Texture Patterns Research Articles

Sublimation of Technology: The Impact of Artificial Intelligence on Esthetics and Artistic Expression

In the creative sector, artificial intelligence (AI) has proven to be a crucial instrument. AI encompasses a variety of artistic creations that were previously thought to be exclusive to human talent, such as paintings and music. The study improves on earlier research showing that artificial creativity processes may produce goods that are competitive with those generated by humans, satisfy customer expectations, and provide enjoyment. This study investigates the impact of AI on esthetics and artistic expression. Directing the machine to paint a landscape, create a pen and ink portrait of a person, or create a gouache before still life, etc. The synthesis of realistic paintings requires more effort than just accurately capturing target styles. It also requires maintaining original content aspects and visual structures, for which the existing techniques are insufficient to provide satisfying creation of art. In this study, a novel redefined generative adversarial network (RGAN) was proposed for automatic art creation and generation of paintings. In this study, a diverse set of art image data for artistic creation were collected. The data were preprocessed using a median filter to remove noise from the obtained data. Histogram of Oriented Gradients (HOG) approaches are used to extract features, which extract gradient orientation to capture texture patterns and edge information. The results demonstrate that the proposed technique achieved better performance than the other existing techniques. The innovative AI model improves the system’s ability to capture style and preserve content, resulting in better art creation outcomes.

Enhanced Semantic Natural Scenery Retrieval System Through Novel Dominant Colour and Multi‐Resolution Texture Feature Learning Model

ABSTRACTA conventional content‐based image retrieval system (CBIR) extracts image features from every pixel of the images, and its depiction of the feature is entirely different from human perception. Additionally, it takes a significant amount of time for retrieval. An optimal combination of appropriate image features is necessary to bridge the semantic gap between user queries and retrieval responses. Furthermore, users should require minimal interactions with the CBIR system to obtain accurate responses. Therefore, the proposed work focuses on extracting highly relevant feature information from a set of images in various natural image databases. Subsequently, a feature‐based learning/classification model is introduced before similarity measure calculations, aiming to minimise retrieval time and the number of comparisons. The proposed work analyses the learning models based on the retrieval system's performance separately for the following features: (i) dominant colour, (ii) multi‐resolution radial difference texture patterns, and a combination of both. The developed work is assessed with other techniques, and the results are reported. The results demonstrate that the implemented ensemble learning model‐based CBIR outperforms the recent CBIR techniques.

Revealing the Dark Side of Non-Local Attention in Single Image Super-Resolution.

Single Image Super-Resolution (SISR) aims to reconstruct a high-resolution image from its corresponding low-resolution input. A common technique to enhance the reconstruction quality is Non-Local Attention (NLA), which leverages self-similar texture patterns in images. However, we have made a novel finding that challenges the prevailing wisdom. Our research reveals that NLA can be detrimental to SISR and even produce severely distorted textures. For example, when dealing with severely degrade textures, NLA may generate unrealistic results due to the inconsistency of non-local texture patterns. This problem is overlooked by existing works, which only measure the average reconstruction quality of the whole image, without considering the potential risks of using NLA. To address this issue, we propose a new perspective for evaluating the reconstruction quality of NLA, by focusing on the sub-pixel level that matches the pixel-wise fusion manner of NLA. From this perspective, we provide the approximate reconstruction performance upper bound of NLA, which guides us to design a concise yet effective Texture-Fidelity Strategy (TFS) to mitigate the degradation caused by NLA. Moreover, the proposed TFS can be conveniently integrated into existing NLA-based SISR models as a general building block. Based on the TFS, we develop a Deep Texture-Fidelity Network (DTFN), which achieves state-of-the-art performance for SISR. Our code and a pre-trained DTFN are available on GitHub† for verification.

Intelligent characterization and robustness quantification of frozen soil strength images using a multi-module fusion strategy

In frozen wall engineering, traditional detection methods are difficult to implement for real-time monitoring of strength parameters, due to their intermittent nature. This makes it difficult to provide timely warnings and effective responses to potential risks of frozen walls, highlighting the urgent need for a method that can continuously and accurately monitor the strength of frozen walls. An image data-driven intelligent identification method for frozen soil strength based on convolutional neural networks is proposed. By capturing images of cured samples from multiple angles and conducting uniaxial compressive strength tests, the collected strength data were divided into 12 categories, creating an image dataset for deep learning model training. A Resnet-34 deep learning model combined with global attention and downsampling showed excellent performance in comparison with a series of basic models, with an accuracy of 93.3 % and no overfitting. The accuracy of the deep learning model was assessed using adversarial attack and defense strategies, serving as an indicator of robustness. The improved model exhibited better robustness in comparative analyses. Using SHapley Additive exPlanations (SHAP) value analysis, the feature extraction process of the convolutional neural network in recognizing frozen soil strength was investigated and clarified, confirming the model's ability to identify and extract key features in frozen soil images, such as particle size, texture, cracks, and ice crystal distribution patterns. This technology offers a cutting-edge method for real-time tracking of frozen wall conditions and early disaster warnings, significantly enhancing the safety and success rate of construction projects under freezing conditions.

