Gray-level Images Research Articles

A Bioengineered Cathepsin B-sensitive Gas Vesicle Nanosystem That Responds With Increased Gray-level Intensity of Ultrasound Biomicroscopic Images

ObjectivesThis work aimed to promote the interaction of a modified Gas Vesicle (GV) with Cathepsin B (CTSB) protease and analyzed their backscattered signal by Ultrasound (US). MethodsWe modified the sequence of the gene coding for GvpC to contain a CTSB cleavage and expressed the protein in an Escherichia coli recombinant system. The protein was purified and added to GVs preparations in which the original GvpC was removed (ΔGV), constituting the modified GV (GV*). Western Blot (WB) test was used to compare GVs with GvpC and engineer GvpC at starting (T0) and after 24 hours (T24) reacting with CTSB. A 21 MHz US B-mode and nonlinear contrast-mode (5% total power) imaged US phantoms having samples of GVwt, ΔGV (stripped GV), GV*, and CTSB+GV*. Also, a 21MHz US B-mode imaged US phantoms having a tumor cell line extracellular fraction (TCEF) and the TCEF+GV* sample. A 100% total US power was applied to collapse the GV structure. ResultsIn WB we detected a decrease in engineered GvpC levels 24 h after the incubation of GV* with CTSB, compared to the concentration at T0, suggesting that CTSB cleaved the engineered GvpC. Regions-of-interest over image of phantom cross-sections were determined and the B-mode image mean gray level intensity resulted in a significant (p<0.05) increase comparing CTSB+GV* with PBS (control), GVwt, ΔGV and GV*. Non-linear mode image gray level intensity from CTSB+GV* increased by 11.79, 7.86 and 14.75 dB from samples containing GVwt, ΔGV and GV*, respectively. GV preparations incubated with TCEF and the TCEF+GV* sample showed an increase of 81% in signal compared to TCEF+GVwt. ConclusionsThe increased ultrasound backscattered signal intensity suggests GVs as a potential biosensor for protease activity, possibly aiding the detection of protease-rich tissue regions.

Based on PVM image gray level data to analysis the effect of N-vinyl caprolactam on hydrate growth

The usage of hydrate inhibitors is an effective method to solve the problem of flow assurance in deep-water pipelines. However, the mechanism of hydrate formation and transformation in inhibitor-containing systems is not well understood, and the research methodology needs to be innovated. In this study, a possible mechanism of wearing away during hydrate particle transformation was proposed for the first time, based on the hydrate growth process in the system containing the kinetic inhibitor N-vinyl caprolactam monomer. A method to analysed the hydrate growth and transformation dynamics through the change of gray level in the image was proposed. And the hydrate growth process was divided into three different stages based on the trend analysis of the gray level data of the images,trends in the dynamics of hydrate particle growth within the bulk phase corresponding to changes in gray level were verified. On this basis, the effects of stirring rate, subcooling and the monomer concentration of the NVCap on the growth of hydrates were discussed, and it was suggested that there might be differences in the mechanisms exhibited by the inhibitor at different growth stages of hydrates. In this study, the process of analysing the internal growth dynamics of hydrate systems through image gray levels was reported for the first time, and its trend changes corresponding to hydrate growth dynamics were verified, which proved the feasibility of this method, and this study provides an innovative research methodology and idea for the study of the dynamics of hydrate generation and transformation.

Examining feature extraction and classification modules in machine learning for diagnosis of low-dose computed tomographic screening-detected in vivo lesions.

Medical imaging-based machine learning (ML) for computer-aided diagnosis of in vivo lesions consists of two basic components or modules of (i)feature extraction from non-invasively acquired medical images and (ii)feature classification for prediction of malignancy of lesions detected or localized in the medical images. This study investigates their individual performances for diagnosis of low-dose computed tomography (CT) screening-detected lesions of pulmonary nodules and colorectal polyps. Three feature extraction methods were investigated. One uses the mathematical descriptor of gray-level co-occurrence image texture measure to extract the Haralick image texture features (HFs). One uses the convolutional neural network (CNN) architecture to extract deep learning (DL) image abstractive features (DFs). The third one uses the interactions between lesion tissues and X-ray energy of CT to extract tissue-energy specific characteristic features (TFs). All the above three categories of extracted features were classified by the random forest (RF) classifier with comparison to the DL-CNN method, which reads the images, extracts the DFs, and classifies the DFs in an end-to-end manner. The ML diagnosis of lesions or prediction of lesion malignancy was measured by the area under the receiver operating characteristic curve (AUC). Three lesion image datasets were used. The lesions' tissue pathological reports were used as the learning labels. Experiments on the three datasets produced AUC values of 0.724 to 0.878 for the HFs, 0.652 to 0.965 for the DFs, and 0.985 to 0.996 for the TFs, compared to the DL-CNN of 0.694 to 0.964. These experimental outcomes indicate that the RF classifier performed comparably to the DL-CNN classification module and the extraction of tissue-energy specific characteristic features dramatically improved AUC value. The feature extraction module is more important than the feature classification module. Extraction of tissue-energy specific characteristic features is more important than extraction of image abstractive and characteristic features.

