Post-processing Module Research Articles

Design and Development of Structural Parameter Identification Software for Nonlinear Vibration Isolators

This paper developed an object-oriented software to facilitate parameter calibration of the quasi-zero stiffness (QZS) vibration isolator for engineering applications. Considering its advantages of convenient programming and high noise resistance, we employ the harmonic balance method to construct the identification core algorithm. The developed software consists of data pre-processing, parameter identification, and post-processing modules. The data pre-processing module imports and classifies all the required data. Then, the parameter identification module conducts preliminary nonlinearity analysis so that nonlinear structural parameter identification can be successfully carried out. After parameter identification, the data post-processing module displays and stores the identified results. The performance of the software is tested by a numerical example of a two-degree-of-freedom QZS vibration isolator, proving the software can give accurate identification results within a few user-friendly graphical interfaces. Based on this software, we hope that the application and promotion of nonlinear system parameter identification become more convenient.

A Neural Coordination Strategy for Attachment and Detachment of a Climbing Robot Inspired by Gecko Locomotion.

Climbing behavior is a superior motion skill that animals have evolved to obtain a more beneficial position in complex natural environments. Compared to animals, current bionic climbing robots are less agile, stable, and energy-efficient. Further, they locomote at a low speed and have poor adaptation to the substrate. One of the key elements that can improve their locomotion efficiency is the active and flexible feet or toes observed in climbing animals. Inspired by the active attachment-detachment behavior of geckos, a hybrid pneumatic-electric-driven climbing robot with active attachment-detachment bionic flexible feet (toes) was developed. Although the introduction of bionic flexible toes can effectively improve the robot's adaptability to the environment, it also poses control challenges, specifically, the realization of attachment-detachment behavior by the mechanics of the feet, the realization of hybrid drive control with different response characteristics, and the interlimb collaboration and limb-foot coordination with a hysteresis effect. Through the analysis of geckos' limbs and foot kinematic behavior during climbing, rhythmic attachment-detachment strategies and coordination behavior between toes and limbs at different inclines were identified. To enable the robot to achieve similar foot attachment-detachment behavior for climbing ability enhancement, we propose a modular neural control framework comprising a central pattern generator module, a post-processing central pattern generation module, a hysteresis delay line module, and an actuator signal conditioning module. Among them, the hysteresis adaptation module helps the bionic flexible toes to achieve variable phase relationships with the motorized joint, thus enabling proper limb-to-foot coordination and interlimb collaboration. The experiments demonstrated that the robot with neural control achieved proper coordination, resulting in a foot with a 285% larger adhesion area than that of a conventional algorithm. In addition, in the plane/arc climbing scenario, the robot with coordination behavior increased by as much as 150%, compared to the incoordinated one owing to its higher adhesion reliability.

Development and Application of Digital Twin Analysis Module for Low Impact Development Techniques

In this study, a digital twin analysis module capable of LID (Low Impact Development) interpretation for various rainfall scenarios was developed. The low-impact development digital twin model consists of a rainfall input module, a SWMM (Storm Water Management Model) -based LID analysis module, a reservoir tracking-based LID analysis module, and a post-processing module. Rainfall scenarios that can be applied in the developed model can simulate stochastic rainfall by frequency and daily heavy rainfall over the last 10 years. Additionally, the results of rainfall-loss-outflow for subwatersheds and inflow-outflow for total LID facilities (five types) are provided. If the LID DT (Digital Twin) simulator developed in this way is used, various water environment information such as the water circulation improvement and water quality reduction effects in the target area can be provided in a series of processes from the low-impact development facility planning stage to the operation management stage.

Backend Bug Finder — a platform for effective compiler fuzzing

Introduction: The standard way to check the quality of a compiler is manual testing. However, it does not allow to cover a vast diversity of programs that can be written in a target programming language. Today, in addition to manual written tests there are many automated compiler testing methods, among which fuzzing is one of the most powerful and useful. A compiler fuzzer is a tool that generates a random program in a target language and checks how the compiler works in this language. Purpose: To develop a platform for compiler fuzzing and, based on it, to develop a tool for Kotlin compiler testing. Results: We have developed Backend Bug Finder which is a platform for compiler fuzzing is. We have chosen a mutation-based approach as a method for generating random programs. First, an existing program is entered to the mutator as the input to be then transformed in some way. Mutations can be both trivial, for example, replacing arithmetic operators with others, and complex, changing the structure of the program. Next, the resulting program is fed to the input of the compiler with the following check of its operation. The developed test oracle can detect three types of errors: crashes, miscompilations, and performance degradations. If an error is detected, the test case is fed into the post-processing module, where reduction and deduplication algorithms are applied. We have developed a tool for fuzzing the Kotlin language compiler based on the platform for its approbation, which showed the applicability of the proposed approach for finding errors in modern compilers. Practical relevance: Over a year and a half of work, our tool has found thousands of different Kotlin compiler bugs, more than 200 of which were sent to the developers, and more than 80 have been fixed.