Nail Disorders as clues to systemic disease.

Disorders of the nail unit can provide important clues to underlying systemic diseases. Onychodystrophy or nail abnormalities include altered nail color, shape, or texture, with morphology and growth patterns often related to local anatomic factors such as edema, vascular supply, and neurologic innervation. Associated pain or loss of function can also affect daily activities. Because nail changes may be due to a range of systemic diseases, we chose to provide a systems-based broad overview of the common nail findings in patients with internal disease.

Three-dimensional displacement measurement based on DIC-assisted polarization fringe projection

Digital image correlation (DIC)-assisted fringe projection profilometry (FPP) is a recently developed method for measuring the shape and displacement of complex structures. However, FPP only requires the fringe pattern on the object surface while DIC only requires the texture pattern on the object surface. Therefore, separating high-quality fringe patterns and texture patterns has always been a research difficulty. In this paper, a texture-separable polarization phase-shift coding strategy (TSPP) is proposed to superimpose the phase-shift pattern of the horizontal polarization state and the white light texture pattern of the vertical polarization state into a new phase-shift fringe. Since the polarization states in two orthogonal directions do not affect each other, the texture pattern on the surface of the object can be obtained while projecting the phase-shifted fringes. Our proposed method can separate fringe patterns and texture patterns in real time without the need for additional hardware equipment, and can cope with different lighting environments to obtain high-quality fringe and texture patterns. Experimental results show that the proposed method can obtain better three-dimensional reconstruction effects and displacement measurement results.

Computer Vision-Based Research on the Mechanism of Stick–Slip Vibration Suppression and Wear Reduction in Water-Lubricated Rubber Bearing by Surface Texture

Water-lubricated rubber bearings are a critical component of the propulsion systems in underwater vehicles. Particularly under conditions of low speed and high load, friction-induced vibration and wear often occur. Surface texturing technology has been proven to improve lubrication performance and reduce friction and wear; however, research on how different texture parameters affect friction-induced vibration and wear mechanisms remains insufficient. In this study, various texture patterns with different area ratios and aspect ratios were designed on the surface of water-lubricated rubber bearings. By combining these designs with an in situ observation system based on computer vision technology, the effects of texture parameters on bearing friction, vibration, and wear were thoroughly investigated. The experimental results show that surface textures play a critical role in improving hydrodynamic effects and stabilizing the lubrication film at the friction interface. Specifically, textures with a high area ratio (15%) and aspect ratio (3:1) exhibited the best vibration suppression effect, primarily due to the reduction in actual contact area. However, excessively high area ratios may lead to increased surface wear. This study concludes that a reasonable selection of texture area and aspect ratios can significantly reduce frictional force fluctuations and vibration amplitude, minimize surface wear, and extend bearing life.

Optimum selection of nature-inspired texture pattern for cutting tool surface using an integrated multi-criteria decision-making approach: a comparative analysis

