Traditional Segmentation Approaches Research Articles

Stroke‐Seg: A deep learning‐based framework for chinese stroke segmentation

AbstractChinese stroke segmentation is a crucial and challenging task for various downstream applications such as font generation, aesthetic evaluation etc. Conventional semantic segmentation techniques typically face difficulties in accurately segmenting strokes, as intersection regions in Chinese characters can belong to multiple strokes simultaneously, and these approaches often lack a holistic understanding of character composition. This paper proposes a character stroke segmentation framework named Stroke‐Seg that integrates with various semantic segmentation architectures, demonstrating adaptability to different backbone networks to tackle the above tasks. A multi‐label output strategy is proposed to effectively classify strokes in intersection areas, overcoming the limitations of traditional semantic segmentation approaches. Additionally, a prior knowledge vector is incorporated into the input layer to provide character‐specific information on stroke composition, enhancing the ability of the framework to precisely identify and segment strokes. The effectiveness of the proposed framework is demonstrated through evaluations of a comprehensive dataset (brush calligraphy stroke segmentation dataset). Evaluations show that the proposed framework significantly improves the capability of semantic segmentation networks, achieving a remarkable improvement of up to 19.9% in the true stroke rate, compared to traditional stroke segmentation techniques. The Stroke‐Seg framework integrated with TransUNet demonstrates its high performance with an impressive 98.2% true stroke rate. Furthermore, the proposed framework combined with FCN still achieves good performance while consuming the least amount of computational resources and memory, demonstrating its potential for lightweight design.

Deep spectral improvement for unsupervised image instance segmentation.

Recently, there has been growing interest in deep spectral methods for image localization and segmentation, influenced by traditional spectral segmentation approaches. These methods reframe the image decomposition process as a graph partitioning task by extracting features using self-supervised learning and utilizing the Laplacian of the affinity matrix to obtain eigensegments. However, instance segmentation has received less attention than other tasks within the context of deep spectral methods. This paper addresses that not all channels of the feature map extracted from a self-supervised backbone contain sufficient information for instance segmentation purposes. Some channels are noisy and hinder the accuracy of the task. To overcome this issue, this paper proposes two channel reduction modules, Noise Channel Reduction (NCR) and Deviation-based Channel Reduction (DCR). The NCR retains channels with lower entropy, as they are less likely to be noisy, while DCR prunes channels with low standard deviation, as they lack sufficient information for effective instance segmentation. Furthermore, the paper demonstrates that the dot product, commonly used in deep spectral methods, is not suitable for instance segmentation due to its sensitivity to feature map values, potentially leading to incorrect instance segments. A novel similarity metric called Bray-curtis over Chebyshev (BoC) is proposed to address this issue. This metric considers the distribution of features in addition to their values, providing a more robust similarity measure for instance segmentation. Quantitative and qualitative results on the Youtube-VIS 2019 and OVIS datasets highlight the improvements achieved by the proposed channel reduction methods and using BoC instead of the conventional dot product for creating the affinity matrix. These improvements regarding mean Intersection over Union (mIoU) and extracted instance segments are observed, demonstrating enhanced instance segmentation performance. The code is available on: https://github.com/farnooshar/SpecUnIIS.

Accurate MRI-Based Brain Tumor Diagnosis: Integrating Segmentation and Deep Learning Approaches

Magnetic Resonance Imaging (MRI) is vital in diagnosing brain tumours, offering crucial insights into tumour morphology and precise localisation. Despite its pivotal role, accurately classifying brain tumours from MRI scans is inherently complex due to their heterogeneous characteristics. This study presents a novel integration of advanced segmentation methods with deep learning ensemble algorithms to enhance the classification accuracy of MRI-based brain tumour diagnosis. We conduct a thorough review of both traditional segmentation approaches and contemporary advancements in region-based and machine learning-driven segmentation techniques. This paper explores the utility of deep learning ensemble algorithms, capitalising on the diversity of model architectures to augment tumour classification accuracy and robustness. Through the synergistic amalgamation of sophisticated segmentation techniques and ensemble learning strategies, this research addresses the shortcomings of traditional methodologies, thereby facilitating more precise and efficient brain tumour classification.