SafeFac: Video-based smart safety monitoring for preventing industrial work accidents

This work presents SafeFac, an intelligent camera-based system for managing the safety of factory environments. In SafeFac a set of cameras installed on the assembly line are used to capture images of workers that approach the machinery under hazardous situations to alert system managers and halt the line if needed. Given a challenging set of practical application-level requirements such as multi-camera support and low response latency, SafeFac exploits a YOLOv3-based light-weight human object detection. To address the latency–accuracy tradeoff, SafeFac incorporates a set of algorithms as pre- and post-processing modules and a novel adaptive camera scheduling scheme.Our evaluation with a video dataset containing more that 113,000 frames from real assembly line activity shows that SafeFac achieves high precision (99.93%) and recall (96.44%), and SafeFac successfully satisfies such challenging requirements as a ready-for-deployment system for safe factory management.

A Data-Driven System Based on Deep Learning for Diagnosis Fetal Cavum Septum Pellucidum in Ultrasound Images

Cavum septum pellucidum (CSP) is one of the most important physiologic structures that should be detected in Ultrasound (US) scanning for the normal development of the fetal central nervous system. However, manual measurement of CSP is still a difficult and time-consuming task due to the high noise of US images, even for experienced sonographers. Especially considering that maternal mortality remains high in many developing countries, a data-driven system with a medical diagnosis can help sonographers and obstetricians make decisions rapidly and improve their work efficiency. In this study, we propose a novel data-driven system based on deep learning for the diagnosis of CSP called CA-Unet, which consists of a channel attention network to segment the CSP and a post-processing module to measure and diagnose the anomalies of CSP. We collected the US data from three hospitals in China from 2012 to 2018 year to validate the effectiveness of our system. Experiments on a fetal US dataset demonstrated that our proposed system is able to help doctors make decisions and has achieved the highest precision of 79.5% and the largest Dice score of 77.5% in the segmentation of CSP.

A deep learning method for individual arable field (IAF) extraction with cross-domain adversarial capability

The monitoring of agricultural fields from remote sensing imagery allows for the effective management of agricultural resources at large spatial scales. Deep learning-based methods have shown great potential in the extraction of individual arable fields (IAF) from high-resolution imagery; however, accurate boundary localization and collection of adequate training samples remain a challenge. This study proposes a novel deep learning network (FieldSeg-DA) to extract IAFs from Chinese high-resolution satellite imagery (Gaofen-2). FieldSeg-DA adopts a parallel network structure consisting of two branch networks (UNet and DeepNetV3+) to independently extract the boundary and extent of IAFs. A post-processing module, connecting boundaries and filling field (CB-FF), was used to integrate the extracted boundary and extent and promote the integrity of each extracted IAF. The parallel network coupled with CB-FF improved the boundary and extent accuracy of IAF extraction. Moreover, we used fine-grain adversarial domain adaption (FADA) in the training stage to promote the transferability of the trained network from source domains with labeled samples to target domains without any labeled samples. We found that FieldSeg-DA outperformed IAFRes, a state-of-the-art method for IAF extraction, in both the source and target domains, with improvements of 0.016 and 0.069 in the F1-score, respectively. Therefore, the proposed FieldSeg-DA method has the potential to extract IAFs accurately across diverse farming areas without training samples.

Monitoring non-specific adsorption at solid-liquid interfaces by supercritical angle fluorescence microscopy.

