Histogram Features Research Articles

Real-Time Tracking of Objects in Video Based on Adaptive Histogram Features

Real-Time Tracking of Objects in Video Based on Adaptive Histogram Features

Sistem Temu Kembali Citra Termal Kanker Payudara Pada Citra Rekam Medis

Medical record images (Medical Imaging) in the form of the thermal images can be able to detect of of breast cancer as early detector for the patient. The technic process is by utilizing the thermal image of an existing breast cancer patient, the thermal image of the new patient can be searched by the similarities the image of the old patient. In order to get the exactly results, required an accurate system to find the thermal imaging of breast cancer patients in the thermal image database. This study aims to build a Content Based Imaged Retrieval (CBIR) system for thermal images of breast cancer patients based on thermal images have been diagnosed by specialist doctors. This system with using a combination of color histogram features and dominant color descriptors. To determine the similarity between the query image and the dataset image with using of two methods that is measuring the Euclidean Distance and the Minkowski Distance. The results of this research show from testing the combination between the two features, the F-measure evaluation value obtained from the top 10 retrieval was in the healthy image category of 0.07 and 0.09 in the cancer image category. From the conducting testing process result, the concluded is the most appropriate feature in carrying out the breast thermal image retrieval process is using a combination of dominant color descriptor features and color histograms.

Limitations of Out-of-Distribution Detection in 3D Medical Image Segmentation.

Deep learning models perform unreliably when the data come from a distribution different from the training one. In critical applications such as medical imaging, out-of-distribution (OOD) detection methods help to identify such data samples, preventing erroneous predictions. In this paper, we further investigate OOD detection effectiveness when applied to 3D medical image segmentation. We designed several OOD challenges representing clinically occurring cases and found that none of the methods achieved acceptable performance. Methods not dedicated to segmentation severely failed to perform in the designed setups; the best mean false-positive rate at a 95% true-positive rate (FPR) was 0.59. Segmentation-dedicated methods still achieved suboptimal performance, with the best mean FPR being 0.31 (lower is better). To indicate this suboptimality, we developed a simple method called Intensity Histogram Features (IHF), which performed comparably or better in the same challenges, with a mean FPR of 0.25. Our findings highlight the limitations of the existing OOD detection methods with 3D medical images and present a promising avenue for improving them. To facilitate research in this area, we release the designed challenges as a publicly available benchmark and formulate practical criteria to test the generalization of OOD detection beyond the suggested benchmark. We also propose IHF as a solid baseline to contest emerging methods.

Haralick texture analysis for microdosimetry: characterization of Monte Carlo generated 3D specific energy distributions

Objective. Explore the application of Haralick textural analysis to 3D distributions of specific energy (energy imparted per unit mass) scored in cell-scale targets considering varying mean specific energy (absorbed dose), target volume, and incident spectrum. Approach. Monte Carlo simulations are used to generate specific energy distributions in cell-scale water voxels ((1 μm)3–(15 μm)3) irradiated by photon sources (mean energies: 0.02–2 MeV) to varying mean specific energies (10–400 mGy). Five Haralick features (homogeneity, contrast, entropy, correlation, local homogeneity) are calculated using an implementation of Haralick analysis designed to reduce sensitivity to grey level quantization and are interpreted using fundamental radiation physics. Main results. Haralick measures quantify differences in 3D specific energy distributions observed with varying voxel volume, absorbed dose magnitude, and source spectrum. For example, specific energy distributions in small (1–3 μm) voxels with low magnitudes of absorbed dose (10 mGy) have relatively high measures of homogeneity and local homogeneity and relatively low measures of contrast and entropy (all relative to measures for larger voxels), reflecting the many voxels with zero specific energy in an otherwise sporadic distribution. With increasing target size, energy is shared across more target voxels, and trends in Haralick measures, such as decreasing homogeneity and increasing contrast and entropy, reflect characteristics of each 3D specific energy distribution. Specific energy distributions for sources of differing mean energy are characterized by Haralick measures, e.g. contrast generally decreases with increasing source energy, correlation and homogeneity are often (not always) higher for higher energy sources. Significance. Haralick texture analysis successfully quantifies spatial trends in 3D specific energy distributions characteristic of radiation source, target size, and absorbed dose magnitude, thus offering new avenues to quantify microdosimetric data beyond first order histogram features. Promising future directions include investigations of multiscale tissue models, targeted radiation therapy techniques, and biological response to radiation.