High-performance laser speckle contrast image vascular segmentation without delicate pseudo-label reliance

Laser speckle contrast imaging (LSCI) is a noninvasive, label-free technique that allows real-time investigation of the microcirculation situation of biological tissue. High-quality microvascular segmentation is critical for analyzing and evaluating vascular morphology and blood flow dynamics. However, achieving high-quality vessel segmentation has always been a challenge due to the cost and complexity of label data acquisition and the irregular vascular morphology. In addition, supervised learning methods heavily rely on high-quality labels for accurate segmentation results, which often necessitate extensive labeling efforts. Here, we propose a novel approach LSWDP for high-performance real-time vessel segmentation that utilizes low-quality pseudo-labels for nonmatched training without relying on a substantial number of intricate labels and image pairing. Furthermore, we demonstrate that our method is more robust and effective in mitigating performance degradation than traditional segmentation approaches on diverse style data sets, even when confronted with unfamiliar data. Importantly, the dice similarity coefficient exceeded 85% in a rat experiment. Our study has the potential to efficiently segment and evaluate blood vessels in both normal and disease situations. This would greatly benefit future research in life and medicine.

Exploring the Use of Cluster Analysis in Market Segmentation for Targeted Advertising

In the rapidly evolving field of digital marketing, precise targeting and segmentation have become essential for optimizing advertising efforts, yet traditional methods often struggle to adequately address the dynamic nature of consumer behaviors. This study delves into the efficacy of cluster analysis as a robust tool in market segmentation, particularly aimed at enhancing the precision of targeted advertising campaigns. By employing a case study approach, the research meticulously analyzes real-world advertising campaigns across various industries, utilizing cluster analysis to segment the market and employing qualitative data analysis to evaluate the outcomes in terms of engagement and conversion improvements. The results indicate that cluster analysis not only facilitates a deeper understanding of market segments but also leads to more tailored and effective advertising strategies. Companies implementing this method reported significant improvements in campaign performance, with higher engagement and conversion rates compared to traditional segmentation approaches. This study underscores the advantages of employing advanced statistical methods like cluster analysis in market segmentation, highlighting its potential to transform targeted advertising by enabling advertisers to adapt more swiftly and effectively to market dynamics. The implications for practice suggest that businesses should integrate cluster analysis into their marketing strategies to gain a competitive edge through enhanced customer insights and optimized advertising effectiveness, thereby contributing valuable empirical evidence to the existing literature.

An overview of statistical and neural-based line segmentation methods for offline handwriting recognition task

The object of the research is the line segmentation task. To recognize the handwritten text from the documents in image format offline handwriting recognition technology is used. The text recognizer module accepts input as separate lines, so one of the important preprocessing steps is the detection and splitting of all handwritten text into distinct lines. In this paper, the handwritten text line segmentation task, its requirements, problems, and challenges are examined. Two main approaches for this task that are used in modern recognition systems are reviewed. These approaches are statistical projection-based methods and neural-based methods. Multiple works and research papers for each type of approach are reviewed analyzing their strengths and weaknesses considering the described tasks, constraints, and input data peculiarities. Overall acquired results are formed in a single table for comparison. Based on the latest works that utilize deep neural networks the new possibilities of using these methods in recognition systems are described that were unavailable with traditional statistical segmentation approaches. The constructive conclusions are made based on the review, describing the main pros and cons of these two approaches for the line segmentation task. These results can be further used for the correct selection of suitable methods in handwriting recognition systems to improve their performance and quality, and for further research in this area.