Supercritical angle fluorescence (SAF) microscopy is a novel imaging tool based on the use of distance-dependent fluorophore emission patterns to provide accurate locations of fluorophores relative to a surface. This technique has been extensively used to construct accurate cellular images and to detect surface phenomena in a static environment. However, the capability of SAF microscopy in monitoring dynamic surface phenomena and changes in millisecond intervals is underexplored in the literature. Here, we report on a hardware add-on for a conventional inverted microscope coupled with a post-processing Python module that extends the capability of SAF microscopy to monitor dynamic surface adsorption in sub-second intervals, thereby greatly expanding the potential of this tool to study surface interactions, such as surface fouling and competitive surface adhesion. The Python module enables researchers to automatically extract SAF profiles from each image. We first assessed the performance of the system by probing the specific binding of biotin-fluorescein conjugates to a neutravidin-coated cover glass in the presence of non-binding fluorescein. The SAF emission was observed to increase with the quantity of bound fluorophore on the cover glass. However, a high concentration of unbound fluorophore also contributed to overall SAF emission, leading to over-estimation in surface-bound fluorescence. To expand the applications of SAF in monitoring surface phenomena, we monitored the non-specific surface adsorption of BSA and non-ionic surfactants on a Teflon-AF surface. Solution mixtures of bovine serum albumin (BSA) and nine Pluronic/Tetronic surfactants were exposed to a Teflon-AF surface. No significant BSA adsorption was observed in all BSA-surfactant solution mixtures with negligible SAF intensity. Finally, we monitored the adsorption dynamics of BSA onto the Teflon-AF surface and observed rapid BSA adsorption on Teflon-AF surface within 10s of addition. The adsorption rate constant (ka) and half-life of BSA adsorption on Teflon-AF were determined to be 0.419 ± 0.004s-1 and 1.65 ± 0.016s, respectively, using a pseudo-first-order adsorption equation.

A quality enhancement network with coding priors for constant bit rate video coding

Video coding can effectively compress data, while the introduction of compression artifacts degrades the visual quality and the performance of artificial intelligence video applications. Video quality enhancement (VQE) methods can improve compressed video quality without modifying the coding standard’s main modules. The existing VQE works mainly aim to improve video quality in the constant quantization parameter (CQP) coding mode. However, constant bit rate (CBR) coding mode is widely used in some streaming playback video applications, and VQE at CBR is more challenging than that at CQP. This article presents a novel Constant bit rate Video quality enhancement Network combined with Coding priors (CVCN). The proposed CVCN can be inserted into High Efficiency Video Coding (HEVC) codec as a CNN-based in-loop filter (LF) module or a post-processing module out of the codec. Moreover, we design a two-pass training strategy for the LF module to overcome multiple filtering. To adapt the QP diversity of CBR videos, we utilize the coding unit (CU)-wise QP prior by constructing a CU-wise QP adaptive module (CQAM) and a QP adaptive multi-scale residual block (QAMSRB) based on CQAM. We construct the CU-partition prior (CPP) by exploiting the relationship between the compression noise and CU partition information. A novel CPP spatial-attention block is proposed to combine the CPP with the self-attention module. Furthermore, the proposed CVCN can effectively enhance CBR videos at different bits per pixel (BPP) via a single model. Extensive experimental results show the superiority of the CVCN over state-of-the-art VQE approaches for CBR videos.

Suffixation Rules of Manipuri Verbs in English to Manipuri Machine Translation

The suffixation of verbs plays an important role in the formation of a meaningful sentence in Manipuri language. All the verbs in Manipuri are bound roots. So, there is always a suffix at the verb in Manipuri sentences. In English language, the tense of a sentence is determined from the verb but in Manipuri language, the tense of a sentence is determined from the suffix(es) associated with the verb. English to Manipuri Machine Translation (EMMT) is a rule-based automatic translation system. In EMMT, the suffixation rules of Manipuri verbs are essential for the derivation of an appropriate suffix(es) of the translated verb in Manipuri from the input English sentence. In this MT, suffixation rules are proposed to use in the post-processing module as a new approach. This paper presents the process of EMMT, different suffixation rules of Manipuri verbs and implementation in EMMT according to the types of tense in English.