A complementary Diagnostic Tool for Diabetic Peripheral Neuropathy Through Muscle Ultrasound and Machine Learning Algorithms

Diabetic peripheral neuropathy represents one of the common long-terms complications that effect about fifty percentage?of diabetes patients. The habitual diagnosis tool based on nerve conduction study that examine the nerve damage and classify the patient status into normal and diabetic peripheral neuropathy with degree of severity without considering the effect on skeletal muscle and take on patient data. A complementary diagnostic tool proposed, in this study integrates the patient’s data including body mass index, age and duration of diabetic, average blood glucose levels, nerve conduction study that involves amplitude and latency of peroneal and tibial nerves and muscle ultrasound alongside the machine learning algorithms to facilitate the clinicians for a precise diagnosis. A group of control and diabetic patients utilized to gather the data with calculating the muscle thickness and statistical properties from the gray-level ultrasound images of six skeletal muscles. Support vector machine, naïve bayes, ensemble of bagged tree and artificial neural network supervised machine learning algorithms categorize each class with a high classification accuracy, 98.1% for tibialis anterior with naïve bayes algorithm. The outcomes of this study show a promising complementary diagnostic tool that will help the clinicians to perform an exact diagnosis and disclose the side effect on both nerves and muscles of diabetic patients.

NFS-23. ASSOCIATION OF LOCALIZED MAGNETIC RESONANCE IMAGING FEATURES IN ANTERIOR VISUAL PATHWAY WITH VISUAL ACUITY LOSS AMONG CHILDREN WITH NF1-OPG

Abstract BACKGROUND Half of children with optic pathway gliomas associated with neurofibromatosis type 1 (NF1-OPG) are at risk for vision acuity (VA) loss. NF1-OPGs manifest along the anterior visual pathway (AVP), where the overall shape and volume from MRI have been recently associated with VA loss. To investigate the added value of localized features within the optic nerves (ONs) and chiasm, we propose an automatic deep-learning framework for VA loss prediction from volumetric and radiomic analysis of ONs, chiasm, and AVP. METHODS We collected MRIs of 60 children with NF1-OPG from Children’s National Hospital (CNH, GE platform) and 75 from Children’s Hospital of Philadelphia (CHOP, Siemens platform). MRI sequences included T1-, T2-weighted and T2-FLAIR. Experts annotated the AVP to establish ground truth. Neuro-ophthalmic evaluation identified VA loss (LogMAR &amp;gt;= 0.2) in 52/135 children. Automatic AVP segmentation was performed using the Swin transformer network. ONs and chiasm were split through template-based registration. Brain volume, tumor location, child age, and 1,172 radiomic features were used to predict VA loss using support vector machines. Sequential feature selection associated with risk VA loss was done using sensitivity and univariate statistical tests (ANOVA). We compared predictions based on new ON and chiasm analysis with results based on AVP alone. RESULTS Balanced accuracy, sensitivity, specificity, and AUROC of VA loss prediction were 0.865, 0.882, 0.857, 0.899, respectively. Significant risk factors were maximal image intensity and gray level run length entropy in T2-FLAIR for ONs, and image intensity range in T2-FLAIR for chiasm. AUROC based on analysis of AVP alone dropped to 0.728 (p-value=0.028). CONCLUSIONS Deep learning-based analysis indicates an association of new localized MRI features in ONs and chiasm with VA loss, which show enhanced capability in predicting VA loss. This automated framework has the potential to accelerate and guide the treatment decisions for children with NF1-OPGs.