An overview of research results and applications in the field of semi-supervised semantic segmentation

Traditional segmentation approaches, supervised deep learning methods, and semi-supervised deep learning methods have all found widespread use as the field of semi-supervised semantic segmentation has advanced. These methods have developed and progressed over time, opening up novel avenues of research in the field of image segmentation and giving potent resources for tackling difficult practical issues. These developments have deepened our understanding of image segmentation and provided flexible and efficient solutions to challenges in practical applications, ranging from classical traditional approaches to supervised methods based on deep learning, and beyond to semi-supervised methods that leverage both labeled and unlabeled data. Focusing on their specialized applications in medical and remote sensing image processing, this paper presents a complete overview of the development status of these methods. This study's image segmentation solutions can help tackle actual-world issues where annotated data is rare or expensive to some extent.

Vectorize Me! A Proposed Machine Learning Approach for Segmenting the Multi-optional Tourist

Contemporary consumer behavior is characterized by its multidimensionality and complexity, which, at the same time, pushes traditional segmentation approaches to their limits. In response, this methodological study proposes a multistage machine learning-based segmentation process using semiotic-semantic community detection. This innovative method was conducted exemplarily and evaluated on a representative sample of 1,101 German travelers. The main contribution of this study lies in the novel use of word vectors, which result from assigning a semiotic meaning to travel-type images. Thus, high-dimensional data could be used during the segmentation process, overcoming several classical segmentation problems. By using semantic similarities, tourists could be grouped and represented in their multidimensionality. From a theoretical perspective, this study was inspired by postmodern tourism practices in order to better understand the (oftentimes) hybrid and multilayered behaviors of tourists. To make this innovative approach reproducible, recommendations for implementation and all necessary data have been provided.

Reliable genotyping of recombinant genomes using a robust hidden Markov model.

Meiotic recombination is an essential mechanism during sexual reproduction and includes the exchange of chromosome segments between homologous chromosomes. New allelic combinations are transmitted to the new generation, introducing novel genetic variation in the offspring genomes. With the improvement of high-throughput whole-genome sequencing technologies, large numbers of recombinant individuals can now be sequenced with low sequencing depth at low costs, necessitating computational methods for reconstructing their haplotypes. The main challenge is the uncertainty in haplotype calling that arises from the low information content of a single genomic position. Straightforward sliding window-based approaches are difficult to tune and fail to place recombination breakpoints precisely. Hidden Markov model (HMM)-based approaches, on the other hand, tend to over-segment the genome. Here, we present RTIGER, an HMM-based model that exploits in a mathematically precise way the fact that true chromosome segments typically have a certain minimum length. We further separate the task of identifying the correct haplotype sequence from the accurate placement of haplotype borders, thereby maximizing the accuracy of border positions. By comparing segmentations based on simulated data with known underlying haplotypes, we highlight the reasons for RTIGER outperforming traditional segmentation approaches. We then analyze the meiotic recombination pattern of segregants of 2 Arabidopsis (Arabidopsis thaliana) accessions and a previously described hyper-recombining mutant. RTIGER is available as an R package with an efficient Julia implementation of the core algorithm.

Deetect: A Deep Learning-Based Image Analysis Tool for Quantification of Adherent Cell Populations on Oxygenator Membranes after Extracorporeal Membrane Oxygenation Therapy.

The strong interaction of blood with the foreign surface of membrane oxygenators during ECMO therapy leads to adhesion of immune cells on the oxygenator membranes, which can be visualized in the form of image sequences using confocal laser scanning microscopy. The segmentation and quantification of these image sequences is a demanding task, but it is essential to understanding the significance of adhering cells during extracorporeal circulation. The aim of this work was to develop and test a deep learning-supported image processing tool (Deetect), suitable for the analysis of confocal image sequences of cell deposits on oxygenator membranes at certain predilection sites. Deetect was tested using confocal image sequences of stained (DAPI) blood cells that adhered to specific predilection sites (junctional warps and hollow fibers) of a phosphorylcholine-coated polymethylpentene membrane oxygenator after patient support (>24 h). Deetect comprises various functions to overcome difficulties that occur during quantification (segmentation, elimination of artifacts). To evaluate Deetects performance, images were counted and segmented manually as a reference and compared with the analysis by a traditional segmentation approach in Fiji and the newly developed tool. Deetect outperformed conventional segmentation in clustered areas. In sections where cell boundaries were difficult to distinguish visually, previously defined post-processing steps of Deetect were applied, resulting in a more objective approach for the resolution of these areas.

