Binarization Strategies Research Articles

CBDA: Chaos-based binary dragonfly algorithm for evolutionary feature selection

The goal of feature selection in machine learning is to simultaneously maintain more classification accuracy, while reducing lager amount of attributes. In this paper, we firstly design a fitness function that achieves both objectives jointly. Then we come up with a chaos-based binary dragonfly algorithm (CBDA) that incorporates several improvements over the conventional dragonfly algorithm (DA) for developing a wrapper-based feature selection method to solve the fitness function. Specifically, the CBDA innovatively introduces three improved factors, namely the chaotic map, evolutionary population dynamics (EPD) mechanism, and binarization strategy on the basis of conventional DA to balance the exploitation and exploration capabilities of the algorithm and make it more suitable to handle the formulated problem. We conduct experiments on 24 well-known data sets from the UCI repository with three ablated versions of CBDA targeting different components of the algorithm in order to explain their contributions in CBDA and also with five established comparative algorithms in terms of fitness value, classification accuracy, CPU running time, and number of selected features. The results show that the proposed CBDA has remarkable advantages in most of the tested data sets.

ISP-IRLNet: Joint optimization of interpretable sampler and implicit regularization learning network for accerlerated MRI

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) was proposed to accelerate data acquisition and reconstruct MR images from under-sampled data in k-space. However, the traditional approaches design the sampling patterns separately from the reconstruction process, which often leads to suboptimal reconstruction performance. To address this issue, we propose a joint optimization model dubbed as ISP-IRLNet to yield optimal recovery including an interpretable sampler and a reconstructor using the implicit regularization learning network. In particular, we introduce a probabilistic distribution model of the sampling incorporated into the prior of k-space locations, which provides a robust CS-MRI sample pattern with an explicit expression. To estimate the approximating gradient in backward propagation for more stable training, we employ a differentiable binarization strategy. In addition, we unroll the ADMM optimization for solving the regularized reconstruction model to be a deep network (i.e., IRLNet) with a learnable implicit regularization sub-network to learn a regularizer or prior term implicitly. The experiments on our collected brain and public knee datasets demonstrate that our method provides an optimal sample pattern and achieves superior image reconstruction performance compared with existing methods, especially at high acceleration rates.

Enhancing medical text detection with vision-language pre-training and efficient segmentation

AbstractDetecting text within medical images presents a formidable challenge in the domain of computer vision due to the intricate nature of textual backgrounds, the dense text concentration, and the possible existence of extreme aspect ratios. This paper introduces an effective and precise text detection system tailored to address these challenges. The system incorporates an optimized segmentation module, a trainable post-processing method, and leverages a vision-language pre-training model (oCLIP). Specifically, our segmentation head integrates three essential components: the Feature Pyramid Network (FPN) module, which combines a residual structure and channel attention mechanism; the Efficient Feature Enhancement Module (EFEM); and the Multi-Scale Feature Fusion with RSEConv (MSFM-RSE), designed specifically for multi-scale feature fusion based on RSEConv. By introducing a residual structure and channel attention mechanism into the FPN module, the convolutional layers are replaced with RSEConv layers that employ a channel attention mechanism, further augmenting the representational capacity of the feature maps. The EFEM, designed as a cascaded U-shaped module, incorporates a spatial attention mechanism to introduce multi-level information, thereby enhancing segmentation performance. Subsequently, the MSFM-RSE adeptly amalgamates features from various depths and scales of the EFEM to generate comprehensive final features tailored for segmentation purposes. Additionally, a post-processing module employs a differentiable binarization strategy, allowing the segmentation network to dynamically determine the binarization threshold. Building on the system’s improvement, we introduce a vision-language pre-training model that undergoes extensive training on various visual language understanding tasks. This pre-trained model acquires detailed visual and semantic representations, further reinforcing both the accuracy and robustness in text detection when integrated with the segmentation module. The performance of our proposed model was evaluated through experiments on medical text image datasets, demonstrating excellent results. Multiple benchmark experiments validate its superior performance in comparison to existing methods. Code is available at: https://github.com/csworkcode/VLDBNet.

Harnessing Neural Networks for Enhancing Image Binarization Through Threshold Combination

Threshold-based methods are prevalent across numerous domains, with specific relevance to image binarization, which traditionally employs global and local threshold algorithms. This paper presents a novel approach to image binarization, where the capacity of neural networks is utilized not just for determining optimal thresholds, but also for combining multiple global thresholds sourced from existing binarization techniques. The primary objective of our method is to develop a robust binarization strategy capable of managing a wide array of image conditions. By integrating the strengths of various thresholding techniques, our approach aims to establish a significant connection between traditional thresholding methods and those underpinned by deep learning.

