Image Preprocessing Steps Research Articles

Crop Leaf Type Classification and Multi-Class Leaf Disease Identification with Tangent Hunter Prey Optimization-Based LeNet

The early detection and accurate rate of classification of plant leaf disease are more important for reliable and good agriculture, which prevents unwanted financial loss and resources. In this study, Tangent Hunter Prey Optimization-based LeNet (THPO-LeNet) is utilized for crop leaf classification and multi-class plant leaf disease identification. In this case, the input image that goes through the image pre-processing step is obtained from the plant village dataset. An adaptive Wiener filter is applied at the pre-processing stage to reduce needless mistakes and improve image quality. The pre-processed image is then sent to the leaf segmentation step, where a Mask Region-based Convolution Neural Network (Mask R-CNN) performs the segmentation. Consequently, image augmentation is performed using techniques such as scaling, rotation, translation, flipping, contrast, saturation, and hue. Afterwards, first-level classification plant leaf classification is processed by LeNet, which is optimized by Tangent Hunter Prey Optimization (THPO). The THPO is the incorporation of a Tangent Search Algorithm (TSA) and Hunter–Prey Optimizer (HPO). At last, the second-level classification of plant leaf disease is conducted by THPO-LeNet. Furthermore, the efficiency of THPO-LeNet is examined based on measures, like accuracy, Negative Predictive Value (NPV), True Positive Rate (TPR), True Negative Rate (TNR), Positive Predictive Value (PPV), loss value, and False Positive Rate (FPR), and the value attained is 95.68%, 92.50%, 91.48%, 92.25%, 92.54%, 8.321%, and 7.754%, respectively.

Simulation of body trajectory detection in sports training based on infrared thermal imaging image features

The traditional motion trajectory detection methods are limited by illumination conditions and occlusion, and it is difficult to capture the athlete’s motion path accurately and in real time. The aim of this study is to improve the accuracy and real-time performance of motion trajectory detection, and to provide more effective auxiliary means for athletes’ training and competition. The image feature analysis method based on Infrared Thermal Imaging, combined with computer vision and machine learning technology, is used to monitor and analyze the motion scene. Infrared Thermal Imaging equipment is used to collect data of motion scenes and obtain infrared image sequence. Then, through the steps of image preprocessing, feature extraction and target recognition, the position and motion trajectory of athletes at different time points are obtained. The experimental results show that the image feature analysis method based on Infrared Thermal Imaging can effectively capture the athlete’s motion trajectory, and has higher accuracy and real-time performance. The method has better adaptability and robustness in complex environments such as lighting conditions and occlusion.

465 Comparative analysis of semantic segmentation and deep regression models with supervised pre-training for accurate prediction of pig body weight from video data: Insights from industry-scale datasets

Abstract Accurate pig body weight (BW) measurement is essential for producers as it is related to pig growth, health, and marketing, yet conventional manual weighing methods are time-consuming and may cause potential stress to the animals. Although there is a growing trend towards the adoption of three-dimensional cameras coupled with computer vision techniques for pig BW estimation, their validation using industry-scale data are still limited. Among the prevailing methodologies, semantic segmentation and supervised pre-training regression are prominent models currently used. Therefore, the objectives of this study were: 1) to estimate pig BW from repeatedly measured video data obtained from a commercial setting, 2) to compare the performance of the two image analysis methods: thresholding segmentation and deep regression approaches, and 3) to evaluate the predictive ability of BW estimation models. An Intel RealSense D435 camera was installed in the commercial farm to collect top-view videos of 540 pigs biweekly at five different time points over three months. At the same time, manually measured BW records were collected using a digital weighing system. We used an automated video conversion pipeline and fine-tuned YOLOv8 to pre-process the raw depth videos. Subsequently, we acquired a total of 151,756 depth images and depth map files. Adaptive thresholding was applied to segment the pig body from the background. Four image-derived biometric features, including dorsal length, abdominal width, height, and volume, were estimated from the segmented images and fitted using ordinary least squares and random forest models. We applied transfer learning by initializing the weights of five deep learning models, including ResNet50, Xception, EfficientNetV2S, ConvNeXtBase, and Vision Transformer, with pre-trained weights from ImageNet. We then fine-tuned these models on the pig depth images. The last layer of each model was adapted to linear regression, enabling direct estimation of BW for each image without the need for additional image pre-processing steps. We employed random repeated subsampling cross-validation, dividing 80% of the pigs for training and 20% for testing, to evaluate prediction performance at each time point. The best prediction coefficients of determination and mean absolute percentage error for each time point were 0.76, 0.86, 0.90, 0.83, 0.90, and 4.57%, 3.76%, 3.01%, 3.41%, 4.84%, respectively. On average, the Xception model resulted in the best prediction coefficient of determination and mean absolute percentage error of 0.90 and 3.01%. Our results suggest that deep learning-based supervised learning models improve the prediction performance of pig BW from industry-scale depth video data.