Patch-based CNN for corneal segmentation of AS-OCT images: Effect of the number of classes and image quality upon performance

Anterior segment optical coherence tomography (AS-OCT) is a fundamental ophthalmic imaging technique. AS-OCT images can be examined by experts and segmented to provide quantitative metrics that inform clinical decision making. Manual segmentation of these images is time-consuming and subjective, encouraging software developers in the field to automate segmentation procedures. Traditional programing segmentation approaches are being replaced by deep learning methods, which have shown state-of-the-art performance in AS-OCT image analysis. In this study, a method based on patch-based convolutional neural networks (CNN) was used to segment the three main boundaries of the cornea: the epithelium, Bowman's layer, and the endothelium. To assess the effect of the number of classes on performance, the model was designed as a patch-based boundary classifier using 4 and 8 classes. The effect of image quality was also assessed using different data distributions during the training process. While the Dice coefficient and probability revealed greater precision for the 8 class models, the boundary error metric indicated comparable performance. Additionally, for 8 class models, the image quality test had only a small negative effect on performance, which may be an indication of the robustness of the model and could also suggest that the data augmentation methods did not show significant improvement. These findings contribute to the development of automatic segmentation techniques for AS-OCT images, since patch-based methods have been largely unexplored in favor of other deep learning techniques. The overall performance of the proposed method is comparable to other well-established segmentation methods.

Automated masks generation for coffee and apple leaf infected with single or multiple diseases-based color analysis approaches

Identification of plant disease is affected by many factors. The scarcity of rare or mild symptoms, the sensitivity of segmentation is influenced by light and shadow of images capturing conditions, and symptoms characteristics are represented by multiple lesions of varied colours on the same leaf at different stages of infection. Traditional approaches face several problems: contrast handling leads to mild symptoms being undetected and deals with edges results in curved surfaces and veins being considered new regions of interest. Thresholding of segmentation restricts it to a specific range of values, which prevents it from dealing with an entire area (healthy, injured, or noise). Deep learning approaches also face problems of dealing with imbalanced datasets. The existence of overlapped symptoms on the same leaf sample is rare. Most deep models detect a single type of lesion at a single time. Masks with a single type of infection are used for training these models that lead to misclassification. Manual annotation of symptoms is considered time-consuming. Therefore, the proposed framework in this study is an attempt to overcome certain drawbacks of traditional segmentation approaches to generate masks for deep disease classification models. The main objective is to label datasets based on a semi-automated segmentation of leaves and disordered regions. There is no need to manage contrast or apply filters that keep lesion characteristics unchanged. As a result, every pixel in the predetermined lesions is selected accurately. The approach is applied to three different datasets with single and multiple infections. The obtained overall precision is 90%. The average intersection over the union of the injured regions is 0.83. The brown and the dark brown lesions are more accurately segmented than the yellow lesions.

Assessing tap water awareness: The development of an empirically-based framework.