Radiomics for Parkinson's disease classification using advanced texture-based biomarkers

Parkinson's disease (PD) is one of the neurodegenerative diseases and its manual diagnosis leads to time-consuming process. MRI-based computer-aided diagnosis helps medical experts to diagnose PD more precisely and fast. Texture-based radiomic analysis is carried out on 3D MRI scans of T1 weighted and resting-state modalities. 43 subjects from Neurocon and 40 subjects from Tao-Wu dataset were examined, which consisted of 36 scans of healthy controls and 47 scans of Parkinson's patients. Total 360 2D MRI images are selected among around 17000 slices of T1-weighted and resting scans of selected 72 subjects. Local binary pattern (LBP) method was applied with custom variants to acquire advanced textural biomarkers from MRI images. LBP histogram helped to learn discriminative local patterns to detect and classify Parkinson's disease. Using recursive feature elimination, data dimensions of around 150-300 LBP histogram features were reduced to 13-21 most significant features based on score, and important features were analysed using SVM and random forest algorithms. Variant-I of LBP has performed well with highest test accuracy of 83.33%, precision of 84.62%, recall of 91.67%, and f1-score of 88%. Classification accuracies were obtained from 61.11% to 83.33% and AUC-ROC values range from 0.43 to 0.86 using four variants of LBP.•Parkinson's classification is carried out using an advanced biomedical texture feature. Texture extraction using four variants of uniform, rotation invariant LBP method is performed for radiomic analysis of Parkinson's disorder.•Proposed method with support vector machine classifier is experimented and an accuracy of 83.33% is achieved with 10-fold cross validation for detection of Parkinson's patients from MRI-based radiomic analysis.•The proposed predictive model has proved the potential of textures of extended version of LBP, which have demonstrated subtle variations in local appearance for Parkinson's detection.

A 3D Point Cloud Feature Identification Method Based on Improved Point Feature Histogram Descriptor

A significant amount of research has been conducted on the segmentation of large-scale 3D point clouds. However, efficient point cloud feature identification from segmentation results is an essential capability for computer vision and surveying tasks. Feature description methods are algorithms that convert the point set of the point cloud feature into vectors or matrices that can be used for identification. While the point feature histogram (PFH) is an efficient descriptor method, it does not work well with objects that have smooth surfaces, such as planar, spherical, or cylindrical objects. This paper proposes a 3D point cloud feature identification method based on an improved PFH descriptor with a feature-level normal that can efficiently distinguish objects with smooth surfaces. Firstly, a feature-level normal is established, and then the relationship between each point’s normal and feature-level normal is calculated. Finally, the unknown feature is identified by comparing the similarity of the type-labeled feature and the unknown feature. The proposed method obtains an overall identification accuracy ranging from 71.9% to 81.9% for the identification of street lamps, trees, and buildings.

Unenhanced computed tomography radiomics help detect endoleaks after endovascular repair of abdominal aortic aneurysm

ObjectivesTo explore the feasibility of unenhanced CT images for endoleak detection of abdominal aortic aneurysm (AAA) after endovascular repair (EVAR).MethodsPatients who visited our hospital after EVAR from July 2014 to September 2021 were retrospectively collected. Two radiologists evaluated the presence or absence of endoleaks using the combination of contrast-enhanced and unenhanced CT as the referenced standard. After segmenting the aneurysm sac of the unenhanced CT, the radiomic features were automatically extracted from the region of interest. Histogram features of patients with and without endoleak were statistically analyzed to explore the differences between the two groups. Twelve common machine learning (ML) models based on radiomic features were constructed to evaluate the performance of endoleak detection with unenhanced CT images.ResultsThe study included 216 patients (69 ± 8 years; 191 men) with AAA, including 64 patients with endoleaks. A total of 1955 radiomic features of unenhanced CT were extracted. Compared with patients without endoleak, the aneurysm sac outside the stent of patients with endoleak had higher CT attenuation (41.7 vs. 33.6, p < 0.001) with smaller dispersion (51.5 vs. 58.8, p < 0.001). The average area under the curve (AUC) of the ML models constructed with unenhanced CT radiomics was 0.86 ± 0.05, the accuracy was 81% ± 4, the sensitivity was 88% ± 10, and the specificity was 78% ± 5. When fixing the sensitivity to > 90% (92% ± 2), the models retained specificity at 72% ± 10.ConclusionsUnenhanced CT features exhibit significant differences between patients with and without endoleak and can help detect endoleaks in AAA after EVAR with high sensitivity.Clinical relevance statementUnenhanced CT radiomics can help provide an alternative method of endoleak detection in patients who have adverse reactions to contrast media. This study further exploits the value of unenhanced CT examinations in the clinical management and surveillance of postoperative abdominal aortic aneurysm.Key Points• Unenhanced CT features of the aneurysm sac outside the stent exhibit significant differences between patients with and without endoleak. The endoleak group showed higher unenhanced CT attenuation (41.7 vs 33.6, p < .001) with smaller dispersion (51.5 vs 58.8, p < .001) than the nonendoleak group.• Unenhanced CT radiomics can help detect endoleaks after intervention. The average area under the curve (AUC) of twelve common machine learning models constructed with unenhanced CT radiomics was 0.86 ± 0.05, the average accuracy was 81% ± 4.• When fixing the sensitivity to > 90% (92% ± 2), the machine learning models retained average specificity at 72% ± 10.