Aflatoxin contamination level estimation in food using reflectance multispectral imaging based system

This study presents a non-invasive, non-destructive, and rapid method of classifying and estimating aflatoxin levels in food samples using a multispectral imaging. A cost effective, mass deployable in-house built multispectral imaging system, suitable for onsite testing and operating in range from 365 nm to 940 nm, is utilized to capture the multispectral images of the aflatoxin contaminated bread samples. Spatial and spectral corrections are performed to mitigate the imperfections of the multispectral imaging system, followed by image preprocessing steps to mitigate the effect of random noise. Linear discriminant analysis is used to reduce the dimensionality of the feature space. Ensemble classification analysis utilizing classical machine learning classifiers yielded an accuracy of 90 % when classifying samples according to aflatoxin contamination levels. A functional relationship between the Bhattacharyya distance of noncontaminated samples to contaminated samples and aflatoxin contamination levels was modeled as a first order polynomial with an R2 value of 0.9723.

Impact of SUSAN Denoising and ComBat Harmonization on Machine Learning Model Performance for Malignant Brain Neoplasms.

Feature variability in radiomics studies due to technical and magnet strength parameters is well-known and may be addressed through various preprocessing methods. However, very few studies have evaluated the downstream impact of variable preprocessing on model classification performance in a multiclass setting. We sought to evaluate the impact of Smallest Univalue Segment Assimilating Nucleus (SUSAN) denoising and Combining Batches harmonization on model classification performance. A total of 493 cases (410 internal and 83 external data sets) of glioblastoma, intracranial metastatic disease, and primary CNS lymphoma underwent semiautomated 3D-segmentation post-baseline image processing (BIP) consisting of resampling, realignment, coregistration, skull-stripping, and image normalization. Post-BIP, 2 sets were generated, one with and another without SUSAN denoising. Radiomics features were extracted from both data sets and batch-corrected to produce 4 data sets: (a) BIP, (b) BIP with SUSAN denoising, (c) BIP with Combining Batches, and (d) BIP with both SUSAN denoising and Combining Batches harmonization. Performance was then summarized for models using a combination of 6 feature-selection techniques and 6 machine learning models across 4 mask-sequence combinations with features derived from 1 to 3 (multiparametric) MRI sequences. Most top-performing models on the external test set used BIP+SUSAN denoising-derived features. Overall, the use of SUSAN denoising and Combining Batches harmonization led to a slight but generally consistent improvement in model performance on the external test set. The use of image-preprocessing steps such as SUSAN denoising and Combining Batches harmonization may be more useful in a multi-institutional setting to improve model generalizability. Models derived from only T1 contrast-enhanced images showed comparable performance to models derived from multiparametric MRI.

A Deep Ensemble Dynamic Learning Network for Corona Virus Disease 2019 Diagnosis.

Corona virus disease 2019 is an extremely fatal pandemic around the world. Intelligently recognizing X-ray chest radiography images for automatically identifying corona virus disease 2019 from other types of pneumonia and normal cases provides clinicians with tremendous conveniences in diagnosis process. In this article, a deep ensemble dynamic learning network is proposed. After a chain of image preprocessing steps and the division of image dataset, convolution blocks and the final average pooling layer are pretrained as a feature extractor. For classifying the extracted feature samples, two-stage bagging dynamic learning network is trained based on neural dynamic learning and bagging algorithms, which diagnoses the presence and types of pneumonia successively. Experimental results manifest that using the proposed deep ensemble dynamic learning network obtains 98.7179% diagnosis accuracy, which indicates more excellent diagnosis effect than existing state-of-the-art models on the open image dataset. Such accurate diagnosis effects provide convincing evidences for further detections and treatments.

An Efficient and Effective Image Decolorization Algorithm Based on Cumulative Distribution Function.

