Corner Detection Research Articles

Squirrel Search Optimization-based near-duplicate image detection

ABSTRACT Near duplicate (ND) image detection is a significant issue in a modern online environment with a wide range of applications like the detection of copyright violations and saving of storage space. Several existing ND detection techniques are perhaps not suitable for online applications due to the large computational burden, and may not successfully detect NDs containing large smooth and plain regions. In addition, the K-means algorithm used in most of the existing methods yield sub-optimal quantization of visual words. This article employs a robust algorithm of Squirrel Search Optimization (SSO) for quantization, fast-hessian matrix-based detector (FHMBD) and FAST Corner Detector (FCD) for the detection of KPs at both plain and non-smooth regions of all images, SURF for computing descriptors and Principal Component Analysis (PCA) for dimensionality reduction. The results of the developed method presented on five image databases. The proposed method offered 99.9% accuracy, 98.67% sensitivity, and 99.91% specificity respectively.

Research on automatic segmentation and recognition of single characters in original rubbings based on intelligent recognition of oracle bone inscriptions

This paper proposes an effective segmentation and recognition method using YOLOv8 to solve the problem of segmentation and recognition of Oracle rubbings images. Draw sub-pixel edge contours through spot detection, corner detection, and edge detection (such as Canny and Sobel), and combine grayscale, opening operations, binarization, and Gaussian filtering to remove noise and repair contours, extract image features, and establish preprocessing Model. Use this model to preprocess the original oracle rubbing image and train it based on YOLOv8. The results show that this method can effectively segment and identify oracle bones characters.

Smart dimensional quality assessment of embedded steel plates based on images and laser data fusion

Abstract Accurate and efficient positioning is critical to ensuring the dimensional quality assessment of embedded steel plates. However, traditional manual measurement methods struggle to efficiently measure and evaluate these plates. Vision-based measurement methods offer advantages such as high resolution, fast data acquisition, and processing speed, allowing accurate measurement of 2D coordinates. Light Detection and Ranging (LiDAR) can capture highly accurate point clouds, due to the unordered nature of point clouds, processing and analysis require significant computational resources. This paper proposes a method for smart 3D localization of embedded steel plates using image and laser data. (1) We introduce an improved rectangular diagonal constraint Harris corner detection method and achieve subpixel 2D corner detection of embedded plates based on deep learning:(2) given a calibrated camera-LiDAR, we develop a smart detection algorithm guided by 2D image bounding boxes, achieving 3D corner localization. In indoor testing and engineering applications, this method effectively ensures the dimensional quality of embedded steel plates. Compared to traditional manual inspection, the measurement efficiency reaches 10 min per station, with an accuracy of 2.12 mm.

An Approach for Implementing Electronic Image Stabilization Using an FPGA System

This paper proposes an approach for the implementation of a low-power electronic (digital) image stabilization using an AMD/Xilinx Zynq UltraScale+ ZU7EV device (CPU+FPGA) with a custom Linux OS. The stabilization method is based on frame-to-frame motion detection (Harris Corner Detector, an iterative optical flow calculator combined with a 4:2:1 down-sampler an 1:2:4 up-sampler) and an affine transformation that applies the stabilization. The scientific contribution of this paper resides in a combination of the most recent software algorithms presented in literature and porting that new resulting algorithm into hardware with the achieved performance of more than 2.5x current state of the art, thus enabling stabilization at 4K-UHD resolution.

Comparative Analysis of Image Stitching Algorithms for Bridge Inspection Imaging Systems

This paper discusses an innovative vehicle-mounted device designed for efficient inspection of bridge undersides, aiming to address the challenges of manual inspections, such as being labor-intensive and inefficient. The device uses high-precision cameras to capture detailed images of bridge bottoms, facilitating a thorough condition assessment. It evaluates three feature point extraction algorithms for image stitching—Scale-Invariant Feature Transform (SIFT), Harris corner detection, and Speeded Up Robust Features (SURF)—to create complete visual representations of bridge undersides. Field tests on a prefabricated I girder bridge demonstrated the device's effectiveness in gathering and stitching images, with the SIFT algorithm performing best for girder bottoms, Harris corner algorithm for web and flange surfaces, and SURF for rapid image processing. This research provides a foundation for the rapid identification of visible defects on bridge superstructures, significantly benefiting bridge maintenance and safety evaluations.