Determining the features of histograms of dangerous parameters of the gas environment in the absence and occurrence of fire

The object of research is histograms of the dynamics of dangerous parameters of the gas environment, the values of which are measured in real time at the intervals of absence and ignition of materials. The method of determining histograms during a typical selection of measurements is described. This method allows one to determine histograms for samples of an arbitrary position and the size of the data interval of measurements of the dynamics of dangerous parameters of the gas environment. On the basis of histograms on the intervals of the absence and occurrence of fires of test materials, indicators of their summary statistics can be determined. Laboratory experiments were conducted to study the features of the histograms of carbon monoxide concentration, smoke density, and temperature of the gas medium for intervals of reliable absence and appearance of ignition of materials in the form of alcohol and textiles. The results of the analysis of the histograms clearly show that the dynamics of the studied dangerous parameters at the indicated intervals differ from the Gaussian. At the same time, the histograms differ in shape, which depends on the type of ignition material and the corresponding dangerous parameter. Based on the features of the histograms of the dynamics of dangerous parameters on the intervals of the absence and appearance of fires of test materials, the simplest indicators of summary statistics in the form of the range, number, and position of the modes are determined. It was established that when alcohol ignites, the variation range of carbon monoxide concentration, smoke density, and gas temperature increases from 0.545, 0.068, and 0.161 to 7.121, 0.523, and 8.71, respectively. At the same time, the range of variation of these parameters during textile ignition increases from 0.182, 0.205, and 0.323 to 0.394, 0.386, and 2.903, respectively. The obtained results in aggregate or one by one can be used in practice for early detection of fires in order to prevent the occurrence of fires in premises

Research on the Clothing Classification of the She Ethnic Group in Different Regions Based on FPA-CNN

In order to achieve the effective computer recognition of the She ethnic clothing from different regions through the extraction of color features, this paper proposes a She ethnic clothing classification method based on the Flower Pollination Algorithm-optimized color feature fusion and Convolutional Neural Network (FPA-CNN). The method consists of three main steps: color feature fusion, FPA optimization, and CNN classification. In the first step, a color histogram and color moment features, which can represent regional differences in She ethnic clothing, are extracted. Subsequently, FPA is used to perform optimal weight fusion, obtaining an optimized ratio. Kernel principal component analysis is then applied to reduce the dimensionality of the fused features, and a CNN is constructed to classify the She ethnic clothing from different regions based on the reduced fused features. The results show that the FPA-CNN method can effectively classify the She ethnic clothing from different regions, achieving an average classification accuracy of 98.38%. Compared to SVM, BP, RNN, and RBF models, the proposed method improves the accuracy by 11.49%, 7.7%, 6.49%, and 3.92%, respectively. This research provides a reference and guidance for the effective recognition of clothing through the extraction of color features.

Two-stage classification strategy for breast cancer diagnosis using ultrasound-guided diffuse optical tomography and deep learning.

Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated great potential for breast cancer diagnosis in which real-time or near real-time diagnosis with high accuracy is desired. We aim to use US-guided DOT to achieve an automated, fast, and accurate classification of breast lesions. We propose a two-stage classification strategy with deep learning. In the first stage, US images and histograms created from DOT perturbation measurements are combined to predict benign lesions. Then the non-benign suspicious lesions are passed through to the second stage, which combine US image features, DOT histogram features, and 3D DOT reconstructed images for final diagnosis. The first stage alone identified 73.0% of benign cases without image reconstruction. In distinguishing between benign and malignant breast lesions in patient data, the two-stage classification approach achieved an area under the receiver operating characteristic curve of 0.946, outperforming the diagnoses of all single-modality models and of a single-stage classification model that combines all US images, DOT histogram, and imaging features. The proposed two-stage classification strategy achieves better classification accuracy than single-modality-only models and a single-stage classification model that combines all features. It can potentially distinguish breast cancers from benign lesions in near real-time.