Image decolorization is an image pre-processing step which is widely used in image analysis, computer vision, and printing applications. The most commonly used methods give each color channel (e.g., the R component in RGB format, or the Y component of an image in CIE-XYZ format) a constant weight without considering image content. This approach is simple and fast, but it may cause significant information loss when images contain too many isoluminant colors. In this paper, we propose a new method which is not only efficient, but also can preserve a higher level of image contrast and detail than the traditional methods. It uses the information from the cumulative distribution function (CDF) of the information in each color channel to compute a weight for each pixel in each color channel. Then, these weights are used to combine the three color channels (red, green, and blue) to obtain the final grayscale value. The algorithm works in RGB color space directly without any color conversion. In order to evaluate the proposed algorithm objectively, two new metrics are also developed. Experimental results show that the proposed algorithm can run as efficiently as the traditional methods and obtain the best overall performance across four different metrics.

A Novel, Deep Learning-Based, Automatic Photometric Analysis Software for Breast Aesthetic Scoring.

Background Breast aesthetics evaluation often relies on subjective assessments, leading to the need for objective, automated tools. We developed the Seoul Breast Esthetic Scoring Tool (S-BEST), a photometric analysis software that utilizes a DenseNet-264 deep learning model to automatically evaluate breast landmarks and asymmetry indices. Methods S-BEST was trained on a dataset of frontal breast photographs annotated with 30 specific landmarks, divided into an 80-20 training-validation split. The software requires the distances of sternal notch to nipple or nipple-to-nipple as input and performs image preprocessing steps, including ratio correction and 8-bit normalization. Breast asymmetry indices and centimeter-based measurements are provided as the output. The accuracy of S-BEST was validated using a paired t -test and Bland-Altman plots, comparing its measurements to those obtained from physical examinations of 100 females diagnosed with breast cancer. Results S-BEST demonstrated high accuracy in automatic landmark localization, with most distances showing no statistically significant difference compared with physical measurements. However, the nipple to inframammary fold distance showed a significant bias, with a coefficient of determination ranging from 0.3787 to 0.4234 for the left and right sides, respectively. Conclusion S-BEST provides a fast, reliable, and automated approach for breast aesthetic evaluation based on 2D frontal photographs. While limited by its inability to capture volumetric attributes or multiple viewpoints, it serves as an accessible tool for both clinical and research applications.

Visual Attention and ODE-inspired Fusion Network for image dehazing

Image dehazing is an improtant image pre-processing step for many computer vision tasks with many proposed methods using convolutional neural networks. Ordinary Differential Equations (ODE) are a powerful mathematical tool in social and natural science, leading to better understanding, prediction, and use of information systems. Because prior knowledge has demonstrated its effectiveness in many practical domains, we design a Visual Attention Network (VAN) and an ODE-inspired Network (ODEN) based on prior knowledge. Then, we develop a multi-model fuzzy fusion strategy, which integrates results predicted by the prior-based Visual Attention Network (VAN) and the ODE-inspired Network (ODEN) into a single network to leverage their respective strengths in improving the dehazing performance. First, to utilize the haze-related prior for dehazing, the VAN removes haze with the help of the haze attention map. Then, to improve performance of stacked residual blocks inspired by the first-order Euler method in ODE-based methods, the ODEN is built by only 3 Runge–Kutta Modules (RKM), each of which not only is related to the stable fourth-order Runge–Kutta method implemented in the Runge–Kutta Block (RKB), but also combines the RKB with an attention mechanism. Finally, an attention based fusion mechanism is used to fuse results estimated by the ODEN and the VAN based on the multi-level features extracted by a pretrained ResNeXt. The experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods in terms of visual effects and accuracy. The average PSNR and SSIM on three public datasets are 31.36 and 0.9766, respectively, which are better than the compared state-of-the-art methods.

Remote sensing and GIS-based study of land use/cover dynamics, driving factors, and implications in southern Ethiopia, with special reference to the Legabora watershed

