Super Pixel Research Articles

Gas detection based on mid-infrared super pixel multi-spectral imaging device

Gas detection based on mid-infrared super pixel multi-spectral imaging device

Anchor selection based deep learning two stage fabric defect localization

<span lang="EN-US">Localizing and classifying fabric defects is a crucial step in the quality control process used in the production of textiles. Recently, fabric defect classification and detection have made use of deep learning approaches based on anchor selection. But due to in effectiveness in anchor selection, the computational overhead and localization error are higher in these solutions. As a solution to this problem, this work proposes a two-stage improvised anchor selection deep learning technique. In first stage, quaternion fourier transform frequency domain analysis along with super pixel segmentation is done over the fabric image to select probable defect regions. In the second stage deep learning based regression along with super pixel segment comparison is done over the probable defect regions localize and categorize the defect. Due to effectiveness in selection of probable defect regions and categorization of regions, the defect localization accuracy is increased at a comparative low computational overhead in the proposed two stage improvise anchor selection deep learning technique. Testing against the irish longitudinal study on ageing (TILDA) fabric defect detection dataset, the proposed solution is found to provide 1.2% higher fabric defect localization accuracy at a 3% lower computation overhead compared to most recent existing works.</span>

Few-shot remote sensing image segmentation based on label propagation and open-set domain adaptation

ABSTRACT Few-shot segmentation aims to segment objects in a task dataset with only a few labelled target examples, aided by a lot of labelled auxiliary datasets. Existing approaches typically assume that the task dataset and auxiliary dataset originate from the same source but have disjoint category sets. However, it is common in remote sensing image segmentation tasks that the datasets are from different sources and the category sets are often partially overlapped, where models trained on the auxiliary dataset degrade in performance on the task dataset. To address these issues, we present a few-shot segmentation method based on graph network and open-set domain adaptation. The proposed method utilizes a graph model to capture the relationships between super pixels and to predict labels for the unlabelled samples by label propagation, meanwhile, leverages open-set domain adaptation to reduce inter-domain discrepancies and enhances model transferability. The proposed method is evaluated on two publicly available datasets, and the effectiveness of the proposed approach is demonstrated by the significant improvement in accuracy compared to existing methods.

Cross-Correlation Driven Aerial Image Segmentation: Leveraging Multi-Scale Features and Edge Information

Abstract: Semantic segmentation of remote sensing images is crucial for interpreting these large, rich in information scenes and our study introduces a new method for segmenting remote sensing imagery (RSI) when faced with limited training data and imbalanced classes. Our approach utilizes a unique potential function that merges information from both super pixel segmentation and edge detection. This combination allows the model to effectively analyze features at various scales and reduce the influence of potential errors in super pixel segmentation. Furthermore, the inclusion of edge details extracted via the Sketch token algorithm refines object boundaries, yielding more accurate segmentation results. This work offers a promising solution for achieving reliable interpretation of RSIs in scenarios with limited training data.

Enhanced Segmentation of Ischemic Stroke Lesion in MRI Images Using a Geometrically Customised Deep Convolution Model (GCDCM)

Ischemic stroke lesion often known as a stroke, is a significant health issue that requires accurate analysis and classification of brain magnetic resonance imaging (MRI) data. In this study, we propose a novel deep transfer learning approach, called geometrically customized deep convolution model, for the purpose of MRI analysis and classification of brain stroke. Neurostroke segmentation is a serious medical image processing challenge. Segmented regions aid disease identification and treatment. Anywhere can form thrombi. Segmentation facilitates automatic detection because they can be any size or shape. Popular image analysis tool MRI diagnoses well. This diagnostic method shows brain stroke architecture. MRI must replace manual detection. Online datasets recommended cerebral stroke detection and segmentation. Deep learning model MRI scans and detectron 2 with masked CNN Nets segment thrombus. This net architecture recognises dataset stroke boundaries. Classifying strokes with vgg16, resnet50, inceptionv3, and resnet5 transfer learning is possible. Mask the image, then binary predict by eliminating the skull, extracting features, and iterating to find stroke. The model and thrombus mask are predicted if the binary prediction matches the human forecast. Otherwise, data processing resumes. Binary prediction uses the segmentation region and pixels overlap between the ground truth and predicted segmentation to calculate parameters. Compared to reality, the categorization of medical images with weak signals seems tough, especially with a short "train" dataset. Mixing deep learning architectures avoids these drawbacks and extracts signals to accurately classify classes. Deep neural networks best recognise, find, and divide computer vision objects for clinical image analysis. Preprocessing MRI scans, skull stripping with deep CNN architecture combinational net, and brain stroke segmentation are our main tasks. Modern medical image processing is hard. Flexible and uneven borders make brain strokes hard to identify and segment. The transfer learning-based super pixel approach segments brainstrokes. Because we predict every visual pixel, dense prediction occurs. Early discovery of thrombus improves treatment and survival. These procedures have considerably improved our quality indexes.

