Image Partition Research Articles

YOLOrot2.0: A novel algorithm for high-precision rice seed size measurement with real-time processing

We present YOLOrot2.0, an automated algorithm for measuring the dimensions of rice seeds, which holds significant importance in evaluating grain quality and genetic breeding research. The current methods for rice seed measurement exhibit various limitations, such as the need for seed preprocessing and selection, specialized equipment for measurement, and prolonged measurement time. To address these issues, YOLOrot2.0 introduces the following improvements: Firstly, it utilizes an anchor-free detection algorithm to optimize the detection of rotated targets. Secondly, the utilization of the Kalman Filter IoU loss function, which combines the horizontal bounding box and smooth L1 loss function, accelerates the convergence speed of the network. Moreover, the YOLOv8 architecture was adjusted by modifying certain convolutional layers and the Context to Fusion module to enhance the detection capabilities for smaller targets. Finally, YOLOrot2.0 enables direct processing of the entire image, eliminating the need for image partitioning and resulting in substantial time and processing savings. Experimental results demonstrate that YOLOrot2.0 achieves an mAP (mean average precision) score of 0.95, surpassing other comparative algorithms. Additionally, YOLOrot2.0 provides highly accurate measurements of seed length and width, closely aligned with ground truth values. Notably, YOLOrot2.0 achieves real-time detection by achieving an average detection time of only 11.5 ms for images sized 3000×4000 pixels.

A novel algorithm for image segmentation (IP-MH-MLT): employing an image partitioning technique with metaheuristic parameters to enhance multilevel thresholding

A novel algorithm for image segmentation (IP-MH-MLT): employing an image partitioning technique with metaheuristic parameters to enhance multilevel thresholding

Iris image retrieval using partial matching of image blocks

AbstractThe problem of human identification through recognition of patterns in iris images captured in unconstrained environments results in image artefacts such as image occlusion and specular reflection, in which iris tissue is observable to extremely low content. To overcome this problem, this paper presents a novel method for iris image retrieval and recognition based on partial pattern matching. The main contribution of the proposed method relies on an image partitioning schema in which the iris is divided into non‐overlapping blocks with varying dimensions, facilitating the identification and removal of image regions impaired by eyelids, eyelashes, and specular reflections. In fact, the blocks that contain artefacts are completely ignored and those blocks are preserved that include useful patterns for identification. In addition, a multi‐feature similarity followed by a score fusion technique is employed for ranking the retrieval results. The remarkable results of the classification stage include an accuracy of 100%, 98.75%, and 99.94% on three benchmark databases, including UPOL, UBIRIS.V2, and CASIA‐Iris‐Interval.v3, respectively. Additionally, in the retrieval stage, the proposed method achieves a precision of 100% on all three benchmark databases, a recall of 83.33%, and a F1‐measure of 90.91 on the CASIA‐Iris‐Interval.v3 dataset.

COVID-19 Detection from Computed Tomography Images Using Slice Processing Techniques and a Modified Xception Classifier.

This paper extends our previous method for COVID-19 diagnosis, proposing an enhanced solution for detecting COVID-19 from computed tomography (CT) images using a lean transfer learning-based model. To decrease model misclassifications, two key steps of image processing were employed. Firstly, the uppermost and lowermost slices were removed, preserving sixty percent of each patient's slices. Secondly, all slices underwent manual cropping to emphasize the lung areas. Subsequently, resized CT scans (224 × 224) were input into an Xception transfer learning model with a modified output. Both Xception's architecture and pretrained weights were leveraged in the method. A big and rigorously annotated database of CT images was used to verify the method. The number of patients/subjects in the dataset is more than 5000, and the number and shape of the slices in each CT scan varies greatly. Verification was made both on the validation partition and on the test partition of unseen images. Results on the COV19-CT database showcased not only improvement from our previous solution and the baseline but also comparable performance to the highest-achieving methods on the same dataset. Further validation studies could explore the scalability and adaptability of the developed methodologies across diverse healthcare settings and patient populations. Additionally, investigating the integration of advanced image processing techniques, such as automated region of interest detection and segmentation algorithms, could enhance the efficiency and accuracy of COVID-19 diagnosis.

Windows 11 and the dawn of the TPM - a forensically sound way to beat it

ABSTRACT As technology evolves so do challenges faced by the digital forensic examiner. An increasingly frequent obstacle appearing now is the BitLocker encryption in conjunction with the Trusted Platform Module (TPM). The roll out of Windows 11 made having an initialised TPM (2.0) a mandatory prerequisite before being able to install Windows 11. Tackling the TPM is going to be one of the major issues encountered by the digital forensic computer examiner in the future as Windows 10 support ends in 2025 (Microsoft, 2024). This paper describes a method for accessing the BitLocker protected partition of a windows computer in a short time using minimal equipment in a forensically sound manner. As a result BitLocker encrypted partitions of physical images can be decrypted using recovery keys obtained via compliance or brute force of the users password or pin.