This paper investigates the trends, drivers, and consequences of LULC changes in Legabora watershed, Ethiopia, by utilizing remote sensing and geographic systems. Landsat Maltispectiral scanner (MSS), Thematic Mapper (TM), Enhanced Thematic Mapper (ETM+), and Operational Land Imager (OLI) images of years 1976, 1991, 2001, and 2022, respectively, were used to study the dynamics of LULC. Essential image pre-processing steps were carefully carried out to correct distortions caused by sensor limitations. Eight main LULC categories were identified based on supervised image categorization methods and the maximum likelihood classification algorithm.The findings of change detection and cross-tabulation matrix demonstrate that there has been a significant increase in the area of cropland 345.1 ha/year, settlement 5.9 ha/year, forest 38.2 ha/year, and degraded lands 2.56 ha/year, respectively, over the period between 1976 and 2022. In contrast, considerable decreases were observed in grasslands (−248 ha/year) and shrublands (−144 ha/year), whereas other LULC categories augmented. The results revealed that the overall accuracy rates stood at 88.3 %, 88.4 %, and 85.6 % for 1976, 1991, and 2022, respectively. The overall kappa coefficient demonstrated values of 0.86 %, 0.86 %, and 0.83 % for the same period. Surveyed respondents perceived population growth, settlement, agricultural expansion, and infrastructure development as the most noticeable drivers of these LULC changes. In contrast, deforestation, land degradation, lack of livestock fodder, and biodiversity loss were identified as the main consequences of LULC changes. The factors and implications addressed in this study may be helpful tool for the formulation and implementation of evidence-based land use policies and strategies within in the study area and elsewhere.

A New Approach for Feeding Multispectral Imagery into Convolutional Neural Networks Improved Classification of Seedlings

Tree species information is important for forest management, especially in seedling stands. To mitigate the spectral admixture of understory reflectance with small and lesser foliaged seedling canopies, we proposed an image pre-processing step based on the canopy threshold (Cth) applied on drone-based multispectral images prior to feeding classifiers. This study focused on (1) improving the classification of seedlings by applying the introduced technique; (2) comparing the classification accuracies of the convolutional neural network (CNN) and random forest (RF) methods; and (3) improving classification accuracy by fusing vegetation indices to multispectral data. A classification of 5417 field-located seedlings from 75 sample plots showed that applying the Cth technique improved the overall accuracy (OA) of species classification from 75.7% to 78.5% on the Cth-affected subset of the test dataset in CNN method (1). The OA was more accurate in CNN (79.9%) compared to RF (68.3%) (2). Moreover, fusing vegetation indices with multispectral data improved the OA from 75.1% to 79.3% in CNN (3). Further analysis revealed that shorter seedlings and tensors with a higher proportion of Cth-affected pixels have negative impacts on the OA in seedling forests. Based on the obtained results, the proposed method could be used to improve species classification of single-tree detected seedlings in operational forest inventory.

Image based prognosis in head and neck cancer using convolutional neural networks: a case study in reproducibility and optimization

In the past decade, there has been a sharp increase in publications describing applications of convolutional neural networks (CNNs) in medical image analysis. However, recent reviews have warned of the lack of reproducibility of most such studies, which has impeded closer examination of the models and, in turn, their implementation in healthcare. On the other hand, the performance of these models is highly dependent on decisions on architecture and image pre-processing. In this work, we assess the reproducibility of three studies that use CNNs for head and neck cancer outcome prediction by attempting to reproduce the published results. In addition, we propose a new network structure and assess the impact of image pre-processing and model selection criteria on performance. We used two publicly available datasets: one with 298 patients for training and validation and another with 137 patients from a different institute for testing. All three studies failed to report elements required to reproduce their results thoroughly, mainly the image pre-processing steps and the random seed. Our model either outperforms or achieves similar performance to the existing models with considerably fewer parameters. We also observed that the pre-processing efforts significantly impact the model’s performance and that some model selection criteria may lead to suboptimal models. Although there have been improvements in the reproducibility of deep learning models, our work suggests that wider implementation of reporting standards is required to avoid a reproducibility crisis.

An artificial intelligence tool for automated analysis of large-scale unstructured clinical cine cardiac magnetic resonance databases.

Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR analysis tool exists to automatically analyse large (unstructured) clinical CMR datasets. We develop and validate a robust AI tool for start-to-end automatic quantification of cardiac function from SAX cine CMR in large clinical databases. Our pipeline for processing and analysing CMR databases includes automated steps to identify the correct data, robust image pre-processing, an AI algorithm for biventricular segmentation of SAX CMR and estimation of functional biomarkers, and automated post-analysis quality control to detect and correct errors. The segmentation algorithm was trained on 2793 CMR scans from two NHS hospitals and validated on additional cases from this dataset (n = 414) and five external datasets (n = 6888), including scans of patients with a range of diseases acquired at 12 different centres using CMR scanners from all major vendors. Median absolute errors in cardiac biomarkers were within the range of inter-observer variability: <8.4 mL (left ventricle volume), <9.2 mL (right ventricle volume), <13.3 g (left ventricular mass), and <5.9% (ejection fraction) across all datasets. Stratification of cases according to phenotypes of cardiac disease and scanner vendors showed good performance across all groups. We show that our proposed tool, which combines image pre-processing steps, a domain-generalizable AI algorithm trained on a large-scale multi-domain CMR dataset and quality control steps, allows robust analysis of (clinical or research) databases from multiple centres, vendors, and cardiac diseases. This enables translation of our tool for use in fully automated processing of large multi-centre databases.

