Algorithm For Binary Images Research Articles

Pre-processing study of multi-sensor data

For multi-sensor data with multi-source heterogeneity, data pre-processing is required for data fusion. This paper proposes a data pre-processing method, firstly, the image data is binarized using the designed image binarization algorithm and flame area extraction algorithm, and the flame area information in the fire image is extracted into one-dimensional data, then the five one-dimensional data of ambient temperature, temperature-sensitive cable, CO2, CO and flame area are noise reduced using the designed wavelet noise reduction algorithm, and finally the final pre-processed data is calculated by the selected normalization formula. The results of the study show that the method can improve the effectiveness of multi-sensor data fusion.

Computer-aided recognition and assessment of a porous bioelastomer in ultrasound images for regenerative medicine applications

It is difficult to use a single edge operator in image processing to extract continuous and accurate contours of a porous bioelastomer due to the fuzzy boundary and complex background in ultrasound images. To solve this problem, this paper proposes a joint algorithm for bioelastomer contour detection and a texture feature extraction method for monitoring the degradation performance of bioelastomers. First, the mean-shift clustering method is utilized to obtain the clustering feature information of bioelastomers and native tissue from manually segmented images, and this information is used as the initial information in the image binarization algorithm for image partitioning. Second, Otsu's thresholding method and mathematical morphology are applied in the process of image binarization. Finally, the Canny edge detector is employed to extract the complete bioelastomers contour from the binary image. To verify the robustness of the proposed joint algorithm, the results using the proposed joint algorithm, where mean-shift clustering is replaced with k-means clustering are also obtained. The proposed joint algorithm based on mean-shift clustering outperforms the joint algorithm based on k-means clustering, as well as algorithms that directly apply the Canny, Sobel and Laplacian methods. Texture feature extraction is based on the computer-aided recognition of bioelastomers. The region of interest (ROI) is set in the scaffold region, and the first-order statistical features and second-order statistical features of the greyscale values of the ROI are extracted and analysed. The proposed joint algorithm can not only extract ideal bioelastomers contours from ultrasound images but also provide valuable feedback on the degradation behaviour of bioelastomers at implant sites.

Analysis of Image Preprocessing and Binarization Methods for OCR-Based Detection and Classification of Electronic Integrated Circuit Labeling

Automatic recognition and classification of electronic integrated circuits based on optical character recognition combined with the analysis of the shape of their housings are essential to machine vision methods supporting the production of electronic parts, especially small-volume ones in the through-hole technology, characteristic of printed circuit boards. Since such methods utilize binary images, applying appropriate image preprocessing and thresholding methods significantly influences the obtained results, particularly in uncontrolled illumination conditions. Therefore, the examination of various adaptive image binarization algorithms for this purpose is conducted in this paper, together with the experimental verification of the proposed method based on the pixel voting approach.

Influence of protocol scan on choroidal vascularity measurements: a spectralis optical coherence tomography study

ObjectivesTo compare choroidal vascularity index (CVI) measurements using the automated image binarization algorithm in healthy subjects with two Spectralis spectral-domain optical coherence tomography (SD-OCT) protocol scans.MethodsSixty-nine eyes of 69 healthy volunteers were included in this cross-sectional prospective study. Two subsequent horizontal 20°line scans passing through the fovea were acquired with enhanced-depth imaging mode with high speed (HS) and high resolution (HR) protocol scans. CVI and its subcomponents were measured with the previously validated automated algorithm. Differences between choroidal measurements obtained with HS and HR protocol scans were evaluated with t-test and Bland & Altman plots.ResultsA total of 33 male (47.8%) and 36 female (52.2%) subjects with a mean age of 35.1 ± 13.4 years were included. Overall, HS protocol scan was associated with significant lower values of total choroidal area (−0.047 mm2) and stromal choroidal area (−0.036 mm2), and a significant greater value of CVI (+0.010%) if compared to HR protocol. Luminal choroidal area was lower when calculated with the HS protocol, although it did not reach significance. To compare the two different protocols, the number of pixels should be multiplied for 3.87 ×5.73 when the CVI is measured on a HR OCT b scan and 3.87 ×11.46 for the HS OCT b scan.ConclusionsHS and HR acquisition modes significantly influence CVI and its subcomponents values measured with the automated software. However, adopting the scale factors can minimize the differences between the two protocol scans.