A Bio-Inspired Visual Perception Transformer for Cross-Domain Semantic Segmentation of High-Resolution Remote Sensing Images

Pixel-level classification of very-high-resolution images is a crucial yet challenging task in remote sensing. While transformers have demonstrated effectiveness in capturing dependencies, their tendency to partition images into patches may restrict their applicability to highly detailed remote sensing images. To extract latent contextual semantic information from high-resolution remote sensing images, we proposed a gaze–saccade transformer (GSV-Trans) with visual perceptual attention. GSV-Trans incorporates a visual perceptual attention (VPA) mechanism that dynamically allocates computational resources based on the semantic complexity of the image. The VPA mechanism includes both gaze attention and eye movement attention, enabling the model to focus on the most critical parts of the image and acquire competitive semantic information. Additionally, to capture contextual semantic information across different levels in the image, we designed an inter-layer short-term visual memory module with bidirectional affinity propagation to guide attention allocation. Furthermore, we introduced a dual-branch pseudo-label module (DBPL) that imposes pixel-level and category-level semantic constraints on both gaze and saccade branches. DBPL encourages the model to extract domain-invariant features and align semantic information across different domains in the feature space. Extensive experiments on multiple pixel-level classification benchmarks confirm the effectiveness and superiority of our method over the state of the art.

Dynamic data hiding capacity enhancement for the Hybrid Near Maximum Histogram image steganography based on Multi-Pixel-Pair approach

AbstractIncreasing data hiding capacity and making it difficult to detect presence of any confidential data in stego images are the key objectives in contemporary image steganography research ever-improving the embedding efficiency. With regard to these crucial and challenging points, a new Multi-Pixel-Pair (MPP)-based data hiding approach is proposed in this paper. It can dynamically increase data embedding capacity of the classical Hybrid Near Maximum Histogram (HNMH) image steganography method while well-maintaining the embedding efficiency. In the proposed MPP approach, the peak value as a reference point in the histogram distribution of a cover image is obtained, and accordingly the pixel-pairs of interest where secret data is to be embedded are determined. Then, the pixels of the cover image are scanned sequentially and data hiding is performed on the relevant pixels by using the Least Significant Bit (LSB) method. In an extensive experimental study of the proposed MPP approach, it is shown that the classical HNMH data hiding capacity is dynamically improved 4.74 to 37.48 times while the Peak Signal to Noise Ratio (PSNR) decreases between 6.62 and 13.75 dB, implying both a reasonable trade-off and 7.61% enhanced embedding efficiency performance. Moreover, using the well-known cover image partitioning technique, offering significant improvements in image steganography, and the proposed MPP approach together, can further extend the data hiding capacity about 7.05%.

A Comprehensive Review and New Taxonomy on Superpixel Segmentation

Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications, since it allows for reducing the workload, removing redundant information, and preserving regions with meaningful features. Due to the rapid progress in this area, the literature fails to catch up on more recent works among the compared ones and to categorize the methods according to all existing strategies. This work fills this gap by presenting a comprehensive review with a new taxonomy for superpixel segmentation, in which methods are classified according to their processing steps and processing levels of image features. We revisit the recent and popular literature according to our taxonomy and evaluate 23 strategies and a grid segmentation baseline based on nine criteria: connectivity, compactness, delineation, control over the number of superpixels, color homogeneity, robustness, running time, stability, and visual quality. Our experiments show the trends of each approach in superpixel segmentation and discuss individual trade-offs. Finally, we provide a new benchmark for superpixel assessment, available at https://github.com/IMScience-PPGINF-PucMinas/superpixel-benchmark .

Image Processing Technique on Identification of Leaf Types and Detection of Diseases Portion on Tomato Leaves

This study presents novel techniques for leaf type identification, employing color histogram and edge histogram approaches. A color histogram serves as a model to represent color through intensity values, while each image is associated with a descriptive caption. Signatures, encompassing shape, color, and texture, provide a basis for comparing images. The edge histogram, delineating the distribution of five edge types in localized sub-images, further enhances the identification process. To address disease detection on tomato leaves, a color-based segmentation method utilizing the k-means clustering technique is proposed. This iterative approach partitions images into k clusters, facilitating the identification of diseases affecting tomato plants. Beyond environmental factors like rain and temperature, crop diseases emerge as primary influencers on production quality and crop yield. Early detection of diseases is crucial for effective control and mitigation. Leveraging technological advancements, the paper emphasizes the potential of using images of diseased leaves for accurate disease identification. This involves feature extraction from images, which can be subsequently employed in classification algorithms or content-based image retrieval systems.