Medical terminology-based computing system: a lightweight post-processing solution for out-of-vocabulary multi-word terms

The linguistic rules of medical terminology assist in gaining acquaintance with rare/complex clinical and biomedical terms. The medical language follows a Greek and Latin-inspired nomenclature. This nomenclature aids the stakeholders in simplifying the medical terms and gaining semantic familiarity. However, natural language processing models misrepresent rare and complex biomedical words. In this study, we present MedTCS—a lightweight, post-processing module—to simplify hybridized or compound terms into regular words using medical nomenclature. MedTCS enabled the word-based embedding models to achieve 100% coverage and enabled the BiowordVec model to achieve high correlation scores (0.641 and 0.603 in UMNSRS similarity and relatedness datasets, respectively) that significantly surpass the n-gram and sub-word approaches of FastText and BERT. In the downstream task of named entity recognition (NER), MedTCS enabled the latest clinical embedding model of FastText-OA-All-300d to improve the F1-score from 0.45 to 0.80 on the BC5CDR corpus and from 0.59 to 0.81 on the NCBI-Disease corpus, respectively. Similarly, in the drug indication classification task, our model was able to increase the coverage by 9% and the F1-score by 1%. Our results indicate that incorporating a medical terminology-based module provides distinctive contextual clues to enhance vocabulary as a post-processing step on pre-trained embeddings. We demonstrate that the proposed module enables the word embedding models to generate vectors of out-of-vocabulary words effectively. We expect that our study can be a stepping stone for the use of biomedical knowledge-driven resources in NLP.

Accurate segmentation of green fruit based on optimized mask RCNN application in complex orchard.

Fruit and vegetable picking robots are affected by the complex orchard environment, resulting in poor recognition and segmentation of target fruits by the vision system. The orchard environment is complex and changeable. For example, the change of light intensity will lead to the unclear surface characteristics of the target fruit; the target fruits are easy to overlap with each other and blocked by branches and leaves, which makes the shape of the fruits incomplete and difficult to accurately identify and segment one by one. Aiming at various difficulties in complex orchard environment, a two-stage instance segmentation method based on the optimized mask region convolutional neural network (mask RCNN) was proposed. The new model proposed to apply the lightweight backbone network MobileNetv3, which not only speeds up the model but also greatly improves the accuracy of the model and meets the storage resource requirements of the mobile robot. To further improve the segmentation quality of the model, the boundary patch refinement (BPR) post-processing module is added to the new model to optimize the rough mask boundaries of the model output to reduce the error pixels. The new model has a high-precision recognition rate and an efficient segmentation strategy, which improves the robustness and stability of the model. This study validates the effect of the new model using the persimmon dataset. The optimized mask RCNN achieved mean average precision (mAP) and mean average recall (mAR) of 76.3 and 81.1%, respectively, which are 3.1 and 3.7% improvement over the baseline mask RCNN, respectively. The new model is experimentally proven to bring higher accuracy and segmentation quality and can be widely deployed in smart agriculture.

Real-time train motion parameter estimation using an Unscented Kalman Filter

Train movement dynamics are usually modelled by means of Newton’s second law. The resulting dynamic equation can be very precise if the parameters that it depends on are determined accurately. However, these parameters may vary in time and show wide variations, making the calibration task nontrivial and jeopardizing the performance of a broad variety of applications in the railway industry: from timetable planning and railway traffic simulation to Driver Advisory Systems and Automatic Train Operation. In this article, the online train motion model calibration problem is addressed with a special focus on energy-efficient on-board applications. To this end, location and speed measurements are assumed to be available for a train running under normal operation conditions. A well-known real-time parameter estimation algorithm, the Unscented Kalman Filter, is combined with a driving regime calculator and a post-processing module in order to obtain bounds and statistics of parameters such as the maximum applied tractive effort and power, the applied brake rates, the cruise speed and the length of the final coasting and braking. The proposed framework is tested in a case study with real data from trains operating on the Eindhoven-’s-Hertogenbosch corridor in the Netherlands. Results obtained show that UKF is able to track the speed and location measurements and to estimate the parameters that model the running resistance in the dynamic equation. The proposed driving regime and the post-processing modules can determine the current regime accurately and give a deeper insight into the variations of the driving style, respectively.

Modelling suspended particulate matter dynamics at an Antarctic fjord impacted by glacier melt