Joint reconstruction algorithm: combining synchrotron radiation with conventional X-ray computed tomography for improved imaging

Synchrotron radiation (SR) is an excellent light source for micro-CT (micro-computed tomography) applications due to its monochromaticity and high brightness, which are crucial for achieving high-resolution imaging. However, when scanning larger objects, the limited field of view (FOV) of SR will lead to data truncation, limiting its utilization efficiency. To address this limitation, this paper proposed a method to integrate conventional X-ray CT data to supplement the truncated SR data for joint reconstruction to improve imaging. We first employ a polynomial transformation to match the image gray levels from the two distinct light sources and then resample these to form joint data. Subsequently, the method derives noise images from the noise characteristics of the projection data to construct image weight constraint that accurately reflects different data quality from two sources. The flexibility of the image weight constraint also allows for its combination with various denoisers to further enhance the reconstruction quality. Experimental results demonstrate that the proposed method can leverage the strengths of both imaging modalities to facilitate larger scale and high-resolution imaging.

A comparative radiographic study of bone density changes around titanium implants in the posterior mandible, preoperative, and postoperative

Background: Implant success and the state of the surrounding bone require multiple measures, especially in humans, and this study aimed to identify the development of the state of the latter by means of radiographic examination performed during the period of osseointegration as well as investigate the changes in bone density that occur after implant installation and 2 months after functional loading. Implant success rates are affected by bone density at the implant site. Therefore, understanding changes in bone density after dental implant placement is essential, as it correlates with subsequent implant success. Materials and methods: Digital radiographs of 28 implants were taken and evaluated at four intervals: preoperatively, 1 and 3 months postoperatively, and 2 months following placement of the permanent prosthesis. Gray values were measured in different areas around the implants through analyzing X-ray images and measuring bone density around the implants using EzDent – 2D software. The aim of this study was to investigate changes in bone density around implants in three regions: apex, neck, and body, as well as to record average density values during the observation period by measuring digital image gray levels (the gray values of the digital radiographs). This was conducted to determine local bone densities in dental implant recipient sites and to study changes in local bone densities at different intervals, preoperatively and postoperatively and after placement of the prosthesis. Results: A decrease was observed in gray values proportional to reference values 1-month after implant insertion, but these increased at 3 months after insertion and continued to rise 2 months after placement of the prosthesis in the apical, body, and neck regions of the implant. Conclusion: Sensor-tuned radiography can be used as an effective method to support clinical follow-ups as well as measure changes in bone densities around implants in critical cases.

Radiometric thermometry of point targets based on dual-band infrared imaging

The observation area of a point target, which is usually inaccessible, is a necessary condition when utilizing the conventional single-band infrared radiometric thermometry method, as the image gray level inevitably undergoes dispersion. Otherwise, significant errors will be generated, seriously affecting the applicability of infrared radiometric thermometry for distant point targets in the external field. To address the above issue, the infrared radiometric thermometry method for point targets has been researched. A point target radiometric thermometry method based on dual-band infrared imaging is proposed, which can effectively measure radiance and temperature when the area of the point target is unknown. The experimental results show that, compared with conventional single-band algorithms, the proposed dual-band point target thermometry algorithm has a maximum error of 11.18°C under the condition of unknown area, which can meet the needs of infrared radiometric thermometry of point targets at long distances in the external field.

Characterizing the internal wave wakes and synthetic aperture radar image features of underwater moving objects

In this study, a refined and improved theoretical model was proposed for calculating the synthetic aperture radar (SAR) images of internal wave wakes. This model was based on an equivalent source model of internal wave wakes and the velocity-bunching principle. Wake field, scattering field, and SAR image characteristics were systematically calculated for multiple scenarios. The model described the transfer and solution processes by inputting the background flow field temperature and salinity profiles to map the radar image intensity distribution. The physical mechanisms of the internal wave wake generation and its capture by SAR were comprehensively explained. The effects of various parameters on the internal wave wake SAR images were analyzed comprehensively. The SAR image features containing internal wave wakes were determined based on the gray-level co-occurrence matrix and image power spectrum, which revealed that the maximum surface current induced by the internal wave modes of the same amplitude was considerably larger than that induced by surface-wave mode. When traveling far from the water surface, the rate of change in the total scattering coefficient because of the Bragg effect was approximately 20 times that of the slope effect. In SAR images, the recognizability of wakes depends primarily on the maximum intensity rather than the average disturbance on the sea surface. Therefore, SAR images exhibit considerable differences during downwind radar observations, with the most prominent contrast differences occurring at the maximum spreading angle of wake scattering and 1500 m behind underwater objects. In the image power spectrum, the frequency range of the first modal internal waves was approximately 10–30 Hz, whereas the higher-order modal internal waves had frequencies lower than 10 Hz. Furthermore, the frequency range of the surface-wave mode was larger than that of internal-wave modes, approximately 50–60 Hz.