Despite the often emphasized importance of water awareness, and notwithstanding the fact that calls for increasing public awareness are becoming commonplace, most studies do not define the concept, let alone operationalise it into measurable units. This is, however, essential to measure and evaluate efforts related to water awareness such as public campaigns, customer communication and behavioural interventions. To address this gap, we conceptualise, operationalise and assess tap water awareness, hereby differentiating between cognitive awareness (head), affectional awareness (heart), and behavioural awareness (hands). In parallel, we also differentiate between tap water quality, quantity and system. By building on a variety of contemporary conceptual insights in literature and a series of expert interviews, an assessment framework is developed. A cohesive set of nine awareness components are identified and operationalised into a set of tangible questions which are put to the test in a large-scale online survey (n = 1003) in the Netherlands, applying both a traditional and modern segmentation approach based on four types of perspectives (‘quality & health concerned’, ‘aware & committed’, ‘egalitarian & solidary’, and ‘down to earth & confident’). Based on the analysis of the results of the first empirical application of our tap water awareness assessment framework, we conclude that—with a score 53.5 points out of 100—tap water awareness in the Netherlands shows ample room for improvement. Interestingly, most significant variations in awareness are generally not related to sociodemographic factors but rather apply to the four customer perspectives on drinking water that are based on people’s subjective views and preferences.

A Brief Review on Brain Tumor Segmentation and Detection Algorithms with Issues and Challenges

Computer vision techniques and development of computer-aided tools are evolving as the areas of research for automatic segmentation of brain tumors. Some of these techniques showed good results but there is no winning technique as these approaches have often not used practically in hospitals. In these days, research on medical healthcare system [1] is an emerging area and main focused on the designing of an efficient segmentation approach with concept of Artificial Intelligence (AI) techniques for appropriate region and fast segmentation purpose. There are a lots of clustering as well as traditional segmentation approaches are available for medical images, but most of them are depended on the data types. In this paper, we presented a brief review on clustering-based medical image segmentation with their challenging factors faced by researchers [2]. Due to high success rate of AI, Deep Learning (DL) algorithms, there has been a considerable amount of brain tumor segmentation works are aimed by researcher and try to solve the exiting challenges. In this survey, various type of brain tumor segmentation and detection system are analyzed to find out the exact tumor location and faced issued by the researchers. In Addition, some challenging factors are also analyzed with various algorithms of segmentation such DL, K-means clustering, Optimization and traditional approaches.

Factors Affecting Customer Analytics: Evidence from Three Retail Cases

The abundance of customer behavioral data alters the design and application of customer analytics systems and approaches. Segmentation is a common customer analytics practice, but researchers highlight that traditional segmentation approaches are not enough. We coin the term “visit segmentation” and devise a visit segmentation approach. When designing or applying a new information system or approach, it is important to consider factors related to the input data, the application context, the users, and all the relevant requirements. Considering the literature, this paper identifies such factors that affect customer analytics approaches and systems. We explore how these factors affect segmentation through applying our segmentation approach to three heterogeneous retailers, e.g., the products’ variety a shopper purchases in each visit seems to be crucial to the segmentation. The more attention data analysts and designers pay to these factors, the more reliable segmentation results they will get and, thus, improved retail decisions are expected.

Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network

Pixel-level analysis of blood images plays a pivotal role in diagnosing blood-related diseases, especially Anaemia. These analyses mainly rely on an accurate diagnosis of morphological deformities like shape, size, and precise pixel counting. In traditional segmentation approaches, instance or object-based approaches have been adopted that are not feasible for pixel-level analysis. The convolutional neural network (CNN) model required a large dataset with detailed pixel-level information for the semantic segmentation of red blood cells in the deep learning domain. In current research work, we address these problems by proposing a multi-level deep convolutional encoder-decoder network along with two state-of-the-art healthy and Anaemic-RBC datasets. The proposed multi-level CNN model preserved pixel-level semantic information extracted in one layer and then passed to the next layer to choose relevant features. This phenomenon helps to precise pixel-level counting of healthy and anaemic-RBC elements along with morphological analysis. For experimental purposes, we proposed two state-of-the-art RBC datasets, i.e., Healthy-RBCs and Anaemic-RBCs dataset. Each dataset contains 1000 images, ground truth masks, relevant, complete blood count (CBC), and morphology reports for performance evaluation. The proposed model results were evaluated using crossmatch analysis with ground truth mask by finding IoU, individual training, validation, testing accuracies, and global accuracies using a 05-fold training procedure. This model got training, validation, and testing accuracies as 0.9856, 0.9760, and 0.9720 on the Healthy-RBC dataset and 0.9736, 0.9696, and 0.9591 on an Anaemic-RBC dataset. The IoU and BFScore of the proposed model were 0.9311, 0.9138, and 0.9032, 0.8978 on healthy and anaemic datasets, respectively.