Purpose This paper aims to focus on the selection of an appropriate nature-inspired texture pattern for cutting tool tribological surface. The selection process uses the recognized skin textures of different snakes scrolling on highly rough and projected surface conditions to analyze suitability of texture based on the texture geometry and machining conditions. The work also aims to propose a texture pattern selection process to incorporate on cutting tool tribological surface. Design/methodology/approach The selection of alternative nature-inspired texture patterns based on the texture pattern geometry and machining properties leads to a multi-criteria decision-making problem. Thirteen criteria are considered for selecting an appropriate texture pattern among 14 alternatives, i.e. nature-inspired texture patterns. In the present work, an integrated analytical hierarchy process (AHP)-TOPSIS, AHP-multi-objective optimization on the basis of ratio analysis (MOORA) and AHP-Vlse Kriterijumska Optimizacija Kompromisno Resenje (VIKOR) approaches have been proposed for the selection of an appropriate nature-inspired texture pattern. AHP is used for the formulation of decision-making matrix and criteria weight calculations and ranking of alternatives is done by three methods. Spearman’s correlation compared and found positive relations between rank assigned by methods. Experimental validation is done in Lathe for selected texture effects. Findings The texture parameters C-1 (Width of texture) and C-2 (Depth of texture) are found significant, while T-2 (Blended Krait) and T-6 (Banded Racer-1) texture is found optimal to generate on cutting tool surface. Research limitations/implications Only some nature-inspired texture patterns have been recognized before the selection; an infinite number of textures are available in nature. The size of the texture pattern is difficult to identify by the selection process because each texture pattern may have different effects on tribological surfaces. Practical implications The proposed selection methodology of nature-inspired texture patterns will help identify optimal texture geometry for specific tribological applications. The nature-inspired texture patterned tool has a significant impact on the cutting force and temperature due to its tribological effect on the cutting tool surface; it decreases the power required for machining. The machining characteristics like roughness are found to decrease by using nature-inspired texture patterned tools. Social implications Various nature-inspire texture studies to generate specific effects on the tribological surfaces may be started study for the surface of aircraft, ships, bearings, etc. Small and big fabrication industries may benefit by decreasing the cost of machining using nature-inspired texture-patterned tools. Research society will pay attention to nature’s inspiration. Originality/value Novel snake-skin-inspired texture patterns are recognized and hybrid MCDM methods are proposed to select optimal texture pattern. Proposed method used single time normalization to effectively rank the alternatives. The insights gained from this research can be extrapolated to address similar challenges in selecting nature-inspired textures for various applications. Peer review The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-05-2024-0163/

Evaluating the Safety Effectiveness of Edge Line Sinusoidal Rumble Strips on Lane Departure Crashes Prevention

Lane departure crashes are among the most common crashes in the United States and Florida. Various types of rumble strips have been used to prevent or reduce lane departure incidents. The Florida Department of Transportation adopted a new sinusoidal rumble strip pattern for statewide audible and vibratory treatment implementation since recent research reveals that sinusoidal rumble strip patterns are effective in providing auditory and tactile alert to drivers in lane departure prevention and produce less external noise in comparison to other rumble strip texture patterns. However, there has not been a systematic evaluation of the safety effectiveness of sinusoidal rumble strips in the U.S. This paper focused on evaluating the safety effectiveness of edge line sinusoidal rumble strips installed in Florida in recent years through an empirical Bayes approach. Crash data at treatment sites and reference sites were collected, and a series of crash modification factors were developed based on the type of rural roads (overall rural roadways, rural two-lane roads, and rural multi-lane roads) and crash severity levels (total crashes and fatal/SI crashes only). In addition, the authors used a multinomial logit model to estimate the influence of different variables and parameters that affect lane departure crashes. The research findings quantify the safety effectiveness of edge line sinusoidal rumbles strips in preventing lane departure crashes and provide insights on countermeasure implementation to improve rural road safety.

Evolutionary design features of virtual fashion brand collections: a three-year analysis in the Metaverse era

ABSTRACT This study aimed to investigate the evolutionary design features in recent virtual fashion brand collections, analysing 314 design images from leading brands, such as Auroboros, Tribute, Republiqe, The Fabricant, and RTFKT. The analysis classified key design elements–colour, silhouette, texture, and textile patterns – into three phases: embryonic, transitional, and expansion. Findings revealed that the embryonic phase prioritises symbolising brand identities and goals as main design elements. The transitional phase marked a shift toward increased collaboration and experimental designs in response to emerging trends. In the expansion phase, collections shifted away from foundational design elements, displaying mature aesthetics and greater collaboration. These findings identify the evolutionary design features of virtual fashion in the Metaverse era and highlight insights into its consistency with contemporary fashion sensibilities. This research contributes to establishing a crucial knowledge base for research into the development of affective design systems, addressing consumer emotional requirements in virtual fashion design.