An Automated Lion-Butterfly Optimization (LBO) based Stacking Ensemble Learning Classification (SELC) Model for Lung Cancer Detection

Lung cancer is one of the most serious and prevalent cancers in the globe. Early detection of lung cancer can increase a patient's chances of life. Computed Tomography (CT) scan images are difficult for clinicians to utilize in order to determine the stages of cancer. Computer-aided systems can assist researchers in more precisely predicting the stages of lung cancer in recent times. This study demonstrates the use of technology that is made possible by machine learning and image processing to accurately classify and predict the lung cancer from CT images. The existing tumor detection frameworks have the major difficulties in terms of high complexity, overfitting and error prediction. Therefore, the proposed work aims to formulate a simple and accurate automated system for the prediction and classification of lung cancer from CT images. Before classifying the input lung scan image, an adaptive median filtering approach is used to improve its contrast and quality. From the segmented lung parts, the histogram and texture features are derived. The most relevant characteristics are chosen using the Lion-Butterfly Optimization (LBO) method for training and testing operations. Eventually, the input CT picture is correctly predicted as either healthy or disease-affected using the Stacking Ensemble Learning Classification (SELC) algorithm. In this study, a thorough performance evaluation is conducted utilizing several measures in order to analyze the outcomes

Improved method for positioning crane grab boom corner points using Hough transform and k‐means clustering

AbstractIn the process of automatic grabbing of bridge segment beams, it is crucial to accurately locate and align the corner points of the crane's boom with the beam's lifting holes. This requires the utilization of image processing techniques to precisely detect and locate the corner points of the crane's boom. Existing feature matching methods face challenges such as low detection accuracy and unsuitability for this specific scenario. This article proposes a novel approach for corner point localization by using the intersection points of lines, facilitating the matching of feature points between left and right images. The method consists of three steps: first, a grayscale difference map is constructed by utilizing the R and G channels of the RGB color space. This enhances the bimodal characteristics of the grayscale histograms between the foreground and background, which facilitates the subsequent binarization process. Additionally, opening and closing operations are employed to remove small artifacts from the Canny edge detection results, effectively reducing noise. Second, an adaptive thresholding method based on the mean and variance of Hough transform voting scores is proposed. This method filters out interference lines from the clustering results by selecting appropriate voting scores. Furthermore, an improved centroid calculation method is introduced, which utilizes weighted formulas based on different proportions of voting scores. These weighted formulas replace the original clustering centroids as the basis for line fitting. Finally, the corner coordinates of the crane's boom are computed based on the line fitting results, and the recognition accuracy is compared under different lighting conditions. Experimental results demonstrate that the proposed algorithm exhibits smaller detection errors and higher robustness compared to other corner detection algorithms, particularly when there are numerous interference edge points in the edge detection results. The computed corner coordinates achieve pixel‐level accuracy. The algorithm performs optimally under strong supplementary lighting conditions, with an average detection error percentage of 97.1% within 0–2 pixels and a recognition accuracy of 98.6%. The recognition success rates under different lighting conditions are all above 92.9%. This method is superior to traditional corner detection methods, meets the requirements for automatic grabbing of the boom, and holds practical engineering value. It provides a basis for addressing the accuracy and robustness challenges of crane algorithms influenced by multiple environmental factors.

Monitoring Built-Up Edge, Chipping, Thermal Cracking, and Plastic Deformation of Milling Cutter Inserts through Spindle Vibration Signals

Condition monitoring provides insights into the type of damage occurring in the cutting tool during machining to facilitate its timely maintenance or replacement. By detecting and analyzing machining consequences (vibrations, chatter, noise, power consumption, spindle load, etc.), correlating them with different tool conditions enables real-time monitoring and the automated detection of tool failures. Machine learning (ML) plays a vital role in making tool condition monitoring (TCM) frameworks intelligent, and most research is geared toward classifying various types of tool wear. However, monitoring built-up edges, chipping, thermal cracking, and plastic deformation of milling cutter inserts are challenging and need careful consideration. To effectively monitor these phenomena, spindle vibrations can narrate the corresponding dynamic behavior of tool conditions and therefore have been investigated in this research. The acquired vibration data are then analyzed using histogram features and trained through the Partial C4.5 (PART) classifier to extract meaningful recommendations related to the milling cutter inserts condition.