Long-Distance Person Travel: A Cluster-Based Approach

Many long-distance person trips (LDPT) modelling efforts fail to accurately represent trips using traditional segmentation approaches. Thus, a clustering approach was used herein to segment an intra-provincial trips data set. The trips’ segments found were short economical getaways (36%), same-day shopping (16%), personal business (14%), visiting friends/relatives (10%), business/casino trips (10%), young adults playing team sports (6%), same-day trips of snow/festival loving young families with kids (3%), costly cottage/camping trips (3%), seniors with medical appointments (2%), and multiple city visitors (1%). The existence of clusters and associated activities shows what segmentation approaches modern models should follow.

Trust in Drinking Water Quality: Understanding the Role of Risk Perception and Transparency

In the context of an increasing societal demand for transparency in parallel with rapidly increasing numbers and concentrations of substances found in drinking water, this paper investigates how different drinking water customers perceive their tap water quality, and possible risks involved. Empirically, the paper draws on results from a representative survey, a series of interviews and focus groups conducted in the Netherlands, applying both a traditional and modern segmentation approach based on four types of perspectives (“aware and committed”, “down to earth and confident”, “egalitarian and solidary”, and “quality and health concerned”). Although in general it was found that people’s trust in tap water is high, certain groups are more concerned about water quality and health effects than others. It was shown that transparency and the availability of more information about water treatment and quality would contribute to increasing customer trust. It was also observed that, at least in the Netherlands, people have a larger trust in drinking water companies than in other institutions. Therefore, instead of referring to standards made by other institutions, it is recommended that water companies themselves provide information on water quality and emphasize their treatment procedures.

Understanding Deep Learning Techniques for Image Segmentation

The machine learning community has been overwhelmed by a plethora of deep learning--based approaches. Many challenging computer vision tasks, such as detection, localization, recognition, and segmentation of objects in an unconstrained environment, are being efficiently addressed by various types of deep neural networks, such as convolutional neural networks, recurrent networks, adversarial networks, and autoencoders. Although there have been plenty of analytical studies regarding the object detection or recognition domain, many new deep learning techniques have surfaced with respect to image segmentation techniques. This article approaches these various deep learning techniques of image segmentation from an analytical perspective. The main goal of this work is to provide an intuitive understanding of the major techniques that have made a significant contribution to the image segmentation domain. Starting from some of the traditional image segmentation approaches, the article progresses by describing the effect that deep learning has had on the image segmentation domain. Thereafter, most of the major segmentation algorithms have been logically categorized with paragraphs dedicated to their unique contribution. With an ample amount of intuitive explanations, the reader is expected to have an improved ability to visualize the internal dynamics of these processes.

Market segmentation and travel choice prediction in Spa hotels through TripAdvisor’s online reviews

Customer segmentation via online reviews and ratings can assist different hotels, including spa hotels, to better inform marketing strategy development and ensure optimal marketing expenditures. However, traditional market segmentation approaches are ineffective in analysing social data on account of size, different dimensions and features of online review data. Machine learning approaches can assist in developing effective hybrid algorithms to overcome data-related complications associated with online reviews. Hence, the objective of this study is to develop a method for spa hotel segmentation and travel choice prediction by applying machine learning approaches. Method evaluation is conducted through a collection of datasets from travelers’ ratings and textual reviews of spa hotels on several features in TripAdvisor. Findings confirm that the proposed hybrid machine learning methods can be implemented as an incremental recommendation agent for spa hotel/resort segmentation through effectively utilizing ‘big data’ procured from online social media contexts.