NIMG-02. DEVELOPING A RADIOMIC HIERARCHICAL GAUSSIAN PROCESS BOOSTING MODEL TO PREDICT PRIMARY TUMOR ORIGIN FROM MULTICENTRIC LONGITUDINAL MRI DATA OF BRAIN METASTASES

Abstract Focal neurologic deficits due to brain metastases might be the initial presentation in patients with cancer. Common approaches to investigate the occult primary malignancy include a whole-body PET-CT, whole-body MRI, studying tumor markers, or histopathological examination. Most of these modalities are expensive, time-consuming, invasive, and delay treatment. The field of radiomics leverages quantitative features extracted from images to improve the decision-making process in clinical practices. Although not easily understandable, these features are proxies for the tumor’s shape, contour, texture, and intensity patterns. They can help understand tumor heterogeneity, predict tumor behavior, and assess treatment response. We propose a robust radiomic workflow using longitudinal MRI data from 914 high-resolution imaging studies from 12 different centers (Ocaña-Tienda et al. (2023), Ramakrishnan et al. (2023), Wang et al. (2023)) to predict the origin of brain metastases from brain MRI scans. After using ensemble feature selection methods, we trained three fixed-effects and one mixed-effects multiclass classification model to account for longitudinal data. Fixed-effects logistic regression and support vector kernel models performed the worst (AUC 0.74 and 0.75, respectively), while the random forest performed better (AUC 0.97). The mixed-effects hierarchical Gaussian process boosting (GPBoost) model performed the best with an accuracy of 85.8%, precision of 85.4%, sensitivity of 85.8%, specificity of 95.7%, and an AUC of 0.98. In one-versus-rest classification, the GPBoost model identified the primary tumor as melanoma with the highest accuracy (96.1%) and non-small cell lung cancer with the lowest accuracy (89.0%). Developing such models holds great promise in reducing patient and institutional costs, improving time to effective treatment, and enhancing overall survival rates through personalized therapy approaches. In the future, we hope that incorporating newer patient data and refining the model to improve external validity would enable more accurate and generalizable predictions, leading to better clinical outcomes across diverse populations.

Two–Stage Detection and Localization of Inter–Frame Tampering in Surveillance Videos Using Texture and Optical Flow

Surveillance cameras provide security and protection through real-time monitoring or through the investigation of recorded videos. The authenticity of surveillance videos cannot be taken for granted, but tampering detection is challenging. Existing techniques face significant limitations, including restricted applicability, poor generalizability, and high computational complexity. This paper presents a robust detection system to meet the challenges of frame duplication (FD) and frame insertion (FI) detection in surveillance videos. The system leverages the alterations in texture patterns and optical flow between consecutive frames and works in two stages; first, suspicious tampered videos are detected using motion residual–based local binary patterns (MR–LBPs) and SVM; second, by eliminating false positives, the precise tampering location is determined using the consistency in the aggregation of optical flow and the variance in MR–LBPs. The system is extensively evaluated on a large COMSATS Structured Video Tampering Evaluation Dataset (CSVTED) comprising challenging videos with varying quality of tampering and complexity levels and cross–validated on benchmark public domain datasets. The system exhibits outstanding performance, achieving 99.5% accuracy in detecting and pinpointing tampered regions. It ensures the generalization and wide applicability of the system while maintaining computational efficiency.

AI-based Validation of Deforestation Using High-Resolution Satellite Imagery in the Brazilian Amazon

Abstract. Forests play an important role in the Earth systems for carbon sequestration and climate change mitigation, yet they have been increasingly disturbed by deforestation and forest degradation at an unprecedented pace. The Brazilian Amazon, for instance, experienced a 140% rise in deforestation from 2012 to 2020, with a record loss of 13,200 km2 between August 2020 and July 2021. Alarmingly, 87% of 2019 deforestation alerts occurred on private properties, with 61% in legally restricted areas. Existing deforestation monitoring systems, such as PRODES and the Global Forest Change dataset, use about 30m resolution satellite imagery, which is insufficient for operational validation at fine scales. The Deforestation Alert System by Imazon leverages high-resolution PlanetScope data (3-4m) but faces challenges due to fewer spectral bands and variations in reflectance values across different satellite sensors and dates. As a result, current validation is based mainly on manual inspection which is highly time-consuming. To address the challenges and automate the validation process, this work develops a system based on deep learning – known for its ability to capture complex texture patterns in high-resolution images – to inspect and confirm new deforestation sites. Specifically, the system takes inputs from potential deforestation sites suggested by coarse-resolution products and uses a pair of PlanetScope images before and after the change at each site to determine new deforestation (excluding existing deforestation). Our results demonstrate that the new system achieves robust and high-quality accuracy under various test conditions.