TrackSafe: A comparative study of data-driven techniques for automated railway track fault detection using image datasets

Railway track accidents continue to occur despite manual inspections, which are often inaccurate and can lead to catastrophic events. While artificial intelligence has been applied in the railway sector, few studies have focused on defect detection using object detection tools. Additionally, there is a lack of studies that compare different models using the same dataset.This paper proposes new data-driven techniques that identify railway track faults using three object detection models: YOLOv5, Faster RCNN, and EfficientDet. These models are compared by testing a dataset of 31 images that contain three different railway track elements (clip, rail, and fishplate), both faulty and non-faulty. Six classes were differentiated in the training of the models: one faulty and one non-faulty for each of the three classes. Image pre-processing steps included data augmentation techniques and image resizing. Results show good precision (equivalent to 1) in detecting non-defective elements, but recall values for defective elements vary among models, with Faster RCNN performing the best (0.93), followed by EfficientDet (0.81), and YOLOv5 (0.68). The full paper discusses the strengths and weaknesses of these proposed techniques for railway fault detection.

Gastrointestinal abnormality detection and classification using empirical wavelet transform and deep convolutional neural network from endoscopic images

With an intention to assist gastroenterologists, this work proposes an intelligent method to classify alimentary canal diseases such as Barrett’s, Esophagitis, Hemorrhoids, Polyps, and Ulcerative colitis by using empirical wavelet transform (EWT) and convolutional neural network (CNN). Here, a publicly available HyperKvasir dataset is used for the experimental work. The framework starts with several image pre-processing steps followed by the implementation of EWT. EWT helps to decompose the image into several modes and extract specific patterns in the images. These decomposed images are then fed into the proposed deep CNN for disease classification in two-levels. Finally, the proposed model is evaluated based on several performance metrics. The result shows 96.65% accuracy, 0.9298 Matthews correlation coefficient (MCC) in the first level, and 94.25% accuracy, 0.8108 MCC in the second level of classification. Lastly, to justify the efficacy of the proposed method, a comparative study is carried out with other contemporary techniques.

A Novel Bacterial Foraging Optimization Based Multimodal Medical Image Fusion Approach

Multimodal medical image fusion (MIF) is the procedure of integrating different images in single into multiple imaging modalities for increasing the image quality by preserving a certain feature. Medical image combination covered a tremendous count of hot topic areas, involving pattern recognition, image processing, artificial intelligence (AI), computer vision (CV), and machine learning (ML). In addition, MIF was more commonly applied in clinical for physicians to understand the lesion by the combination of various modalities of medicinal image. This article introduces a novel bacterial foraging optimization-based multimodal medical image fusion approach (BFO-M3IFA). The presented BFO-M3IFA technique considered two distinct patterns of the images as the input of systems and the outcome will be the fused image. Primarily, the BFO-M3IFA technique exploits Weiner filtering (WF) technique as an image pre-processing step to get rid of the noise. Besides, discrete wavelet transform (DWT) was applied for decomposing the image into distinct subbands. Afterward, the estimated coefficients of modality 1 and comprehensive coefficients of modality 2 are integrated and vice versa. At last, a fusion rule is generated to fuse the details of two image modalities and the optimal fusion rule parameter is chosen with utilize of BFO algorithm. The experimental validation of the BFO-M3IFA system was tested and outcomes ensured the improved performance of the BFO-M3IFA system on existing models.

A dataset of rodent cerebrovasculature from in vivo multiphoton fluorescence microscopy imaging

We present MiniVess, the first annotated dataset of rodent cerebrovasculature, acquired using two-photon fluorescence microscopy. MiniVess consists of 70 3D image volumes with segmented ground truths. Segmentations were created using traditional image processing operations, a U-Net, and manual proofreading. Code for image preprocessing steps and the U-Net are provided. Supervised machine learning methods have been widely used for automated image processing of biomedical images. While much emphasis has been placed on the development of new network architectures and loss functions, there has been an increased emphasis on the need for publicly available annotated, or segmented, datasets. Annotated datasets are necessary during model training and validation. In particular, datasets that are collected from different labs are necessary to test the generalizability of models. We hope this dataset will be helpful in testing the reliability of machine learning tools for analyzing biomedical images.