Enhancing Target Tracking: A Novel Grid-Based Beetle Antennae Search Algorithm and Confusion-Aware Detection.

Unmanned aerial vehicle target tracking is a complex task that encounters challenges in scenarios involving limited computing resources, real-time requirements, and target confusion. This research builds on previous work and addresses challenges by proposing a grid-based beetle antennae search algorithm and designing a lightweight multi-target detection and positioning method, which integrates interference-sensing mechanisms and depth information. First, the grid-based beetle antennae search algorithm's rapid convergence advantage is combined with a secondary search and rollback mechanism, enhancing its search efficiency and ability to escape local extreme areas. Then, the You Only Look Once (version 8) model is employed for target detection, while corner detection, feature point extraction, and dictionary matching introduce a confusion-aware mechanism. This mechanism effectively distinguishes potentially confusing targets within the field of view, enhancing the system's robustness. Finally, the depth-based localization of the target is performed. To verify the performance of the proposed approach, a series of experiments were conducted on the grid-based beetle antennae search algorithm. Comparisons with four mainstream intelligent search algorithms are provided, with the results showing that the grid-based beetle antennae search algorithm excels in the number of iterations to convergence, path length, and convergence speed. When the algorithm faces non-local extreme-value-area environments, the speed is increased by more than 89%. In comparison with previous work, the algorithm speed is increased by more than 233%. Performance tests on the confusion-aware mechanism by using a self-made interference dataset demonstrate the model's high discriminative ability. The results also indicate that the model meets the real-time requirements.

Artificial intelligence-based smart agricultural systems for saffron cultivation with integration of Unmanned Aerial Vehicle imagery and deep learning approaches

This paper presents an integrated Unmanned Aerial Vehicle (UAV) imagery system and artificial intelligence-based smart farming for saffron cultivation. This work is about monitoring the growth of saffron flowers through UAV imagery every week or month during the pre-harvesting time while the percentage of the covered area by leaf and saffron flowers is calculated. This is crucial for predicting saffron growing areas over cultivated regions. From the vertical viewing of UAV imagery from above, it is problematic from the bird’s eye perspective to identify the particular saffron-growing areas of things, so the multi-class classification of flowers (subjects) recognition system is proposed. So, the implementation of this work is divided into four phases. The first two phases (Phase 1 and Phase 2) are about the algorithms for Saffron growing region detections and predictions using the modified You Only Look Once (YOLO) higher version model followed by statistical analysis based region corner detections. The outcomes of the first two phases are used to form a database of saffron flowers with different scales, orientations, and deformations. This is further used to build a two-class classification model in the third phase (Phase 3) that discriminates saffron vs. non-saffron flowers. In the fourth phase, the two-class classification model is extended to a multi-class flower recognition model for recognizing 900 flower images database available in the largest social media website dedicated exclusively to gardening in the Phase 4. Extensive experiments are conducted, and the performances are compared with some existing state-of-the-art methods that show the superiority of the proposed system.

Implementation of Augmented Reality of Laboratory Building and Room Using Fast Corner Detection Algorithm

The Laboratory Buildsing is one of the buildings in Campus IV UINSU which is used to carry out practicum activities, many of the lecturers students and the community do not know the location and also the rooms in the Laboratory building. This research aims to make this application can provide convenience for users such as students, lecturers and the public to obtain information about laboratory buildings. In this research, the method used is Marker Based Tracking where application users must scan the marker first in order to see 3D objects from a floor plan and laboratory building. The results of this study in the form of Augmented Reality applications using Android as an operating system, on the marker added with the Fast Corner Detection algorithm aims to speed up real-time computing time with the consequence of reducing the level of accuracy of corner detection. The conclusion of AR and Fast Corner Detection can be implemented through a scan of the marker, the result obtained is that when scanning the marker a point from the FCD algorithm will appear indicating that the point on this marker is the result of the implementation of the FCD algorithm.