Automatic Identification of on Shelf Stock Availability in Retail Shops Using GCN

In retail industry ensuring on shelf availability is crucial for customer satisfaction. This project introduces an innovative solution for automated on shelf stock monitoring by Graph Convolution Network (GCN) fundamental algorithm as framework. This particular system will combine computer vision techniques to capture real time shelf images and employees GCN to process the visual data efficiently. Through graph based representation of store shelves and products, the GCN algorithm will analyze the items and their availability status. This project includes in data collection, image preprocessing, object detection. The application of GCN is used to construct a dynamic graph that capture items. This algorithm’s ability to model complex dependencies within the shelf inventory facilitates accurate stock availability. Alerts are generated when low stock or out of stock situations are detected. Keywords—super pixel graph ,Graph convolutional network ,SVM , shelf image and notification alert

The application of Hyperpixel segmentation algorithm in Chinese painting

Chinese painting, as an important component of traditional Chinese art, not only expresses Chinese culture and history, but also contains rich artistic connotations. Therefore, extracting and analyzing the main objects of Chinese painting is of great significance. The research introduces a fusion deep network based super pixel segmentation algorithm for image segmentation, and utilizes user marked segmentation target objects and backgrounds. The maximum similarity region merging idea is adopted to extract the main subject objects in Chinese painting, thereby achieving a deep understanding of the work. The results show that the boundary recall and segmentation accuracy of the Chinese painting subject object segmentation algorithm based on super pixels on the BuptPainting dataset are as high as 94.38% and 98.06%, respectively, with an undersegmentation error rate of only 7.69%. Meanwhile, the average accuracy value, optimal data scale value, and optimal image scale value of this method on the BuptPainting dataset are as high as 0.657, 0.541, and 0.529, respectively. The method proposed by the research institute has significant advantages in segmenting the main objects of Chinese painting, providing new ideas and methods for image analysis and processing of modern Chinese painting, and helping to further explore the artistic charm and cultural connotations of Chinese painting.

Object Based Classification in Google Earth Engine Combining SNIC and Machine Learning Methods (Case Study: Lake Köyceğiz)

Köyceğiz Lake is one of our country’s most critical coastal barrier lakes, rich in sulfur, located at the western end of the Mediterranean Region. Köyceğiz Lake, connected to the Mediterranean via the Dalyan Strait, is one of the 7 lakes in the world with this feature. In this study, water change analysis of Köyceğiz Lake was carried out by integrating the Object-Based Image Classification method with CART (Classification and Regression Tree), RF (Random Forest), and SVM (Support Vector Machine) algorithms, which are machine learning algorithms. SNIC (Simple Non-iterative Clustering) segmentation method was used, which allows a detailed analysis at the object level by dividing the image into super pixels. Sentinel 2 Harmonized images of the study area were obtained from the Google Earth Engine (GEE) platform for 2019, 2020, 2021, and 2022,and all calculations were made in GEE. When the classification accuracies of four years were examined, it was seen that the classification accuracies(OA, UA, PA, and Kappa) of the lake water area were above 92%, F-score was above 0.98 for all methods using the object-based classification method obtained by the combination of the SNIC algorithm and CART, RF, and SVM machine learning algorithms. It has been determined that the SVM algorithm has higher evaluation metrics in determining the lake water area than the CART and RF methods.