Digital fundus image quality assessment

Diabetic retinopathy (DR) is a disease caused by complications of diabetes. It starts asymptomatically and can end in blindness. To detect it, doctors use special fundus cameras that allow them to register images of the retina in the visible range of the spectrum. On these images one can see features, which determine the presence of DR and its grade. Researchers around the world are developing systems for the automated analysis of fundus images. At present, the level of accuracy of classification of diseases caused by DR by systems based on machine learning is comparable to the level of qualified medical doctors.The article shows variants for representation of the retina in digital images by different cameras. We define the task to develop a universal approach for the image quality assessment of a retinal image obtained by an arbitrary fundus camera. It is solved in the first block of any automated retinal image analysis system. The quality assessment procedure is carried out in several stages. At the first stage, it is necessary to perform binarization of the original image and build a retinal mask. Such a mask is individual for each image, even among the images recorded by one camera. For this, a new universal retinal image binarization algorithm is proposed. By analyzing result of the binarization, it is possible to identify and remove imagesoutliers, which show not the retina, but other objects. Further, the problem of no-reference image quality assessment is solved and images are classified into two classes: satisfactory and unsatisfactory for analysis. Contrast, sharpness and possibility of segmentation of the vascular system on the retinal image are evaluated step by step. It is shown that the problem of no-reference image quality assessment of an arbitrary fundus image can be solved.Experiments were performed on a variety of images from the available retinal image databases.

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast-based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. The proposed technique is then applied to identify surface cracks on the surface of roads, bridges or pavements. An extensive comparison with existing techniques is conducted on various datasets and subject to a number of evaluation criteria including the average F-measure ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$AF_\beta $ </tex-math></inline-formula> ) introduced here for dynamic quantification of the performance. Experiments on crack images, including those captured by unmanned aerial vehicles inspecting a monorail bridge. The proposed technique outperforms the existing methods on various tested datasets especially for GAPs dataset with an increase of about 1.4% in terms of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$AF_\beta $ </tex-math></inline-formula> while the mean percentage error drops by 2.2%. Such performance demonstrates the merits of the proposed HCNNFP architecture for surface defect inspection.

An automated vertical drift correction algorithm for AFM images based on morphology prediction

The atomic force microscope (AFM) has become a powerful tool in many fields. However, environmental noise and other disturbances are very likely to cause the AFM probe to vibrate, which lead to vertical drift in AFM imaging and limit its further application. Therefore, to correct image distortion caused by vertical drift, a morphology prediction based image correction algorithm is proposed in this paper. Specifically, a Gaussian–Hann filter is first designed for distorted AFM images, based on which, an adaptive image binarization algorithm is developed to achieve accurate object detection and background extraction. Furthermore, an advanced morphology prediction algorithm, consisting of morphological approximation prediction and morphological detail prediction, is proposed to correct image distortion by using the extracted substrate of a sample image. Approximate morphology is generated by an improved weighted fusion autoregressive model, and morphological detail is obtained by energy analysis based on discrete wavelet transform. Experimental and application results are presented to illustrate that the proposed algorithm is able to effectively eliminate vertical drift of AFM images.

Design of Trajectory Tracking Algorithm of Isolated Observation Point Automatic Distribution Vehicle based on Visual Servo

The medical isolation observation point for epidemic prevention and control is an important part of the epidemic prevention and control link. With the attention paid by all countries to the epidemic prevention and control, the design and construction of the medical isolation observation point for epidemic prevention and control have put forward higher requirements. This design uses a visual servo-based automatic delivery car for trajectory tracking and research on the tracking algorithm to realize the automatic delivery car for the regular delivery of medicines, food and other daily necessities for isolated personnel. The application of automatic trolleys in the epidemic prevention and control medical isolation observation point can effectively alleviate the pressure on staff, avoid infection, and improve the efficiency of epidemic prevention. Aiming at the complexity of its motion trajectory, a tracking algorithm of vision and information fusion is used to implement the trajectory tracking of the smart car. The trend of the target trajectory is determined by the least square method. The image information collected by the image binarization algorithm is added to a certain anti-jamming program. The PID algorithm is used to optimize the control of the steering gear and the drive motor, improve the operating efficiency and system stability, and meet the actual application.