A Segment-Based Algorithm for Grid Junction Corner Detection Used in Stereo Microscope Camera Calibration

Corner detection is responsible for accurate camera calibration, which is an essential task for binocular three-dimensional (3D) reconstruction. In microscopic scenes, binocular 3D reconstruction has significant potential to achieve fast and accurate measurements. However, traditional corner detectors and calibration patterns (checkerboard) performed poorly in microscopic scenes due to the non-uniform illumination and the shallow depth of field of the microscope. In this paper, we present a novel method for detecting grid junction corners based on image segmentation, offering a robust alternative to the traditional checkerboard pattern. Model fitting was utilized to obtain the coordinates at a sub-pixel level. The procedures of the proposed method were elaborated, including image segmentation, corner prediction, and model fitting. The mathematical model was established to describe the grid junction. The experiment was conducted using both synthetic and real data and the experimental result shows that this method achieves high precision and is robust to image blurring, indicating this method is suitable for microscope camera calibration.

Trademark Text Recognition Combining SwinTransformer and Feature-Query Mechanisms

The task of trademark text recognition is a fundamental component of scene text recognition (STR), which currently faces a number of challenges, including the presence of unordered, irregular or curved text, as well as text that is distorted or rotated. In applications such as trademark infringement detection and analysis of brand effects, the diversification of artistic fonts in trademarks and the complexity of the product surfaces where the trademarks are located pose major challenges for relevant research. To tackle these issues, this paper proposes a novel recognition framework named SwinCornerTR, which aims to enhance the accuracy and robustness of trademark text recognition. Firstly, a novel feature-extraction network based on SwinTransformer with EFPN (enhanced feature pyramid network) is proposed. By incorporating SwinTransformer as the backbone, efficient capture of global information in trademark images is achieved through the self-attention mechanism and enhanced feature pyramid module, providing more accurate and expressive feature representations for subsequent text extraction. Then, during the encoding stage, a novel feature point-retrieval algorithm based on corner detection is designed. The OTSU-based fast corner detector is presented to generate a corner map, achieving efficient and accurate corner detection. Furthermore, in the encoding phase, a feature point-retrieval mechanism based on corner detection is introduced to achieve priority selection of key-point regions, eliminating character-to-character lines and suppressing background interference. Finally, we conducted extensive experiments on two open-access benchmark datasets, SVT and CUTE80, as well as a self-constructed trademark dataset, to assess the effectiveness of the proposed method. Our results showed that the proposed method achieved accuracies of 92.9%, 92.3% and 84.8%, respectively, on these datasets. These results demonstrate the effectiveness and robustness of the proposed method in the analysis of trademark data.

Event Vision-based Corner Detection with Count-normalized Multi-Layer Perceptron and Throughput Indicator

The advancement of event cameras has sparked a revolution in imaging technology, presenting exciting opportunities for vision-based measurement tasks. Event cameras operate on an innovative asynchronous imaging principle, which offers several advantages over traditional cameras, including ultra-high dynamic range and exceptional temporal resolution. As a result, event cameras excel in challenging environments characterized by motion blur, overexposure, or underexposure, outperforming conventional frame-based cameras. However, the asynchronous signal streams generated by event cameras pose compatibility challenges with existing vision-based measurement algorithms. This paper focuses specifically on corner detection, a critical vision-based measurement task, tailored for event cameras. To address this challenge, we propose novel corner detectors that leverage advanced optimization techniques, including enhanced time surface representations, multi-layer perceptron classifiers, and an innovative throughput mechanism. Through rigorous experimentation, our method consistently shows lower projection errors compared to state-of-the-art methods across all datasets while also maintaining longer tracking times in low-textured scenarios. Specifically, our CMLP and CMLP-T methods achieve an average valid tracking rate of 83.38% and 84.65%, respectively, on the DAVIS240C dataset collection, surpassing all existing methods. We validate the effectiveness of our proposed corner detectors by demonstrating their enhanced performance compared to state-of-the-art methods. Furthermore, our work contributes to the application of machine learning in event signal processing for vision-based measurement tasks, providing insights into optimizing models for the unique characteristics of event cameras.