The Weight of Hyperion and PRISMA Hyperspectral Sensor Characteristics on Image Capability to Retrieve Urban Surface Materials in the City of Venice.

Following the success of the first hyperspectral sensor, the evaluation of hyperspectral image capability became a challenge in research, which mainly focused on improving image pre-processing and processing steps to minimize their errors, whereas in this study, the focus was on the weight of hyperspectral sensor characteristics on image capability in order to distinguish this effect from errors caused by image pre-processing and processing steps and improve our knowledge of errors. For these purposes, two satellite hyperspectral sensors with similar spatial and spectral characteristics (Hyperion and PRISMA) were compared with corresponding synthetic images, and the city of Venice was selected as the study area. After creating the synthetic images, the errors in the simulation of Hyperion and PRISMA images were evaluated (1.6 and 1.1%, respectively). The same spectral unmixing procedure was performed using real and synthetic images, and their accuracies were compared. The spectral accuracies in root mean square error were equal to 0.017 and 0.016, respectively. In addition, 72.3 and 77.4% of these values were related to sensor characteristics. The spatial accuracies in the mean absolute error were equal to 3.93 and 3.68, respectively. A total of 55.6 and 59.0% of these values were related to sensor characteristics, and 22.6 and 22.3% were related to co-localization and spatial resampling errors. The difference between the radiometric precision values of the sensors was 6.81 and 5.91% regarding the spectral and spatial accuracies of Hyperion image. In conclusion, the results of this study showed that the combined use of two or more real hyperspectral images with similar characteristics and their synthetic images quantifies the weight of hyperspectral sensor characteristics on their image capability and improves our knowledge regarding processing errors, and thus image capability.

Automated Colonic Polyp Detection and Classification Enabled Northern Goshawk Optimization with Deep Learning

The major mortality factor relevant to the intestinal tract is the growth of tumorous cells (polyps) in various parts. More specifically, colonic polyps have a high rate and are recognized as a precursor of colon cancer growth. Endoscopy is the conventional technique for detecting colon polyps, and considerable research has proved that automated diagnosis of image regions that might have polyps within the colon might be used to help experts for decreasing the polyp miss rate. The automated diagnosis of polyps in a computer-aided diagnosis (CAD) method is implemented using statistical analysis. Nowadays, Deep Learning, particularly through Convolution Neural networks (CNN), is broadly employed to allow the extraction of representative features. This manuscript devises a new Northern Goshawk Optimization with Transfer Learning Model for Colonic Polyp Detection and Classification (NGOTL-CPDC) model. The NGOTL-CPDC technique aims to investigate endoscopic images for automated colonic polyp detection. To accomplish this, the NGOTL-CPDC technique comprises of adaptive bilateral filtering (ABF) technique as a noise removal process and image pre-processing step. Besides, the NGOTL-CPDC model applies the Faster SqueezeNet model for feature extraction purposes in which the hyperparameter tuning process is performed using the NGO optimizer. Finally, the fuzzy Hopfield neural network (FHNN) method can be employed for colonic poly detection and classification. A widespread simulation analysis is carried out to ensure the improved outcomes of the NGOTL-CPDC model. The comparison study demonstrates the enhancements of the NGOTL-CPDC model on the colonic polyp classification process on medical test images.

Track Line Recognition Based on Morphological Thinning Algorithm

In the field of intelligent driving of freight trains, determining the track line ahead of the train is an important function in the autopilot technology of such trains. Combining the characteristics of freight railway tracks, we conduct an in-depth analysis of the shortcomings of object detection technology in extracting track lines and propose an improved Zhang–Suen (ZS) thinning theory for a railway track line recognition algorithm. Through image preprocessing and single pixel thinning steps, a continuous track line is obtained and then processed by a denoising algorithm to obtain a complete track line. Experimental results show that the track extracted by our method has good continuity and less noise. It can simultaneously perform track detection on straight roads, curves and turnouts, and is suitable for changing weather conditions such as sunny daytime, mild rainy daytime, cloudy daytime, night with lamp lighting and night without lamp lighting conditions.