Ultimate neutron and x-ray radiography images compression using artificial bee colony and firefly optimization algorithms

Optimum compression ratio (OCR) of neutron and x-ray radiography images with minimum decomposition distortion is the main target of this paper. Artificial bee colony (ABC) and firefly optimal algorithms are applied for achieving this goal. These algorithms are applied in conjunction with proposed image encoding/decoding and decomposition/decompression algorithms. The encoding/decoding algorithms depend on binary image, Huffman, and hierarchical trees. In addition, the decompression algorithms use real dual-tree transform, Hilbert transform, real a trou transform, and Gaussian pyramidal transform. A fitness function (FF) that correlates to compression ratio and image quality is conducted. The OCR with the best radiography image quality is the purpose of the suggested FF. A comparison between the optimized compressed ratio of x-ray and neutron radiography images for both optimization techniques is demonstrated. The proposed algorithms are validated. For the ABC algorithm, optimum values of 80.3610% and 80.3610% are fulfilled for x-ray and neutron images via hierarchical trees with Hilbert transforms. An optimum value of 85.333333% is attained by the Huffman algorithm with discrete cosine transform for both images. For the firefly optimization algorithm (FOA), the hierarchical trees with Hilbert transform achieve an optimum value of 97.0499% for both images. The binary image encoding with pyramidal transform gives optimum values of 68.8055% and 77.4566% for x-ray and neutron images, respectively. The FOA is noted to accomplish more advanced results over the ABC algorithm for compressed radiography images. Additionally, the binary image algorithm with a trou decompression provides an optimum value of 76.77% for neutron radiography images. The achieved optimum values of neutron images are better than of x-ray images due to the absorption of more energy by neutron radiation. Robustness and the significant task of the supposed FF are clarified. This confirms the applicability of image compression optimization algorithms with neutron and x-ray radiography images.

Optical method for measuring the volume fraction of granular media: Application to faced-centered cubic lattices of monodisperse spheres.

In order to understand the dynamics of granular flows, one must have knowledge about the solid volume fraction. However, its reliable experimental estimation is still a challenging task. Here, we present the application of a stochastic-optical method (SOM) [L. Sarno et al., Granul. Matter 18, 80 (2016)10.1007/s10035-016-0676-3] to an array of spheres arranged according to faced-centered cubic lattices, where spheres' locations are known a priori. The purpose of this study is to test the robustness of the image binarization algorithm, introduced in the SOM for the indirect estimation of the near-wall volume fraction through an optically measurable quantity, defined as two-dimensional volume fraction. A comprehensive range of volume fractions and illumination conditions are numerically and experimentally investigated. The proposed binarization algorithm is found to yield reasonably accurate estimations of the two-dimensional volume fraction with a root-mean-square error smaller than 0.03 for all investigated illumination conditions. A slightly worse performance is observed for samples with relatively low volume fractions (<0.3), where the binarization algorithm occasionally cannot identify the surface elements in the second and third layers of the regular lattice.

Monitoring driver attention distraction with binocular vision

Driver attention distraction (DAD) is a typical artificial factor traffic accident, and DAD monitoring can improve driving security. In this study, a method was developed for accurate DAD monitoring based on binocular vision. A binocular vision system was built, and camera parameters of the system were calibrated based on Open CV. In the method, the driver’s facial image is obtained by using active infrared imaging technology and preprocessed to locate the eye positions. The connected component labeling algorithm for binary images is used to pinpoint the eye locations. The characteristic information of the eye pupils is extracted with the least-squares ellipse fitting algorithm, and the characteristic information of the Purkinje image is obtained with the Harris corner detection algorithm. A DAD warning model based on the binocular vision system was established to evaluate the attention state of the driver.