Design and Implementation of Fabric Wrinkle Detection System Based on YOLOv5 Algorithm

Background Nowadays, robots have been widely used in handling rigid objects, but research on deformable objects like fabrics is still in its early stages. This is because fabrics possess infinite degrees of freedom and their state modeling is highly complex, making robot manipulation of fabrics challenging due to the occurrence of wrinkles and deformations during the operation. The detection and recognition of fabric deformations such as wrinkles and fabric manipulation features like corners are of great significance in enhancing a robot's capability to handle deformable objects. Methods In response to the issue of fabric wrinkles in various scenarios, we propose a real-time fabric wrinkle and corner detection system based on the YOLOv5 detection algorithm. Additionally, we implement a fabric flattening operation on a hardware platform using the detected wrinkle and corner information. Results We collected and created a dataset of fabric deformation features and trained a detection model, achieving a detection accuracy of over 90%. The model was deployed in the fabric wrinkle detection system, using a heuristic operation strategy of flattening the fabric from the four corners. As a result, the robot successfully performed the flattening operation on wrinkled fabric. Conclusions The application of the YOLOv5 algorithm enables effective detection of fabric wrinkles and corner points. Based on the detection information and using the quadrilateral flattening operation method, the robotic system achieves fabric flattening operations.

A Proposed Text Encryption inside Video Using Harris Corner Detection and Salas20 Encryption Algorithm

يعد تشفير النص في الفيديو أداة حيوية في العديد من الصناعات حيث تكون حماية المعلومات الحساسة هي الأكثر أهمية. عادةً ما تواجه الخوارزميات وطرق الكشف الآلي صعوبة في تحديد موقع النص المخفي في إطارات الفيديو. تزيد هذه المقاومة من أمان المعلومات المخفية لأنه من الصعب على الأطراف غير المدعوة اكتشاف وجود نص مشفر. كما أنه يجمع بين المحتوى المكتوب والمرئي لتقديم كلا النوعين من المعلومات في وقت واحد وبسلاسة. في هذا البحث ، نقدم طريقة جديدة لتشفير النص داخل الفيديو باستخدام خوارزمية التشفير Salsa20 و Harris Corner Detection. الهدف من هذه الدراسة هو زيادة سرية وأمن المعلومات النصية المضمنة في محتوى الفيديو ، وهناك خطوتان أساسيتان في المنهجية المقترحة. لتحديد الزوايا أو النقاط المهمة داخل إطارات الفيديو ، تم استخدام طريقة Harris Corner Detection لأول مرة. تعمل هذه الزوايا كنقاط ميزة قوية يمكن استخدامها لدمج النص. تساعد طريقة Harris Corner Detection في تحديد الأماكن التي قد يتم إخفاء النص بها بدقة ، وذلك دون التقليل من جودة الصورة المرئية الإجمالية للفيديو ، وثانيًا ، يتم إنشاء مفتاح التشفير باستخدام تقنية التشفير Salsa20. Salsa20 هو تشفير دفق شائع يوفر تشفيرًا موثوقًا وتشغيلًا فعالاً. يتم تحويل النص المضمن إلى نص تشفير بواسطة XOR باستخدام مفتاح التشفير قبل تضمينه في الفيديو ، مما يضمن سريته وحمايته من الوصول غير المصرح به. تكشف مقارنة الطريقة المقترحة مع طرق تشفير النص الحالية عن عدد من المزايا. تدمج تقنية Harris Corner Detection النص في إطارات الفيديو بحيث يتم دمجها بشكل أقل وضوحًا ، مما يجعل من الصعب على الخصوم تحديد وجود المعلومات المخفية. يضمن استخدام Salsa20 أيضًا المستوى العالي من الأمان والحماية للنص المشفر ، والدفاع عنه ضد الهجمات المحتملة. يتم تقييم النظام المقترح باستخدام MSE و PSNR والارتباط و NPCR و UACI والإنتروبيا ، وتوفر مقاييس التقييم هذه نتائج ممتازة.