Breast ultrasound image despeckling using multi-filtering DFrFT and adaptive fast BM3D

Improving the quality of breast ultrasound images is of great significance for clinical diagnosis which can greatly boost the diagnostic accuracy of ultrasonography. However, due to the influence of ultrasound imaging principles and acquisition equipment, the collected ultrasound images naturally contain a large amount of speckle noise, which leads to a decrease in image quality and affects clinical diagnosis. To overcome this problem, we propose an improved denoising algorithm combining multi-filter DFrFT (Discrete Fractional Fourier Transform) and the adaptive fast BM3D (Block Matching and 3D collaborative filtering) method. Firstly, we provide the multi-filtering DFrFT method for preprocessing the original breast ultrasound image so as to remove some speckle noise early in fractional transformation domain. Based on the fractional frequency spectrum characteristics of breast ultrasound images, three types of filters are designed correspondingly in low, medium, and high frequency domains. And by integrating filtered images, the enhanced images are obtained which not only remove some speckle noise in background but also preserve the details of breast lesions. Secondly, for further enhancing the image quality on the basis of multi-filter DFrFT, we propose the adaptive fast BM3D method by introducing the DBSCAN-based super pixel segmentation to block matching process, which utilizes super pixel segmentation labels to provide a reference on how similar it is between target block and retrieval blocks. It reduces the number of blocks to be retrieved and make the matched blocks with more similar features. At last, the local noise parameter estimation is also adopted in the hard threshold filtering process of traditional BM3D algorithm to achieve local adaptive filtering and further improving the denoising effect. The synthetic data and real breast ultrasound data examples show that this combined method can improve the speckle suppression level and keep the fidelity of structure effectively without increasing time cost.

Unsupervised super pixel level change detection based on canonical correlation analysis

Unsupervised super pixel level change detection based on canonical correlation analysis

Brain Tumor Detection in MRI Images Using CNN With U-NET

Human brain tumors are exceptionally hazardous and devil of the advanced period, prompting definite death. Likewise, when a brain tumor progresses, the patient's life turns out to be more muddled. Early tumor diagnosis is subsequently vital for save the patient's life and expanding their personal satisfaction. In this way, further developed brain tumor recognizable proof is required in the clinical space. Magnetic resonance imaging (MRI)programmed ID of human brain tumors is fundamental for a few indicative and remedial applications. The ongoing techniques, for example, wavelet transform, random forest, fuzzy C-means, and artificial neural networks (ANN), may identify brain tumors, however they need additional opportunity to execute (in minutes) and have less accuracy. In this work, we give a better technique to distinguishing brain cancers in people that utilizes principal component analysis (PCA) and super pixels related to the format based K-means (TK) calculation to rapidly track down growths more. To increment exactness, we will expand this and use CNN with U-Net. To start with, we use PCA and super pixels to remove key qualities that guide in the exact recognition of cerebrum cancers. Then, a channel that guides in expanding exactness is utilized to improve the image. To recognize the mind growth, the TK-means grouping strategy is utilized to lead picture division. The discoveries of the examination exhibit that, in contrast with other current strategies, the proposed detection system for brain tumor recognizable proof in attractive reverberation imaging accomplishes higher exactness and more limited execution times (measured in seconds).

Recognition and detection of unusual activities in ATM using dual-channel capsule generative adversarial network

Real-time detection of human activity has become essential for monitoring and security of public spaces such as bank ATMs and workplaces, due to daily rise in criminal activities. Currently, monocular CCTV cameras that only record RGB video are used for monitoring such restricted areas. In addition to RGB data, the RGB + D sensor also offers depth information about the scene. To overcome the issue of online recognition of anomalous activities in Bank ATMs, a supervised deep learning method utilizing Dual-Channel Capsule Generative Adversarial Network (DCCGAN) and RGB + D sensor is proposed. The input RGB + D Dataset is given to super pixel motion detection method to find the region of interest (ROI). Motion detection is a significant stage examination of wide scene for background subtraction and foreground detection. After arranging the motion detection, its region is positioned frame by frame. Then, the detected ROI is given to fast discrete curvelet transform with the wrapping (FDCT-WRP) method. FDCT-WRP feature extraction method. These extracting features are supplied to Deep Convolutional Spiking neural network (DCSNN), which realize the object. RGB and depth video segments are used to create motion templates from the RGB + D data online video stream. These templates are trained on DCCGANs to identify distrustful events in current activity and categorized as normal and abnormal. Additionally, a unique RGB + D dataset is employed because there was no existing dataset available for analyzing human activity in ATMs. The proposed DUA-DCCGAN-ATM approach is assessed on qualitative with quantitative statistical evaluation parameters and identify suspect occurrence with 0.932 precision and 98.2 % accuracy. The detailed statistical analysis exemplifies that the proposed technique can identify distrustful events in a real-time online manner prior completing the anomalous activity.