Improving the processing of machine vision images of robotic systems in the Arctic

The transformation of the development of the Arctic is due to modern robotic systems. The use of unmanned vehicles in many industries in the Arctic provides an array of photo and video information. Accuracy of image analysis and pattern recognition is enhanced by image preprocessing. However, the existing binarization algorithms are not universal for images with different distortions and loss of information. The accuracy of binarization algorithms depends on many factors, such as shadows, uneven lighting, low contrast, noise, etc. Images with different characteristics of light and noise are simulated in order to model various lighting conditions on information from digital cameras of robotic systems. The paper investigates global and adaptive image binarization algorithms. The binarized images were obtained using these algorithms and the results of binarized images recognition are compared by an optical character recognition system. An analysis of the comparison results showed that for images made in poor lighting conditions or images with low contrast, or images with high noise levels, adaptive binarization algorithms are better suited. However, in most cases it is not possible to obtain fully correctly recognized images.The paper proposes a new binarization method based on artificial neural networks. The process of creating an artificial neural network is shown, include the parameters for determining the class of a pixel, the adjustment of weights, the architecture of an artificial neural network. A comparison of the proposed artificial neural network with existing image binarization algorithms demonstrate that in most cases the artificial neural network has the result of image processing at the level of adaptive algorithms or higher. The proposed method of images binarization based on the image color characteristics analysis allows to solve image recognition tasks by robotized systems.

Similarity assessment of quantum images

Similarity assessment of quantum images is important in the area of quantum image processing. In this paper, quantum counting is applied to five algorithms for similarity assessment of quantum images, which brings an advantage to the number of quantum measurement. Among these algorithms, one algorithm is suitable for quantum binary image, two algorithms are suitable for quantum gray image and two algorithms are suitable for quantum color images. Moreover, the similarity assessment of quantum gray and color images involves two quantum image binarization algorithms. At the end of the paper, the quantum circuit complexity of these algorithms is analyzed and then an example is given to demonstrate the functionality of the algorithm.

Choroidal vascularity index changes after vitreomacular surgery.

To study the structural changes in the choroid using swept-source (SS) optical coherence tomography (OCT), a tool for the choroidal vascularity index (CVI) following epiretinal membrane removal. Fifty-two eyes of 26 patients were evaluated in this prospective, single-centre, observational study. Twenty-six eyes underwent vitrectomy for epiretinal membrane removal (VT-group), and the control group consisted of 26 corresponding fellow eyes (F-group). All patients were evaluated at baseline, 30 and 90days postsurgery. Using a modified image binarization algorithm for SS-OCT scans, the subfoveal choroidal area was segmented into the luminal and stromal areas, and the CVI was measured by calculating the proportion of the luminal area (LA) to the cross-sectional choroid area. The mean CVI in the VT-group was 63.86±4.04% at the baseline, 62.45±4.21% at 30days postsurgery and 61.06±3.79% at 90days (p<0.001). The F-group had a mean CVI of 61.12±2.29% at the baseline, 60.91±2.25% at 30days postsurgery and 61.05±2.28% at 90days (p=0.29). The CVI decreases following epiretinal membrane removal when compared to the fellow eyes, which suggests structural changes in the vascular layers of the choroid. The implication of these results may be that secondary inflammation resulting from mechanical traction induces choroidal thickness by way of increased vascularization of the choroid.

LPI Radar Waveform Recognition Based on Time-Frequency Distribution.

In this paper, an automatic radar waveform recognition system in a high noise environment is proposed. Signal waveform recognition techniques are widely applied in the field of cognitive radio, spectrum management and radar applications, etc. We devise a system to classify the modulating signals widely used in low probability of intercept (LPI) radar detection systems. The radar signals are divided into eight types of classifications, including linear frequency modulation (LFM), BPSK (Barker code modulation), Costas codes and polyphase codes (comprising Frank, P1, P2, P3 and P4). The classifier is Elman neural network (ENN), and it is a supervised classification based on features extracted from the system. Through the techniques of image filtering, image opening operation, skeleton extraction, principal component analysis (PCA), image binarization algorithm and Pseudo–Zernike moments, etc., the features are extracted from the Choi–Williams time-frequency distribution (CWD) image of the received data. In order to reduce the redundant features and simplify calculation, the features selection algorithm based on mutual information between classes and features vectors are applied. The superiority of the proposed classification system is demonstrated by the simulations and analysis. Simulation results show that the overall ratio of successful recognition (RSR) is 94.7% at signal-to-noise ratio (SNR) of −2 dB.