Characteristics of slurry-water mixing region in fractured rock mass grouting process: Experimental study

Grouting is one of the most commonly used methods to control water inrush disasters in fractured rock mass. At present, most of the research on the diffusion process of fracture grouting is carried out on the hypothesize that the groundwater was completely displaced by the slurry, which is lack of sufficient theoretical basis. Therefore, a one-dimensional visual fracture grouting experimental system was developed and a new characterization method of slurry concentration based on the image gray level was proposed in this paper in order to characterize the variation law of slurry-water mixing region during the grouting process. Results show that there exists slurry-water mixing region at the frontal surface of the diffusion slurry in the grouting process in fractured rock mass. The slurry-water mixing region can be characterized by the gray level of the images captured by cameras. The relationship of water to cement ratio of slurry (w/c) and image gray level of slurry (G) conforms to linear function, which can be expressed by G = 19.17 w/c when w/c is between 0.8 and 10. In addition, slurry concentration decreased linearly along the diffusion flow path in the slurry-water mixing region. The size of slurry-water mixing region is positively related to grouting flow rate, the mass ratio of water to cement (w/c) and fracture aperture when the grouting flow rate is between 0.6 L/min to 2.4 L/min, w/c is between 0.8 and 1.6 and fracture aperture is between 1 mm to 5 mm. Furthermore, the ratio of slurry-water mixing region size to hypothetical diffusion radius (RSR) was proposed to characterize development degree of slurry-water mixing region. The stable value of RSR was between 0.04 and 0.24 under the experimental conditions in this paper. The index of RSR can be used to provide theoretical basis for the simplification of the interface between slurry and water. The distribution rules of the slurry-water mixing region can be applied to predict the diffusion range more accurately and perfect the grouting theory.

Automatic design of W-operators using membership functions: a case study in brain MRI segmentation

A W-operator is an image transformation that is locally defined inside a window W, invariant to translations. The automatic design of the W-operators consists of the design of functions, whose domain is a set of patterns or vectors obtained by translating a window through training images and the output of each vector is a class or label. The main difficulty to consider when designing W-operators is the generalization problem that occurs due to lack of training images. In this work, we propose the use of membership functions to solve the generalization problem in gray level images. Membership functions are defined from the training images to model regions that are often inaccurate due to ambiguous gray levels in the images. This proposal was applied to brain magnetic resonance image segmentation to test its performance in a field of interest in biomedical images. The experiments were carried out with different numbers of training and test images, windows sizes of 3×3\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3\ imes 3$$\\end{document}, 5×5\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$5\ imes 5$$\\end{document}, 7×7\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$7\ imes 7$$\\end{document}, 11×11\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$11\ imes 11$$\\end{document}, and 15×15\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$15\ imes 15$$\\end{document}, and images with noise levels at 0, 1, 3, 5, 7, and 9%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}. To calculate the performance of each designed W-operator, the classification error, sensitivity, and specificity were used. From the experimental results, it was concluded that the best performance is achieved with a window of size 3×3\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3\ imes 3$$\\end{document}. In images with noise levels from 1 to 5%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, the classification error is less than 4%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} and the sensitivity and specificity are greater than 94 and 98%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, respectively.

A Multicenter Cohort Study on 301 Tissue-Level Implants: Cumulative Implant Survival Rate and Marginal Bone Level Change up to 4.5 Years.

To retrospectively determine the cumulative survival rate (CSR) and marginal bone level change (ΔMBL) around novel hybrid design tissue-level (TL) dental implants that support multiple-screw-retained restorations. Implant CSRs were analyzed at the implant and patient level using Kaplan-Meier estimates. ΔMBL was measured by comparing the periapical loading and follow-up visit radiographs using an improved standardized digital methodology based on image gray levels. ΔMBL outcomes were subject to linear mixed regression to identify potential risk factors. A total of 301 TL implants in 69 patients with an average age of 62.6 ± 11.7 years (range: 36 to 87 years) at the time of implant placement were considered for the analysis. All 301 implants were successfully restored and loaded. The 54-month CSRs at the implant and patient levels were 98.9% (95% CI: 96.7 to 99.6) and 95.3% (95% CI: 86.1 to 98.5), respectively. ΔMBL after a mean follow-up of 22 ± 10.7 months after loading was 0.00 ± 0.57 mm. None of the implant sites showed marginal bone loss exceeding 1.5 mm. Multivariate regression analysis revealed a significant association between ΔMBL and the loading protocol (P = .027) but not between ΔMBL and age or transgingival height. The high CSRs and stable peri-implant marginal bone levels support the use of recent TL implants, which have a hybrid design inherited from the bone-level implant-abutment connection, as a suitable treatment option for restoring partially or fully edentulous patients with a good mid-term prognosis. These results should be complemented by further prospective studies in a real-world multicenter private practice setup that represents the daily realities of implant treatment.