Machine Learning and Deep Learning Approaches For Brain Disease Diagnosis

Recent Recognition and division of a mind cancer, for example, glioblastoma multi shaped in attractive reverberation (MR) pictures are frequently difficult because of its characteristically heterogeneous sign qualities. A strong division strategy for cerebrum growth X-ray checks was created and tried. Techniques Basic limits and measurable strategies can't enough portion the different components of the GBM, like nearby difference upgrade, rot, and edema. Most voxel-based techniques can't accomplish agreeable outcomes in bigger informational indexes, and the strategies in view of generative or discriminative models have natural constraints during application, for example, little example set learning and move. The commitments of these two tasks were to show the complicated collaboration of mind and conduct and to comprehend and analyze cerebrum sicknesses by gathering and dissecting huge amounts of information. Chronicling, examining, and sharing the developing neuroimaging datasets presented significant difficulties. Multimodal MR pictures are sectioned into super pixels utilizing calculations to ease the inspecting issue and to further develop the example representativeness. Then, highlights were separated from the super pixels utilizing staggered Gabor wavelet channels. In view of the elements, grey level co-occurrence matrix (GLCM) model and a fondness metric model for growths were prepared to beat the impediments of past generative models.

CEGAT: A CNN and enhanced-GAT based on key sample selection strategy for hyperspectral image classification

In recent years, the application of convolutional neural networks (CNNs) and graph convolutional networks (GCNs) in hyperspectral image classification (HSIC) has achieved remarkable results. However, the limited label samples are still a major challenge when using CNN and GCN to classify hyperspectral images. In order to alleviate this problem, a double branch fusion network of CNN and enhanced graph attention network (CEGAT) based on key sample selection strategy is proposed. First, a linear discrimination of spectral inter-class slices (LD_SICS) module is designed to eliminate spectral redundancy of HSIs. Then, a spatial spectral correlation attention (SSCA) module is proposed, which can extract and assign attention weight to the spatial and spectral correlation features. On the graph attention (GAT) branch, the HSI is segmented into some super pixels as input to reduce the amount of network parameters. In addition, an enhanced graph attention (EGAT) module is constructed to enhance the relationship between nodes. Finally, a key sample selection (KSS) strategy is proposed to enable the network to achieve better classification performance with few labeled samples. Compared with other state-of-the-art methods, CEGAT has better classification performance under limited label samples.

Sea Cucumber Identification Fishing System Based on Hog Super Pixel Feature Extraction

Due to the refraction, reflection and absorption of light induced by seawater and suspended particles, the image recognition of underwater vehicle has the problem of low accuracy and difficult localization, and to solve this one problem, an improved LSTM classification algorithm (CH-LSTM) based on CLAHE and HOG is given. First, the improved CLAHE algorithm is used to enhance image by image noise removal and de-fogging, the problems of underwater image distortion, fine lines, and abrupt changes are solved in the aquaculture waters image. Then, the Histogram of Orientation Gradient (HOG) operator is used for feature extraction to describe the shape of sea cucumbers and generate feature vectors; finally, the LSTM algorithm is used to classify the feature vectors and avoid overfitting through memory gates, so the generalization ability of the model was enhanced. The identification and sorting experiments of underwater fishing sea cucumbers show that the proposed algorithm is superior, especially in the environment of poor water quality, and the identification and localization accuracy of sea cucumbers is improved compared with the traditional ground SVM and BP neural network algorithms, and the identification accuracy is above 95.28%.