Design of an Unordered Gripping System Based on 3D Vision

For the current mainstream 2D vision-guided robotic arm gripping system in industrial production, the vision part is seriously affected by the lighting environment, camera imaging distance, and other factors. It cannot provide more comprehensive 6DOF position information on the target workpiece and complete the gripping of mutually scattered and stacked workpieces. This paper designs a disordered grasping system based on the 3D vision to solve the above problems. In addition, the traditional Euclidean clustering algorithm and fast point feature histogram algorithm are improved to enhance the segmentation and feature recognition efficiency of the point cloud. The accuracy of the system is 94.3 % without stacking and 88.2 % with stacking, which is 5.2 % higher than the average accuracy of the system before the algorithm improvement and more than 2s higher than the time. The accuracy and speed of the system meet the requirements of general industrial production for a robotic arm grasping system, which has certain practical application value.

Point Cloud Registration Based on Fast Point Feature Histogram Descriptors for 3D Reconstruction of Trees

Three-dimensional (3D) reconstruction is an essential technique to visualize and monitor the growth of agricultural and forestry plants. However, inspecting tall plants (trees) remains a challenging task for single-camera systems. A combination of low-altitude remote sensing (an unmanned aerial vehicle) and a terrestrial capture platform (a mobile robot) is suggested to obtain the overall structural features of trees including the trunk and crown. To address the registration problem of the point clouds from different sensors, a registration method based on a fast point feature histogram (FPFH) is proposed to align the tree point clouds captured by terrestrial and airborne sensors. Normal vectors are extracted to define a Darboux coordinate frame whereby FPFH is calculated. The initial correspondences of point cloud pairs are calculated according to the Bhattacharyya distance. Reliable matching point pairs are then selected via random sample consensus. Finally, the 3D transformation is solved by singular value decomposition. For verification, experiments are conducted with real-world data. In the registration experiment on noisy and partial data, the root-mean-square error of the proposed method is 0.35% and 1.18% of SAC-IA and SAC-IA + ICP, respectively. The proposed method is useful for the extraction, monitoring, and analysis of plant phenotypes.

The impact of selection of reference samples and DEM on the accuracy of land cover classification based on Sentinel-2 data

Up-to-date and reliable information on land cover and land use status is important in many aspects of human activities. Knowledge about the reference dataset, its coverage, nomenclature, thematic and geometric accuracy, spatial resolution is crucial for appropriate selection of reference samples used in the classification process. In this study, we examined the impact of the selection and pre-processing of reference samples for the classification accuracy. The classification based on Random Forest algorithm was performed using firstly the automatically selected reference samples derived directly from the national databases, and secondly using the pre-processed and verified reference samples. The verification procedures involved the iterative analysis of histogram of spectral features derived from the Sentinel-2 data for individual land cover classes. The verification of the reference samples improved the accuracy of delineation of all land cover classes. The highest improvement was achieved for the woodland broadleaved and non- and sparce vegetation classes, with the overall accuracy increasing from 51% to 73%, and from 33% to 74%, respectively. The second objective of this study was to derive the best possible land cover classification over the mountain area in Norway, therefore we examined whether the use of the Digital Elevation Model (DEM) can improve the classification results. Classifications were carried out based on Sentinel-2 data and a combination of Sentinel-2 and DEM. Using the DEM the accuracy for nine out of ten land cover classes was improved. The highest improvement was achieved for classes located at higher altitudes: low vegetation and non- and sparse vegetation.

A Stereo-Vision-Based Spatial-Positioning and Postural-Estimation Method for Miniature Circuit Breaker Components