Robust image registration for analysis of multisource eye fundus images

This study underscores the crucial role of image preprocessing in enhancing the outcomes of multimodal image registration tasks using scale-invariant feature selection. The primary focus is on registering two types of retinal images, assessing a methodology’s performance on a set of retinal image pairs, including those with and without microaneurysms. Each pair comprises a color optical image and a gray-level fluorescein image, presenting distinct characteristics and captured under varying conditions. The SIFT methodology, encompassing five stages, with preprocessing as the initial and pivotal stage, is employed for image registration. Out of 35 test retina image pairs, 33 (94.28%) were successfully registered, with the inability to extract features hindering automatic registration in the remaining pairs. Among the registered pairs, 42.42% were retinal images without microaneurysms, and 57.57% had microaneurysms. Instead of simultaneous registration of all channels, independent registration of preprocessed images in each channel proved more effective. The study concludes with an analysis of the fifth registration’s resulting image to detect abnormalities or pathologies, highlighting the challenges encountered in registering blue channel images due to high intrinsic noise.

Stable and invertible invariants description for gray-level images based on Radon transform

Stable and invertible invariants description for gray-level images based on Radon transform

A machine learning system to identify progress level of dry rot disease in potato tuber based on digital thermal image processing

This study proposed a quick and reliable thermography-based method for detection of healthy potato tubers from those with dry rot disease and also determination of the level of disease development. The dry rot development inside potato tubers was classified based on the Wiersema Criteria, grade 0 to 3. The tubers were heated at 60 and 90 °C, and then thermal images were taken 10, 25, 40, and 70 s after heating. The surface temperature of the tubers was measured to select the best treatment for thermography, and the treatment with the highest thermal difference in each class was selected. The results of variance analysis of tuber surface temperature showed that tuber surface temperature was significantly different due to the severity of disease development inside the tuber. Total of 25 thermal images were prepared for each class, and then Otsu’s threshold method was employed to remove the background. Their histograms were extracted from the red, green, and blue surfaces, and, finally, six features were extracted from each histogram. Moreover, the co-occurrence matrix was extracted at four angles from the gray level images and five features were extracted from each co-occurrence matrix. Totally, each thermograph was described by 38 features. These features were used to implement the artificial neural networks and the support vector machine in order to classify and diagnose the severity of the disease. The results showed that the sensitivity of the models in the diagnosis of healthy tubers was 96 and 100%, respectively. The overall accuracy of the models in detecting the severity of tuber tissue destruction was 93 and 97%, respectively. The proposed methodology as an accurate, nondestructive, fast, and applicable system reduces the potato loss by rapid detection of the disease of the tubers.

Global optimization radiometric calibration method for an infrared system with a wide dynamic range.

Considering the conventional calibration restriction of the complicated calibration procedures, narrow dynamic range, and less correlation in the calibration data, a global optimization radiometric calibration method is proposed in this paper. First, a unified database is generated by integrating different gray-level images, neutral density attenuators, integration times, and target radiations under the deduced infrared physical model. Then, the calibration coefficients are automatically learned through the relative error backward propagation network. Finally, experiments are conducted on a large-aperture ground-based infrared system to evaluate the effectiveness of the proposed method. The results indicate the proposed method can solve the problem of learning imbalance with large fluctuations of infrared radiation, ensure global measurement precision with a simpler calibration procedure, and accurately measure the internal stray radiation of the optical system.