Role of Optical Coherence Tomography Angiography in Predicting Risk of Progression of Diabetic Retinopathy

Purpose: To determine the role of Optical Coherence Tomography Angiography (OCTA)in predicting risk of progression of diabetic retinopathy. Study Design: Descriptive observational study. Place and Duration of Study: Jinnah Post graduate Medical Center, Karachi, from June 2022 to June 2023. Methods: Patients with type 1 or 2 diabetes were included. Base line investigations were done including Central subfield thickness and OCTA at first visit. Second visit was conducted at 6th month and patients were followed for 24 months.OCT images of poor quality, motion artifact, inaccurate partition of tissue layers and blurry images were excluded. Results: Among 97 enrolled patients, 88 cases finished the complete 24-months follow up. Out of 88 patients, 16 (18.18%) patients showed progression of diabetic retinopathy (DR), 9 (10.22%) patients developed DME, two showed both DR and DME .In univariate analysis, greater FAZ area, reduced FAZ circularity, Fractal dimension (FD) and vessel density (VD) of the deep capillary plexus (DCP) were significantly related to the advancement in DR. Among these, FAZ area, VD, and FD remained significant in the multivariate analysis. Whereas, only decreased VD and FD of superficial capillary plexus (SCP) were significantly related to advancement in DR and DME. Conclusion: Changes in OCTA parameters is significantly associated with progression of diabetic ocular complications including diabetic retinopathy and diabetic macular edema. High risk subjects can be identified by this method for more rigorous treatment.

A fully Bayesian approach for comprehensive mapping of magnitude and phase brain activation in complex-valued fMRI data

Functional magnetic resonance imaging (fMRI) plays a crucial role in neuroimaging, enabling the exploration of brain activity through complex-valued signals. These signals, composed of magnitude and phase, offer a rich source of information for understanding brain functions. Traditional fMRI analyses have largely focused on magnitude information, often overlooking the potential insights offered by phase data. In this paper, we propose a novel fully Bayesian model designed for analyzing single-subject complex-valued fMRI (cv-fMRI) data. Our model, which we refer to as the CV-M&P model, is distinctive in its comprehensive utilization of both magnitude and phase information in fMRI signals, allowing for independent prediction of different types of activation maps. We incorporate Gaussian Markov random fields (GMRFs) to capture spatial correlations within the data, and employ image partitioning and parallel computation to enhance computational efficiency. Our model is rigorously tested through simulation studies, and then applied to a real dataset from a unilateral finger-tapping experiment. The results demonstrate the model's effectiveness in accurately identifying brain regions activated in response to specific tasks, distinguishing between magnitude and phase activation.

Transformer-Based Selective Super-resolution for Efficient Image Refinement

Conventional super-resolution methods suffer from two drawbacks: substantial computational cost in upscaling an entire large image, and the introduction of extraneous or potentially detrimental information for downstream computer vision tasks during the refinement of the background. To solve these issues, we propose a novel transformer-based algorithm, Selective Super-Resolution (SSR), which partitions images into non-overlapping tiles, selects tiles of interest at various scales with a pyramid architecture, and exclusively reconstructs these selected tiles with deep features. Experimental results on three datasets demonstrate the efficiency and robust performance of our approach for super-resolution. Compared to the state-of-the-art methods, the FID score is reduced from 26.78 to 10.41 with 40% reduction in computation cost for the BDD100K dataset.

Assessing Hierarchies by Their Consistent Segmentations

AbstractCurrent approaches to generic segmentation start by creating a hierarchy of nested image partitions and then specifying a segmentation from it. Our first contribution is to describe several ways, most of them new, for specifying segmentations using the hierarchy elements. Then, we consider the best hierarchy-induced segmentation specified by a limited number of hierarchy elements. We focus on a common quality measure for binary segmentations, the Jaccard index (also known as IoU). Optimizing the Jaccard index is highly nontrivial, and yet we propose an efficient approach for doing exactly that. This way we get algorithm-independent upper bounds on the quality of any segmentation created from the hierarchy. We found that the obtainable segmentation quality varies significantly depending on the way that the segments are specified by the hierarchy elements, and that representing a segmentation with only a few hierarchy elements is often possible.