Signature Elevation Using Parametric Fusion for Large Convolutional Network for Image Extraction

The image acquisition process involves finding regions of interest and defining feature vectors as visual features of the image. This encompasses local and global delineations for specific areas of interest, enabling the classification of images through the extraction of high-level and low-level information. The proposed approach computes the Harris determinants and Hessian matrix after converting the input image to grayscale. Blob structuring is then performed to identify potential regions of interest that can adequately describe texture, color, and shape at different representation levels and the Harris corner detector is used to identify keypoints within these regions. Moreover, scale adaptation method is applied to the determinants of the Harris matrix and the Laplacian operator to extract scale-invariant features. Meanwhile, the input image undergoes processing through VGG-19, DenseNet, and AlexNet architectures to extract features representing diverse levels of abstraction. Furthermore, the RGB channels of the input image are extracted and their color values are computed. All extracted features local, global, and color are then integrated in feature set and encoded through a bag-of-words model to rank and retrieve images based on their shared visual characteristics. The proposed technique is tested on challenging datasets including Caltech-256, Cifar-10, and Corel-1000. The presented approach shows remarkable precision, recall and f-score rates in most of the image categories. The proposed approach leverages the complementary strengths of multiple feature extraction techniques to achieve high accuracy.

Head motion-corrected eye gaze tracking with the da Vinci surgical system.

To facilitate the integration of point of gaze (POG) as an input modality for robot-assisted surgery, we introduce a robust head movement compensation gaze tracking system for the da Vinci Surgical System. Previous surgical eye gaze trackers require multiple recalibrations and suffer from accuracy loss when users move from the calibrated position. We investigate whether eye corner detection can reduce gaze estimation error in a robotic surgery context. A polynomial regressor is first used to estimate POG after an 8-point calibration, and then, using another regressor, the POG error from head movement is estimated from the shift in 2D eye corner location. Eye corners are computed by first detecting regions of interest using the You Only Look Once (YOLO) object detector trained on 1600 annotated eye images (open dataset included). Contours are then extracted from the bounding boxes and a derivative-based curvature detector refines the eye corner. Through a user study (n = 24), our corner-contingent head compensation algorithm showed an error reduction in degrees of visual angle of 1.20 (p = 0.037) for the left eye and 1.26 (p = 0.079) for the right compared to the previous gold-standard POG error correction method. In addition, the eye corner pipeline showed a root-mean-squared error of 3.57 (SD = 1.92) pixels in detecting eye corners over 201 annotated frames. We introduce an effective method of using eye corners to correct for eye gaze estimation, enabling the practical acquisition of POG in robotic surgery.

Quaternion-Based Attitude Estimation of an Aircraft Model Using Computer Vision.

Investigating aircraft flight dynamics often requires dynamic wind tunnel testing. This paper proposes a non-contact, off-board instrumentation method using vision-based techniques. The method utilises a sequential process of Harris corner detection, Kanade-Lucas-Tomasi tracking, and quaternions to identify the Euler angles from a pair of cameras, one with a side view and the other with a top view. The method validation involves simulating a 3D CAD model for rotational motion with a single degree-of-freedom. The numerical analysis quantifies the results, while the proposed approach is analysed analytically. This approach results in a 45.41% enhancement in accuracy over an earlier direction cosine matrix method. Specifically, the quaternion-based method achieves root mean square errors of 0.0101 rad/s, 0.0361 rad/s, and 0.0036 rad/s for the dynamic measurements of roll rate, pitch rate, and yaw rate, respectively. Notably, the method exhibits a 98.08% accuracy for the pitch rate. These results highlight the performance of quaternion-based attitude estimation in dynamic wind tunnel testing. Furthermore, an extended Kalman filter is applied to integrate the generated on-board instrumentation data (inertial measurement unit, potentiometer gimbal) and the results of the proposed vision-based method. The extended Kalman filter state estimation achieves root mean square errors of 0.0090 rad/s, 0.0262 rad/s, and 0.0034 rad/s for the dynamic measurements of roll rate, pitch rate, and yaw rate, respectively. This method exhibits an improved accuracy of 98.61% for the estimation of pitch rate, indicating its higher efficiency over the standalone implementation of the direction cosine method for dynamic wind tunnel testing.