This paper proposes a stereo-vision-based method that detects and registers the positions and postures of muti-type, randomly placed miniature circuit breaker (MCB) components within scene point clouds acquired by a 3D stereo camera. The method is designed to be utilized in the flexible assembly of MCBs to improve the precision of gripping small-sized and complex-structured components. The proposed method contains the following stages: First, the 3D computer-aided design (CAD) models of the components are converted to surface point cloud models by voxel down-sampling to form matching templates. Second, the scene point cloud is filtered, clustered, and segmented to obtain candidate-matching regions. Third, point cloud features are extracted by Intrinsic Shape Signatures (ISSs) from the templates and the candidate-matching regions and described by Fast Point Feature Histogram (FPFH). We apply Sample Consensus Initial Alignment (SAC-IA) to the extracted features to obtain a rough matching. Fourth, fine registration is performed by employing Iterative Closest Points (ICPs) with a K-dimensional Tree (KD-tree) between the templates and the roughly matched targets. Meanwhile, Random Sample Consensus (RANSAC), which effectively solves the local optimal problem in the classic ICP algorithm, is employed to remove the incorrectly matching point pairs for further precision improvement. The experimental results show that the proposed method achieves spatial positioning errors smaller than 0.2 mm and postural estimation errors smaller than 0.5°. The precision and efficiency meet the requirements of the robotic flexible assembly for MCBs.

Occluded Face Recognition Using Machine Learning

A fascinating and intense issue nowadays is the difficult problem of identifying human faces when they are obscured by various obstructions. Due to a sizable occluded zone and a dearth of un-occluded portions, the capacity of most identification algorithms goes off dramatically. We describe a pre-processing approach for occluded faces that is effective and features-based to the fullest extent. Pose, lighting, age, emotions, and hair covering the face are among the 40 different occlusions that are included in the dataset. Edge-preserving enhancement and contrast measurement-correction for the occluded face pictures are part of the two simultaneous procedures used in the pre-processing step. Utilizing Gabor coefficients, Linear Binary Patterns based on Haar Wavelet components, and Histogram of Gaussian features, the finest textural characteristics are retrieved. The other set of characteristics used to represent the entire occluded face region is composed of wavelet components, color histograms, and statistical global features based on first order. In order to validate utilizing support vector machines, the study takes into account 100 celebrities from the CelebA dataset with posture and other occlusions. Compared to other well- known systems, the suggested efficient pre-processing and optimal features-based face recognition system exhibited increased classification accuracy in experiment analysis.

A real-time e-commerce accessories recommender system by coupling deep learning and histogram features

Online shopping is a form of electronic commerce that enables customers to purchase products directly from the seller over the internet using a web browser or a mobile application. With the growing number of research papers on Deep Learning (DL)-based recommendations, DL models have proven to be effective in Recommender systems. Hence in this paper, relevant product accessories recommendation is proposed using deep learning and histogram features. The proposed recommendation describes the novel way of content-based filtering which divides the work into two phases. In phase 1, the implemented approach determines the color and category of the product. In phase 2, the recommendation system retrieves the matching accessories for the chosen product. For phase 1, Decision Tree, Linear Regression, Logistic Regression, Naïve Bayes, Long Short-Term Memory (LSTM), and a novel method of Stack dense Recurrent Neural Network (RNN) along with the color histogram is applied to identify the category and color of the product. It is justified that the proposed technique of stack dense RNN achieves 98% accuracy. In phase 2, from the Machine Learning (ML) perspective, Random Forest (RF) is employed for the recommendation. The RF model finds the matching accessories for the chosen product and retrieves the top relevant items.

Integration of Deep Direction Distribution Feature Extraction and Optimized Attention Based Double Hidden Layer GRNN Models for Robust Cursive Handwriting Recognition

Cursive handwriting recognition (CHWR) is an interesting area of research as it has a wide range of applications but lacks an accurate approach to provide better results due to its character shapes, the non-uniform spacing between words and within a word, diverse placements of dots, and diacritics, and very low inter-class variation among individual classes. A novel CHWR model is proposed to enhance the recognition accuracy with high global stability. The proposed model introduces three major phases: pre-processing, feature extraction and classification. In the pre-processing stage, the noise removal and binarization are adapted with the intrusion of improved adaptive wiener filtering (IAWF) and structural symmetric pixels. A hybrid deep direction distribution feature extraction (HDDDFE) approach is proposed to extract directional Local gradient histogram (LGH), column gradient histogram (CGH) features and a wavelet convolutional neural network with Block Attention Module (WCNN-BAM) is proposed to extract deep global features (GF), profile features (PF) and dynamic features (DF). A novel double hidden layer gated recurrent neural network with a feature attention mechanism (ODHL-GRNN-FAM) is proposed to offer handwritten classification results. The developed model is evaluated with the IAM database and attains an overall recognition accuracy of 98%, precision of 97%, f-measure of 97.99%, character error rate (CER) of 1.23%, word error rate (WER) of 4.8%, respectively.