Correction to: Efficient COVID‑19 super pixel segmentation algorithm using MCFO‑based SLIC

Correction to: Efficient COVID‑19 super pixel segmentation algorithm using MCFO‑based SLIC

Anomaly-Based Ship Detection Using SP Feature-Space Learning with False-Alarm Control in Sea-Surface SAR Images

Synthetic aperture radar (SAR) can provide high-resolution and large-scale maritime monitoring, which is beneficial to ship detection. However, ship-detection performance is significantly affected by the complexity of environments, such as uneven scattering of ship targets, the existence of speckle noise, ship side lobes, etc. In this paper, we present a novel anomaly-based detection method for ships using feature learning for superpixel (SP) processing cells. First, the multi-feature extraction of the SP cell is carried out, and to improve the discriminating ability for ship targets and clutter, we use the boundary feature described by the Haar-like descriptor, the saliency texture feature described by the non-uniform local binary pattern (LBP), and the intensity attention contrast feature to construct a three-dimensional (3D) feature space. Besides the feature extraction, the target classifier or determination is another key step in ship-detection processing, and therefore, the improved clutter-only feature-learning (COFL) strategy with false-alarm control is designed. In detection performance analyses, the public datasets HRSID and LS-SSDD-v1.0 are used to verify the method’s effectiveness. Many experimental results show that the proposed method can significantly improve the detection performance of ship targets, and has a high detection rate and low false-alarm rate in complex background and multi-target marine environments.

Mixture Based Superpixel Segmentation and Classification of SAR Images

Abstract: The proposed approach suggests a mixture-based super pixel segmentation technique for synthetic aperture radar (SAR) images. SAR is a radar system used to generate 2D or 3D representations of objects like landscapes. This method utilizes SAR image amplitudes and pixel coordinates as features. Super pixels are large irregular-shaped regions obtained through oversegmentation of an image. While super pixel segmentation methods are commonly designed for colour images, this approach adapts a finite mixture model (FMM) for single-channel SAR images. By employing finite mixture models, the pixels are clustered into super pixels. Following the super pixel segmentation, the method employs a hierarchical decision tree clustering algorithm for classifying different land covers, such as climate monitoring and natural resources exploitation. The decision tree algorithm creates a dendrogram or tree structure to group feature vectors. The proposed super pixel method demonstrates improved classification accuracy compared to state-of-the-art methods like quick-shift, turbo pixels, simple linear iterative clustering, and pixel intensity and location similarity. The implementation of the proposed method is efficiently carried out using MATLAB software.

Image semantic segmentation using deep learning technique

With the deepening research on image understanding in many application fields, including auto drive system, unmanned aerial vehicle (UAV) landing point judgment, virtual reality wearable devices, etc., computer vision and machine learning researchers are paying more and more attention to image semantic segmentation (ISS). In this paper, according to the different region generation algorithms, the regional classification image semantic segmentation methods are classified into the candidate region method and the segmentation mask method, according to different learning methods, the image semantic segmentation methods based on super pixels are divided into fully supervised learning method and weakly supervised learning method. The typical algorithms in these various categories are summarized and compared. In addition, this paper also systematically expounds the role of DL technology in the field of ISS, and discusses the main challenges and future development prospects in this field.

Multi-scale image depth fusion method based on superpixel-level convolutional neural network

In order to improve the image quality, reduce the image noise and improve the image definition, the image depth fusion processing is realized by using the sp CNN network (Super pixel level convolution neural network, sp CNN). The improved non-local mean method is used to de-noise the image to highlight the role of the center pixel of the image block; the de-noised image is segmented by the improved CV model (Chan-Vese, CV), and the globally optimal multi-scale image segmentation result is obtained after optimization; From the perspective of regional features, the similarity measurement of image regions is carried out to realize image preprocessing. The sp-CNN network is constructed, and with the help of the idea of pyramid pooling, the average pooling is used to extract the features of each layer from the global and local levels of the convolutional features, and the training data set is generated for training, thereby realizing multi-scale image fusion. The experimental results show that the optimal value of the root mean square error index of the proposed method is 0.58. The optimal value of structural similarity index is 41.22. On the average slope index, the optimal value is 21.39. The optimal value of cross entropy index is 2.21. This shows that the proposed method has high image definition and good visual effect, which verifies the effectiveness of the method.