Gradient-Based Optimization Method for Experimental Modal Parameter Estimation with Finite Element Model

This paper presents a novel gradient-based optimization algorithm for improving the accuracy of experimentally estimated modal parameters with the assistance of finite element models. Initially, we recast the discrete vibration response equation into a matrix form and formulate the parameter estimation problem in modal analysis as an optimization problem. Then the problem is solved with a gradient-based iterative algorithm, which explicitly exhibits the closed form of gradients used in optimization. Initial values for this iteration are parameters derived from finite element models, since every important engineering structure should be analyzed with a finite element model before it is constructed. Subsequently, the performance of this algorithm is validated by both pure numerical experiments, which simulate the physical world, and experiments using real measurement data gathered by sensors in the real physical world. The algorithm’s performance is further enhanced by incorporating gradient clipping and an adaptive iteration threshold. As a comparison, a discussion on classical least-squares time-domain method for the problem is provided. For practical applications, the Shi–Tomasi corner detection and Lucas–Kanade optical flow methods are deployed to detect corner points from videos taken during the vibration of a structure and track the motion of these points in the videos.

Detection of Vehicle Number Plate and Speed Using Machine Learning

In an era marked by a significant upsurge in vehicular traffic and the resultant increase in road accidents, the need for advanced traffic management systems is paramount. This paper presents an innovative solution, "Detection of vehicle number plate and speed using machine learning" which aims to enhance road safety by addressing the persistent problem of over-speeding. The project leverages state-of-the-art technologies, including machine learning, deep learning, and computer vision, to develop a smart system that can detect speeding vehicles, recognize license plates, and record crucial data related to speed limit violations. The primary motivation for this endeavor is the escalating rate of road accidents, particularly in India, driven by speeding in areas susceptible to accidents. The system employs image segmentation, corner detection algorithms, filtering algorithms, and automatic vehicle plate recognition techniques to achieve its objectives. By using machine learning and deep learning models, the system accurately identifies license plates, segments characters on these plates, and recognizes them. In summary, this project represents a significant advancement in road safety and traffic management. By deploying an intelligent system that can proactively detect over-speeding vehicles and maintain comprehensive records, it strives to create a safer and more responsible driving environment, ultimately working towards the prevention of accidents and saving lives. Key Words: Automatic Number Plate Recognition, Vehicle Speed Detection, Machine Learning, Computer Vision, Traffic Management

Evaluation of 2D affine — hand-crafted detectors for feature-based TLS point cloud registration

Abstract The development of modern surveying methods, particularly, Terrestrial Laser Scanning (TLS), has found wide application in protecting and monitoring engineering and objects and sites of cultural heritage. For this reason, it is crucial that several factors a˛ecting the correctness of point cloud registration are considered, including the correctness of the distribution of control points (both signalised and natural), the quality of the process, and robustness analysis. The aim of this article is to evaluate the quality and correctness of TLS registration based on point clouds converted to raster form (in spherical mapping) and hand-crafted detectors. The expanded Structure-from-Motion (SfM) was used to detect the tie points for TLS registration and reliability assessment. The results demonstrated that affine detectors are useful in detecting a high number of key points (increased for point detectors by 8–12 times and for blob detectors by about 10–24 times), improving the quality and TLS registration completeness. For the registration accuracy of point cloud on signalised check points, the lower values can be noted for maximum RMSE errors for blob affine detectors than detectors and larger values for corner detectors and affine detectors (not more than 4 mm in the extreme cases, typically 2 mm). The commonly-applied target-based registration method yields similar results (di˛erences do not exceed – in extreme cases – 3.5 mm, typically less than 2 mm), proving that using affine detectors in the TLS registration process is and reasonable and can be recommended.

A New Approach for Classification of Spices to Make Special Herbal Tea Using Caralluma Fimbriata

Classification of multiple types of spice images is automatically challenging due to conflict between the texture patterns of spice images. This work aims to develop an automatic system for classifying different types of spice images so that the system can choose an appropriate spice to make herbal tea using Caralluma fimbriata. This work considers the following seven spices, namely, cinnamon, citrus peel, clove, ginger, jeera, kokum, mint, and Caralluma fimbriata as one more class for classification. Most of the existing systems need human intervention to choose different spices to make Caralluma fimbriata tea. It is observed that the pattern of different spice images represents different textures. This observation motivated us to extract features based on multi-Sobel kernels. To reduce the number of computations, the proposed work introduces a novel idea of corner detection based on Gaussian distribution. For each corner, the method performed is multi-Sobel kernels for extracting features. The features are fed to convolutional neural network layers for the classification of multiple spice images. The results of our dataset and comparative study with the state-of-the-art methods show that the proposed model is superior to existing methods in terms of classification rate.