorithms in the literature. The experimental results demonstrate that the overall visual qualities of our method are more suitable for human visual perception.

An Adaptive Threshold Image Inpainting Method Based on Markov Random Field

An Adaptive Threshold Image Inpainting Method Based on Markov Random Field