Geochemical Dynamics and Evolutionary Implications of Sediments at the Xingu–Amazon Rivers’ Confluence: Proxies for Mixing, Mobility and Weathering

This study investigates the geochemical characteristics and evolutionary implications of sediments at the confluence of the Xingu and Amazon Rivers. The main objective is to understand sediment mixing, mobility, and weathering processes through geochemical proxies. Samples were collected from various sections of the lower Xingu River, focusing on its interaction with the Amazon River. Analytical techniques such as X-ray diffraction (XRD), X-ray fluorescence (XRF), and inductively coupled plasma mass spectrometry (ICP-MS) were employed to analyze major and trace elements. The results reveal significant spatial variations in mineralogical and textural patterns, with sediments forming distinct groupings based on their location. The data suggest that the lower Xingu River is strongly influenced by sediment inputs from the Amazon River, particularly affecting sediment composition and chemical weathering processes. This research highlights the critical interactions between river systems and their implications for the evolution of the Amazon basin, especially regarding sediment contributions from various geological sources. Even though the Xingu River drains cratonic regions at higher elevations, the geochemistry of the bottom sediments confirms that the bedload is derived from heterogeneous sources with primarily intermediate igneous compositions and has undergone substantial recycling during river transport.

Study on the Method of Vineyard Information Extraction Based on Spectral and Texture Features of GF-6 Satellite Imagery

Accurately identifying the distribution of vineyard cultivation is of great significance for the development of the grape industry and the optimization of planting structures. Traditional remote sensing techniques for vineyard identification primarily depend on machine learning algorithms based on spectral features. However, the spectral reflectance similarities between grapevines and other orchard vegetation lead to persistent misclassification and omission errors across various machine learning algorithms. As a perennial vine plant, grapes are cultivated using trellis systems, displaying regular row spacing and distinctive strip-like texture patterns in high-resolution satellite imagery. This study selected the main oasis area of Turpan City in Xinjiang, China, as the research area. First, this study extracted both spectral and texture features based on GF-6 satellite imagery, subsequently employing the Boruta algorithm to discern the relative significance of these remote sensing features. Then, this study constructed vineyard information extraction models by integrating spectral and texture features, using machine learning algorithms including Naive Bayes (NB), Support Vector Machines (SVMs), and Random Forests (RFs). The efficacy of various machine learning algorithms and remote sensing features in extracting vineyard information was subsequently evaluated and compared. The results indicate that three spectral features and five texture features under a 7 × 7 window have significant sensitivity to vineyard recognition. These spectral features include the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and Normalized Difference Water Index (NDWI), while texture features include contrast statistics in the near-infrared band (B4_CO) and the variance statistic, contrast statistic, heterogeneity statistic, and correlation statistic derived from NDVI images (NDVI_VA, NDVI_CO, NDVI_DI, and NDVI_COR). The RF algorithm significantly outperforms both the NB and SVM models in extracting vineyard information, boasting an impressive accuracy of 93.89% and a Kappa coefficient of 0.89. This marks a 12.25% increase in accuracy and a 0.11 increment in the Kappa coefficient over the NB model, as well as an 8.02% enhancement in accuracy and a 0.06 rise in the Kappa coefficient compared to the SVM model. Moreover, the RF model, which amalgamates spectral and texture features, exhibits a notable 13.59% increase in accuracy versus the spectral-only model and a 14.92% improvement over the texture-only model. This underscores the efficacy of the RF model in harnessing the spectral and textural attributes of GF-6 imagery for the precise extraction of vineyard data, offering valuable theoretical and methodological insights for future vineyard identification and information retrieval efforts.

Optical Micro/Nanofiber Enabled Multiaxial Force Sensor for Tactile Visualization and Human-Machine Interface.

Tactile sensors with capability of multiaxial force perception play a vital role in robotics and human-machine interfaces. Flexible optical waveguide sensors have been an emerging paradigm in tactile sensing due to their high sensitivity, fast response, and antielectromagnetic interference. Herein, a flexible multiaxial force sensor enabled by U-shaped optical micro/nanofibers (MNFs) is reported. The MNF is embedded within an elastomer film topped with a dome-shaped protrusion. When the protrusion is subjected to vector forces, the embedded MNF undergoes anisotropic deformations, yielding time-resolved variations in light transmission. Detection of both normal and shear forces is achieved with sensitivities reaching 50.7dB N-1 (14% kPa-1) and 82.2dB N-1 (21% kPa-1), respectively. Notably, the structural asymmetry of the MNF induces asymmetrical optical modes, granting the sensor directional responses to four-directional shear forces. As proof-of-concept applications, tactile visualizations for texture and relief pattern recognition are realized with a spatial resolution of 160µm. Moreover, a dual U-shaped MNF configuration is demonstrated as a human-machine interface for cursor manipulation. This work represents a step towards advanced multiaxial tactile sensing.