Sizing mudsnails: Applying superpixels to scale growth detection under ocean warming

Abstract The expansion of scientific image data holds great promise to quantify individuals, size distributions and traits. Computer vision tools are especially powerful to automate data mining of images and thus have been applied widely across studies in aquatic and terrestrial ecology. Yet marine benthic communities, especially infauna, remain understudied despite their dominance of marine biomass, biodiversity and playing critical roles in ecosystem functioning. Here, we disaggregated infauna from sediment cores taken throughout the spring transition (April–June) from a near‐natural mesocosm setup under experimental warming (Ambient, +1.5°C, +3.0°C). Numerically abundant mudsnails were imaged in batches under stereomicroscopy, from which we automatically counted and sized individuals using a superpixel‐based segmentation algorithm. Our segmentation approach was based on clustering superpixels, which naturally partition images by low‐level properties (e.g., colour, shape and edges) and allow instance‐based segmentation to extract all individuals from each image. We demonstrate high accuracy and precision for counting and sizing individuals, through a procedure that is robust to the number of individuals per image (5–65) and to size ranges spanning an order of magnitude (<750 μm to 7.4 mm). The segmentation routine provided at least a fivefold increase in efficiency compared with manual measurements. Scaling this approach to a larger dataset tallied >40k individuals and revealed overall growth in response to springtime warming. We illustrate that image processing and segmentation workflows can be built upon existing open‐access R packages, underlining the potential for wider adoption of computer vision tools among ecologists. The image‐based approach also generated reproducible data products that, alongside our scripts, we have made freely available. This work reinforces the need for next‐generation monitoring of benthic communities, especially infauna, which can display differential responses to average warming.

An image partition security-sharing mechanism based on blockchain and chaotic encryption.

To ensure optimal use of images while preserving privacy, it is necessary to partition the shared image into public and private areas, with public areas being openly accessible and private areas being shared in a controlled and privacy-preserving manner. Current works only facilitate image-level sharing and use common cryptographic algorithms. To ensure efficient, controlled, and privacy-preserving image sharing at the area level, this paper proposes an image partition security-sharing mechanism based on blockchain and chaotic encryption, which mainly includes a fine-grained access control method based on Attribute-Based Access Control (ABAC) and an image-specific chaotic encryption scheme. The proposed fine-grained access control method employs smart contracts based on the ABAC model to achieve automatic access control for private areas. It employs a Cuckoo filter-based transaction retrieval technique to enhance the efficiency of smart contracts in retrieving security attributes and policies on the blockchain. The proposed chaotic encryption scheme generates keys based on the private areas' security attributes, largely reducing the number of keys required. It also provides efficient encryption with vector operation acceleration. The security analysis and performance evaluation were conducted comprehensively. The results show that the proposed mechanism has lower time overhead than current works as the number of images increases.

Transformer-Based Visual Segmentation: A Survey.

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical analysis. Over the past decade, deep learning-based methods have made remarkable strides in this area. Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision processing tasks. Specifically, vision transformers offer robust, unified, and even simpler solutions for various segmentation tasks. This survey provides a thorough overview of transformer-based visual segmentation, summarizing recent advancements. We first review the background, encompassing problem definitions, datasets, and prior convolutional methods. Next, we summarize a meta-architecture that unifies all recent transformer-based approaches. Based on this meta-architecture, we examine various method designs, including modifications to the meta-architecture and associated applications. We also present several specific subfields, including 3D point cloud segmentation, foundation model tuning, domain-aware segmentation, efficient segmentation, and medical segmentation. Additionally, we compile and re-evaluate the reviewed methods on several well-established datasets. Finally, we identify open challenges in this field and propose directions for future research. The project page can be found at https://github.com/lxtGH/Awesome-Segmentation-With-Transformer.

A Multi-Point Geostatistical Modeling Method Based on 2D Training Image Partition Simulation

In this paper, a multi-point geostatistical (MPS) method based on variational function partition simulation is proposed to solve the key problem of MPS 3D modeling using 2D training images. The new method uses the FILTERSIM algorithm framework, and the variational function is used to construct simulation partitions and training image sequences, and only a small number of training images close to the unknown nodes are used in the partition simulation to participate in the MPS simulation. To enhance the reliability, a new covariance filter is also designed to capture the diverse features of the training patterns and allow the filter to downsize the training patterns from any direction; in addition, an information entropy method is used to reconstruct the whole 3D space by selecting the global optimal solution from several locally similar training patterns. The stability and applicability of the new method in complex geological modeling are demonstrated by analyzing the parameter sensitivity and algorithm performance. A geological model of a uranium deposit is simulated to test the pumping of five reserved drill holes, and the results show that the accuracy of the simulation results of the new method is improved by 11.36% compared with the traditional MPS method.