Psychophysical Validation of A Digital Method to Assess Ill‐Defined Visual Boundaries: An Example with Fabric Openness Factor

AbstractFabric openness factor (OF) is the fraction of the web area that is uncovered by yarns.OFis a critical feature regarding the end‐use performance of the fabric and should be accurately assessed. However, digitalOFestimates yielded by image binarization algorithms differ among them depending on the criteria used, mainly due to ill‐defined boundaries, thus precluding a straightforward assessment of the actual fabricOFvalue. Lacking any standard to compare actualOFvalues with measuredOFvalues, we addressed the validation procedure of the digital assessment method from visualOFestimates.OFof 81 distinct fabric samples was evaluated from digital images by a panel of 18 observers using visual binarization technique. Following the psychophysical models of Fechner and Stevens, these visual estimates were correlated with digital estimates yielded by several binarization algorithms. Stevens’ psychophysical model and an automatic binarization algorithm developed by us scored the highest correlation.Practical ApplicationsThis work addresses the problems that arise at the moment of measuring the area of a region with ill‐defined boundaries without any standard to control the process of measurement. Similar problems are also found in important fields such as medical imaging. In these cases, there are usually different digital methods that give rise to estimates of the magnitude which mismatch among them. To solve these differences, a more common approach is to use estimates provided by a panel of observers and consider them to be objective, regardless of the bias between subjective responses and actual values. However, visual estimates do not show either accuracy (because they are psychophysical measures) or precision (due to the variability among observers). To overcome these difficulties, we propose a procedure to validate a digital method through visual estimates provided by a panel of observers, taking into account the psychophysical models of Fechner and Stevens.

Image Binarization using Intensity Range of Grayscale Images

The performance of binarization algorithms is determined by the selection of threshold value for binarization, and most of the previous binarization algorithms analyze the intensity distribution of the original images by using the histogram and determine the threshold value using the mean value of intensity or the intensity value corresponding to the valley of the histogram. The previous algorithms could not get the proper threshold value in the case that doesn't show the bimodal characteristic in the intensity histogram or for the case that tries to separate the feature area from the original image. Therefore, this paper proposed a novel algorithm for image binarization, which, first segments the intensity range of grayscale images to several intervals and calculates a mean value of intensity for each interval, and then repeats the interval integration until getting the final threshold value. The interval integration of two neighborhood intervals calculates the ratio of the distances between mean value and adjacent boundary value of two intervals and determine as the threshold value of the new integrated interval the intensity value that divides the distance between mean values of two intervals according to the ratio. The experiment for performance evaluation showed that the proposed algorithm generates the more effective threshold value than the previous algorithms.

A Improve Robust Watermarking Algorithm for Binary Images

A improve robust watermarking algorithm is proposed for binary images. The primary focus of the proposed algorithm lies in finding more flippable pixels and enhancing the robustness of watermarking. Based on Haar Wavelet Transform, the more flippable pixels was found not only in the neighbourhood but also in the Wavelet Transform domain. The embedding mechanism based on dynamic step size was proposed for enhancing the robustness of watermarking. And the experiment results and analyses demonstrate that proposed algorithm can find more flippable pixels, and is has better in robustness and invisibility.

The Chemical Stain Inspection of Polysilicon Solar Cell Wafer by the Fuzzy Theory Method

This study proposed an automatic optical inspection (AOI) technique to improve the inspection of chemical stains on solar wafers. Poly-silicon solar cell wafers were inspected for chemical stains, and the inspection was rapid and stable. The system used a laser-reflection-point-based AOI method for solar wafer chemical stain inspection. Based on the fuzzy theory, the image binarization algorithm could efficiently filter irrelevant image information, and the back-propagation method was also utilized to determine if the image was stained. The inspection algorithm integrated fuzzy theory and the back-propagation method in order to shorten the comparison time and quickly find the target. The experiment proved that the validity of the proposed method could achieve a recognition rate of 98% from among 1000 images.

Modified stable Euler-number algorithm implementation for real-time image binarization

The stable Euler-number-based image binarization has been shown to give excellent visual results for images containing high amount of image noise. Being computationally expensive, its applications are limited mostly to general-purpose processors and in application specific integrated circuits. In this paper a modified stable Euler-number-based algorithm for image binarization is proposed and its real-time hardware implementation in a Field Programmable Gate Array with a pipelined architecture is presented. The proposed modifications to the algorithm facilitate hardware implementation. The end result is a design that out-performs known software implementations. The amount of noisy pixels introduced during the binarization process is also minimized. Despite the stable Euler-number-based image binarization being computationally expensive, our simulations show that the proposed architecture gives accurate results and this in real time and without consuming all chip resources.