Process modeling and optimization in laser drilling of bulk metallic glasses based on GABPNN and machine vision

It is a challenging to ensure the quality of microholes during the laser drilling of bulk metallic glasses (BMGs), where the defects such as heat-affected zones, burrs, and low smoothness are usually obtained. Based on machine vision, back-propagation neural network (BPNN), and genetic algorithm (GA) in artificial intelligence technology, a relationship model between the microhole features and laser processing parameters was proposed, so as to predict and optimize the processing parameters during the laser drilling of BMGs. Firstly, the geometric parameters and texture information of microholes were obtained using fractal theory and machine vision techniques, including the gray-level co-occurrence matrix (GLCM) algorithm, image binarization, and edge extraction. A comprehensive numerical characterization of various microhole features was conducted, providing the basis for subsequent prediction and optimization. Secondly, the previously-extracted microhole features were set as input layer, and the processing parameters were set as output layer. After proper training, the BP neural network optimization model (GABPNN), based on the genetic algorithm, was established. As compared to the original BPNN model, the GABPNN model exhibited improved performance, reducing the maximum prediction error from 4.860% to 2.285%. Thirdly, with a set of input layer parameters, the required processing parameters were predicted by the model. The predicted results were verified in experiments, where good surface quality of the laser-drilled BMG microholes with good roundness and small ablation was obtained. This shows that it is feasible to predict and optimize processing parameters by GABPNN based on feature parameters extracted by machine vision.

Tchebichef moments and bat optimization algorithm-based information hiding and authentication of medical gray level images

Tchebichef moments and bat optimization algorithm-based information hiding and authentication of medical gray level images

Adaptive high-gray image enhancement algorithm based on logarithmic mapping and simulated exposure

In the fields of industry, security, military and other areas, high gray-level low contrast images have been widely used. However, due to the large dynamic range of gray level, high noise, blurry detail information and low contrast, it brings difficulties to subsequent image enhancement, target detection and other processes. Ordinary image enhancement algorithms are only suitable for conventional 8-bit images, which are not effective to deal with high-gray and low-contrast images. To address these issues, this paper proposed an adaptive high-gray image enhancement algorithm based on logarithmic mapping and simulated exposure, which was used for processing X-ray film images, infrared images, SAR images and other high gray-level low contrast images. Firstly, a detailed algorithm model construction method was provided for high gray-level low contrast images. Secondly, in order to verify the universality of the algorithm proposed in this paper, qualitative and quantitative experimental analyses were carried out using X-ray film images, infrared images and SAR images respectively. Finally, taking the most complex infrared image in the application environment as an example, the images, enhanced by the algorithm proposed in this paper, were sent to the YOLOv8 neural network for target detection, which improved the detection accuracy. The experiment shows that the algorithm, proposed in this paper, can significantly improve the image quality of high gray-level low contrast images, the detail information is obvious and the contrast is significantly improved. Various indicators are far higher than those of traditional algorithms. At the same time, this algorithm can provide reliable technical support for applications, such as target detection and target tracking in this field.

FPGA-Based CNN for Eye Detection in an Iris Recognition at a Distance System

Neural networks are the state-of-the-art solution to image-processing tasks. Some of these neural networks are relatively simple, but the popular convolutional neural networks (CNNs) can consist of hundreds of layers. Unfortunately, the excellent recognition accuracy of CNNs comes at the cost of very high computational complexity, and one of the current challenges is managing the power, delay and physical size limitations of hardware solutions dedicated to accelerating their inference process. In this paper, we describe the embedding of an eye detection system on a Zynq XCZU4EV UltraScale+ multiprocessor system-on-chip (MPSoC). This eye detector is used in the application framework of a remote iris recognition system, which requires high resolution images captured at high speed as input. Given the high rate of eye regions detected per second, it is also important that the detector only provides as output images eyes that are in focus, discarding all those seriously affected by defocus blur. In this proposal, the network will be trained only with correctly focused eye images to assess whether it can differentiate this pattern from that associated with the out-of-focus eye image. Exploiting the neural network’s advantage of being able to work with multi-channel input, the inputs to the CNN will be the grey level image and a high-pass filtered version, typically used to determine whether the iris is in focus or not. The complete system synthetises other cores and implements CNN using the so-called Deep Learning Processor Unit (DPU), the intellectual property (IP) block released by AMD/Xilinx. Compared to previous hardware designs for implementing FPGA-based CNNs, the DPU IP supports extensive deep learning core functions, and developers can leverage DPUs to conveniently accelerate CNN inference. Experimental validation has been successfully addressed in a real-world scenario working with walking subjects, demonstrating that it is possible to detect only eye images that are in focus. This prototype module includes a CMOS digital image sensor that provides 16 Mpixel images, and outputs a stream of detected eyes as 640 × 480 images. The module correctly discards up to 95% of the eyes present in the input images as not being correctly focused.