Learning Semantics-Consistent Stripes With Self-Refinement for Person Re-Identification.

Aligning human parts automatically is one of the most challenging problems for person re-identification (re-ID). Recently, the stripe-based methods, which equally partition the person images into the fixed stripes for aligned representation learning, have achieved great success. However, the stripes with fixed height and position cannot well handle the misalignment problems caused by inaccurate detection and occlusion and may introduce much background noise. In this article, we aim at learning adaptive stripes with foreground refinement to achieve pixel-level part alignment by only using person identity labels for person re-ID and make two contributions. 1) A semantics-consistent stripe learning method (SCS). Given an image, SCS partitions it into adaptive horizontal stripes and each stripe is corresponding to a specific semantic part. Specifically, SCS iterates between two processes: i) clustering the rows to human parts or background to generate the pseudo-part labels of rows and ii) learning a row classifier to partition a person image, which is supervised by the latest pseudo-labels. This iterative scheme guarantees the accuracy of the learned image partition. 2) A self-refinement method (SCS+) to remove the background noise in stripes. We employ the above row classifier to generate the probabilities of pixels belonging to human parts (foreground) or background, which is called the class activation map (CAM). Only the most confident areas from the CAM are assigned with foreground/background labels to guide the human part refinement. Finally, by intersecting the semantics-consistent stripes with the foreground areas, SCS+ locates the human parts at pixel-level, obtaining a more robust part-aligned representation. Extensive experiments validate that SCS+ sets the new state-of-the-art performance on three widely used datasets including Market-1501, DukeMTMC-reID, and CUHK03-NP.

The partitioning ensemble control chart for on-line monitoring of high-dimensional image-based quality characteristics

The widespread implementation of computer technology has led to an increased use of Machine Vision Systems (MVS) for quality control in advanced manufacturing industries. The application of Statistical Process Control (SPC) techniques, especially control charts, is one of the most important and effective ways for fault detection in this field. Several statistical control charts have been extended to monitor images in the framework of MVS where the major aim is to improve the on-line detection ability, which is equivalent to avoid production of nonconforming products. In various industrial and non-industrial applications, control charts have been shown to be better able to detect anomalies in the underlying process(es) by integrating machine and ensemble learning techniques. However, in the field of image monitoring, approaches based on intelligent techniques have rarely been proposed. To bridge this gap and to improve the detection ability of control charts in monitoring image-based quality characteristics, this paper presents a novel control chart that combines machine learning, ensemble learning and image partitioning. In order to reach the maximum performance in Phase II SPC applications, specific designing and parameter tuning procedures are provided. The superiority of the proposed Partitioning Ensemble Control Chart (PECC) is verified by comparative analysis including conventional monitoring schemes by means of extensive simulations, in which different fault sizes and fault locations are applied to the images. Finally, a real MVS for quality control of O-rings is discussed to illustrate the practical application of the PECC.

Computer-aided recognition and assessment of a porous bioelastomer in ultrasound images for regenerative medicine applications

It is difficult to use a single edge operator in image processing to extract continuous and accurate contours of a porous bioelastomer due to the fuzzy boundary and complex background in ultrasound images. To solve this problem, this paper proposes a joint algorithm for bioelastomer contour detection and a texture feature extraction method for monitoring the degradation performance of bioelastomers. First, the mean-shift clustering method is utilized to obtain the clustering feature information of bioelastomers and native tissue from manually segmented images, and this information is used as the initial information in the image binarization algorithm for image partitioning. Second, Otsu's thresholding method and mathematical morphology are applied in the process of image binarization. Finally, the Canny edge detector is employed to extract the complete bioelastomers contour from the binary image. To verify the robustness of the proposed joint algorithm, the results using the proposed joint algorithm, where mean-shift clustering is replaced with k-means clustering are also obtained. The proposed joint algorithm based on mean-shift clustering outperforms the joint algorithm based on k-means clustering, as well as algorithms that directly apply the Canny, Sobel and Laplacian methods. Texture feature extraction is based on the computer-aided recognition of bioelastomers. The region of interest (ROI) is set in the scaffold region, and the first-order statistical features and second-order statistical features of the greyscale values of the ROI are extracted and analysed. The proposed joint algorithm can not only extract ideal bioelastomers contours from ultrasound images but also provide valuable feedback on the degradation behaviour of bioelastomers at implant sites.