Fusion of Wavelet Features and Gabor Features for SVM-based Iris Verification

Iris verification now become increasingly prominent in biometric-based person verification systems. It has gained a significant role in biometric systems due to its stability, high uniqueness, contactless and non-invasive properties. Iris has more inherent distinctive features than other biometrics. Feature extraction of iris plays a crucial role in this system for accurate person verification. Using the feature extraction process, unique iris features like textural patterns, crypts, and furrows of iris are extracted. In our study, we did a fusion of Discrete Wavelet Transform (DWT) features with multiple wavelet bases (db4, haar, coif3, and sym4) and Gabor features, which contain a good amount of textural and localized information. Fusion here indicates the concatenation of the extracted features using the above techniques. In this work, we studied this method on the full iris only so that a maximum number of features can be extracted. This combined approach yielded a significant 112 number of features. The extracted features are then verified using a support vector machine (SVM) classifier based on radial basis function (RBF) kernel with training vs testing split ratios of 8:2, 6:4, 4:6 and 2:8. In this study, we achieved the highest overall verification accuracy of 95.9% with training vs testing split ratio of 8:2. For other training vs testing split ratios of 6:4, 4:6 and 2:8 we achieved overall verification accuracies of 91.4%, 93.2% and 91.2% respectively. We got an overall verification accuracy of 92.9%, considering training vs testing ratios of 8:2, 6:4, 4:6 and 2:8.

Texture Analysis and Classification using Local Binary Patterns and Statistical Features

Texture analysis and classification are crucial in many applications such as medical applications, satellite imagery analysis, and so on. This paper presents a new technique that incorporates the LBP with the HOG to improve the texture analysis and classification. LBP is famous for finding out the local texture descriptors by comparing the pixel intensities it deals with and can challenge light variations and image transformations. On the other hand, there is HOG which emphasizes edge and gradient information to detect the orientation and shape of a texture in a given image. While LBP describes the local micro-patterns HOG gives the perspective of the global gradient orientation. The combined use of local and global texture information is helpful in the presented problem when prioritizing the recognition of complex texture patterns that cannot be deciphered by a single algorithm. To demonstrate the efficiency of the proposed hybrid method, several experiments are performed on several texture databases. According to the findings, the proposed LBP-HOG strategy proves more beneficial than basic LBP and HOG techniques concerning the classification rate and computing time. The combination method shows improved performance in terms of agreement with the reference of fine and coarse level of texture descriptions along with providing large-scale description of the texture which results in the improved discriminatory power of the texture classes.

Texture graph transformer for prostate cancer classification

Prostate cancer classification plays a pivotal role in the diagnosis and treatment of this disease. In this paper, we present a novel approach called the texture graph transformer, which combines texture analysis techniques, graph-based representations, and multi-head attention to enhance the accuracy of prostate cancer classification. Our texture graph transformer adeptly captures intricate texture details and patterns within prostate cancer lesion regions, efficiently improving the model’s ability to discern between different cancer types. By leveraging graph-based representations, our model constructs texture graphs that effectively capture the spatial and textural relationships among various regions in MRI images, enabling comprehensive feature extraction. The incorporation of a texture graph multi-head attention further enhances the model’s capacity to capture long-range dependencies and global context, with a specific focus on informative regions. Through extensive experiments conducted on a dataset comprising 226 MRI images, we demonstrate the efficacy of our proposed approach in significantly improving the performance of prostate cancer classification.

Estimation of video sequence homography based on a first-order estimation method

As it is a pre-processing task, estimation of video-sequence-based homography requires low computational costs and fast evaluation. However, current algorithms for video sequence tasks are commonly based on image-pair homography and do not consider the inner properties of the video sequences. Therefore they take unnecessary computational resources. In this work, we propose a novel algorithm with a first-order estimation method to fill the gap between estimation of image-pairs and video sequence homography. By considering the continuous movement of the camera, the proposed algorithm adopts a first-order estimation to accelerate the estimation process while maintaining its robustness. Instead of extracting many image features from every frame, we demonstrate that estimating a homography matrix with pixel-based texture patterns is effective and sufficient for video sequences. Experiments show that homography estimation with simple one-dimensional texture vectors, as used in our algorithm, can surpass state-of-the-art feature-based algorithms and deep-learning-based methods. This first-order estimation method was more than 40 times faster and real-time estimation used only the CPU.