When Antarctic glaciers retreat, high sediment loads from geomorphological and glaciological sources can disturb the biota, especially filtering organisms, and thereby significantly alter the ecology of the Antarctic coast. We applied the Finite volumE Sea-ice Ocean-Coastal Model (FESOM-C), a numerical tool equipped with a sediment module, to simulate for the first time the suspended particulate matter (SPM) dynamics in a fjordic environment at the northern West Antarctic Peninsula, Potter Cove as a case study. Depth-averaged SPM dynamics during a meteorologically representative austral summer (120 days from December to March) considered tidal and atmospheric forcing. Additionally, idealised experiments with passive particles based on post-processing Lagrangian module identified and followed possible material trajectories in Potter Cove. Particle dynamics in the area show them to be primarily tidal and wind-driven, sensitive to bathymetry, with the higher SPM concentrations in the inner cove and the highest hydrographical complexity in the transitional area between the fjordic and marine habitat. The SPM plume covers 5.5 km2 of the total inlet of 9 km2, with monthly mean values between 15 and 330 mg/l. The maximum SPM concentrations are during January (790 mg/l), and the maximum plume expansion during February. The model was validated with available in situ measurements. With this study, we can identify areas in Potter Cove (and similar coastal fjordic environments, prospectively) of increasing physical stress by longer SPM residence time and high accumulation rates induced by glacial meltwater. These factors are crucial for pelagic and benthic assemblages dependent on light and food availability, as well sediment deposition.

Contrast Normalization Filtering Modules for Segmentations of Retinal Blood Vessels from Color Retinal Fundus Images

Vision loss is one of the main complications of eye disease, especially diabetic retinopathy (DR), because DR is a silent disease affecting the retina of the eye and resulting in loss of vision. Manual observation of eye disease takes time and delays effective treatment, so computerized methods are used to diagnose eye disease by extracting their features such as blood vessels, optic disc, and other abnormalities. Many computerized methods are proposed but it is still lacking to obtain small vessels. To overcome this problem, we have proposed methods based on image processing techniques for detection of retinal vessels. The proposed method is based on the elimination of uneven illumination using morphological tactics and principal component analysis. These initial steps are known as the preprocessing module, and our post-processing module contains the vessel coherence and the double threshold binarization method to obtain an image of the segmented vessels. Our proposed method obtained comparable results (average results (sensitivity: 0.78, specificity: 0.95 and precision: 0.951)) compared to the existing methods on the DRIVE and STARE databases.

Data assimilation of adaptive observation and application for typhoon forecasts over the Western North Pacific

In this study, we added the post-processing module of the Ensemble Transform Sensitivity (ETS) to identify regions sensitive to adaptive observations of different variables at different levels for typhoon forecasts. We selected five cases between 2015 and 2020 over the Western North Pacific (WNP) using 50 ensemble forecasts from the European Center provided by the THORPEX Interactive Grand Global Ensemble (TIGGE) portal. Furthermore, intercomparison experiments were performed to explore the impact of adaptive observational data assimilation with conventional observations and Himawari-8 data over the sensitive (SEN), non-sensitive (NOSEN), and all studied regions (ALL) on typhoon forecasts using the Gridpoint Statistical Interpolation (GSI) assimilation system of the National Centers for Environmental Prediction (NCEP) of United States. The results show that the assimilation of less observational data in the SEN areas can achieve the forecast effect of assimilation in ALL regions, the intensity error can be reduced by approximately 15%, and the track error is reduced in some cases. Finally, detailed analysis of the circulation field and flux perspectives for Typhoon Lekima, which occurred in August 2019 over the WNP, confirmed our conclusion. At 1800 UTC on August 8, the data assimilation was performed over the SEN, NOSEN, and ALL areas. The initial circulation field, in which the vorticity increased in the southwest of the typhoon and decreased in the southeast, benefited the westward movement of the typhoon. The 18 h forecast indicated that the circulation in the SEN area assimilation experiment showed a negative vorticity increase in the southwest side of the typhoon and positive potential temperature as well as water vapor forecast differences on its north side, which contrasted with the results obtained in the NOSEN and ALL experiments. This provided favorable weather conditions for the typhoon to change direction and move northward. Targeted observation experiments investigating Typhoon Lekima indicated that assimilating observations of sensitive areas greatly improves typhoon forecasting and assimilation efficiency. However, the ALL experiment yielded the best forecast among the three cases.

Learned Block-Based Hybrid Image Compression

Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. First, parallel acceleration of the autoregressive entropy model cannot be achieved due to serial decoding. Second, full-resolution inference often causes the out-of-memory (OOM) problem with limited GPU resources, especially for high-resolution images. Block partition is a good choice to handle the above issues, but it brings about new challenges in reducing the redundancy between blocks and eliminating block effects. To tackle the above challenges, this paper provides a learned block-based hybrid image compression (LBHIC) framework. Specifically, we introduce explicit intra prediction into a learned image compression framework to utilize the relation among adjacent blocks. Superior to context modeling by linear weighting of neighbor pixels in traditional codecs, we propose a contextual prediction module (CPM) to better capture long-range correlations by utilizing the strip pooling to extract the most relevant information in neighboring latent space, thus achieving effective information prediction. Moreover, to alleviate blocking artifacts, we further propose a boundary-aware postprocessing module (BPM) with the edge importance taken into account. Extensive experiments demonstrate that the proposed LBHIC codec outperforms the VVC, with a bit-rate conservation of 4.1%, and reduces the decoding time by approximately 86.7% compared with that of state-of-the-art learned image compression methods.

Learning to Detect Open Carry and Concealed Object With 77 GHz Radar

Detecting harmful carried objects plays a key role in intelligent surveillance systems and has widespread applications, for example, in airport security. In this paper, we focus on the relatively unexplored area of using low-cost 77GHz mmWave radar for the carried objects detection problem. The proposed system is capable of real-time detecting three classes of objects - laptop, phone, and knife - under open carry and concealed cases where objects are hidden with clothes or bags. This capability is achieved by the initial signal processing for localization and generating range-azimuth-elevation image cubes, followed by a deep learning-based prediction network and a multi-shot post-processing module for detecting objects. Extensive experiments for validating the system performance on detecting open carry and concealed objects have been presented with a self-built radar-camera testbed and collected dataset. Additionally, the influence of different input formats, factors, and parameters on system performance is analyzed, providing an intuitive understanding of the system. This system would be the very first baseline for other future works aiming to detect carried objects using 77GHz radar.

Dual-path transformer-based network with equalization-generation components prediction for flexible vibrational sensor speech enhancement in the time domain.

The flexible vibrational sensor (FVS) has the potential to become a popular wearable communication device because of its natural noise shielding characteristics and soft materials. However, FVS speech faces a severe loss of frequency components. To improve speech quality, a time-domain neural network model based on the dual-path transformer combined with equalization-generation components prediction (DPT-EGNet) is proposed. More specifically, the DPT-EGNet consists of five modules, namely the pre-processing module, dual-path transformer module, equalization module, generation module, and post-processing module. The dual-path transformer module is leveraged to extract the local and global contextual relationship of long-term speech sequences, which is extremely beneficial for inferring the missing components. The equalization and generation modules are designed according to the characteristics of FVS speech, which further improve the speech quality by simulating the inversion process of the speech distortion. The experimental results demonstrate that the proposed model effectively improves the quality of FVS speech; the average perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and composite measure for overall speech quality (COVL) scores of three males and three females are relatively increased by 64.19%, 29.63%, and 101.37%, which is superior to other baseline models developed in different domains. The proposed model also has significantly lower complexity than the others.

Computerized Analysis of Mammogram Images for Early Detection of Breast Cancer

Breast cancer is widespread worldwide and can be cured if diagnosed early. Using digital mammogram images and image processing with artificial intelligence can play an essential role in breast cancer diagnosis. As many computerized algorithms for breast cancer diagnosis have significant limitations, such as noise handling and varying or low contrast in the images, it can be difficult to segment the abnormal region. These challenges could be overcome by proposing a new pre-processing model, exploring its impact on the post-processing module, and testing it on an extensive database. In this research work, the three-step method is proposed and validated on large databases of mammography images. The first step corresponded to the database classification, followed by the second step, which removed the pectoral muscle from the mammogram image. The third stage utilized new image-enhancement techniques and a new segmentation module to detect abnormal regions in a well-enhanced image to diagnose breast cancer. The pre-and post-processing modules are based on novel image processing techniques. The proposed method was tested using data collected from different hospitals in the Qassim Health Cluster, Qassim Province, Saudi Arabia. This database contained the five categories in the Breast Imaging and Reporting and Data System and consisted of 2892 images; the proposed method is analyzed using the publicly available Mammographic Image Analysis Society database, which contained 322 images. The proposed method gives good contrast enhancement with peak-signal to noise ratio improvement of 3 dB. The proposed method provides an accuracy of approximately 92% on 2892 images of Qassim Health Cluster, Qassim Province, Saudi Arabia. The proposed method gives approximately 97% on the Mammographic Image Analysis Society database. The novelty of the proposed work is that it could work on all Breast Imaging and Reporting and Data System categories. The performance of the proposed method demonstrated its ability to improve the diagnostic performance of the computerized breast cancer detection method.