An Efficient Fuzzy based MRI Brain Tumor Segmentation and Classification

Picture division is a significant testing factor in clinical picture division. This paper portrays the division strategy comprising two stages. In the initial step, the MRI cerebrum picture is gained from the patients' information base, in that film, relics and commotion are taken out after the Binarization strategy is applied for picture division. The Binaraization works with the assistance of the Fuzzy C Means Clustering calculation, hence the calculation assumes the principle part in the framework, in this most minimal level of the weight vector, higher worth of cancer pixels, calculation speed is accomplished by the Fuzzy C Mean with vector quantization. The point of this exploration work is to give an assortment of fluffy c-implies (FCM) calculation that gives picture bunching utilizing the MRI Brain Tumor data set. The proposed calculation joins the neighborhood spatial data and dark level data in an original fluffy manner. The new calculation is called Fuzziness Confined Message C-Means (FCM2). FCM2 can defeat the drawbacks of the known fluffy c-implies calculations and simultaneously improves the grouping execution. The significant trait of FCM2 is the utilization of a fluffy neighborhood (both spatial and dark level) closeness measure, expecting to ensure clamor heartlessness and picture detail conservation. Besides, the proposed calculation Experiments performed on manufactured and true pictures show that the FCM2 calculation is powerful and proficient, giving strength to uproarious pictures.

Structural modal identification using a portable laser-and-camera measurement system

Vision-based techniques for modal analysis of full-scale civil infrastructure have been constrained by the challenge of collecting measurements of all points on a large structure using limited-resolution video devices. This paper proposes a portable, simple-to-assemble laser-and-camera (LAC) system capable of measuring multipoint displacements at a low cost. An efficient video processing flow with an improved binarization strategy for pinpointing the laser spot's center is provided to extract the displacement from the video collected by LAC devices. In addition, the laser-assisted vision-based measurement technique is implemented for structural modal identification for the first time. To evaluate the performance of LAC devices in displacement measurement and structural modal identification, an error analysis test, a measurement accuracy test, and a scaled bridge model experiment are conducted in succession. The results with different types of laser receiving panels and under variable light environments demonstrate the feasibility and application potential of the proposed LAC system and approach for structural health monitoring.

Lightweighted Hyperspectral Image Classification Network by Progressive Bi-Quantization

Convolutional neural network (CNN) has shown its powerful ability for hyperspectral image (HSI) classification, which however, is difficult to deploy on resource-limited or low-latency platforms due to its parameter and computation redundancy. Though binary neural network (BNN) has attracted attention for its extreme compressing and speeding up ability by binarizing both weights and activations, it has rarely been explored for HSI classification. In this study, we elaborately design a BNN with good performance for HSI classification task. Specifically, an adaptive gradient scale module is proposed to flexibly modify the gradient during training stage to better optimize the BNN and does not add any extra computation for inference. Furthermore, a curriculum learning-based progressive binarization strategy is utilized to improve the performance. Compared with the existing BNN works, our method can increase the HSI classification accuracy by a large margin while maintaining the compressing ratio. Abundant experiments on three datasets demonstrate the effectiveness of the proposed method.

A flexible data-driven audiological patient stratification method for deriving auditory profiles.

For characterizing the complexity of hearing deficits, it is important to consider different aspects of auditory functioning in addition to the audiogram. For this purpose, extensive test batteries have been developed aiming to cover all relevant aspects as defined by experts or model assumptions. However, as the assessment time of physicians is limited, such test batteries are often not used in clinical practice. Instead, fewer measures are used, which vary across clinics. This study aimed at proposing a flexible data-driven approach for characterizing distinct patient groups (patient stratification into auditory profiles) based on one prototypical database (N = 595) containing audiogram data, loudness scaling, speech tests, and anamnesis questions. To further maintain the applicability of the auditory profiles in clinical routine, we built random forest classification models based on a reduced set of audiological measures which are often available in clinics. Different parameterizations regarding binarization strategy, cross-validation procedure, and evaluation metric were compared to determine the optimum classification model. Our data-driven approach, involving model-based clustering, resulted in a set of 13 patient groups, which serve as auditory profiles. The 13 auditory profiles separate patients within certain ranges across audiological measures and are audiologically plausible. Both a normal hearing profile and profiles with varying extents of hearing impairments are defined. Further, a random forest classification model with a combination of a one-vs.-all and one-vs.-one binarization strategy, 10-fold cross-validation, and the kappa evaluation metric was determined as the optimal model. With the selected model, patients can be classified into 12 of the 13 auditory profiles with adequate precision (mean across profiles = 0.9) and sensitivity (mean across profiles = 0.84). The proposed approach, consequently, allows generating of audiologically plausible and interpretable, data-driven clinical auditory profiles, providing an efficient way of characterizing hearing deficits, while maintaining clinical applicability. The method should by design be applicable to all audiological data sets from clinics or research, and in addition be flexible to summarize information across databases by means of profiles, as well as to expand the approach toward aided measurements, fitting parameters, and further information from databases.

Class binarization to neuroevolution for multiclass classification

Multiclass classification is a fundamental and challenging task in machine learning. The existing techniques of multiclass classification can be categorized as (1) decomposition into binary (2) extension from binary and (3) hierarchical classification. Decomposing multiclass classification into a set of binary classifications that can be efficiently solved by using binary classifiers, called class binarization, which is a popular technique for multiclass classification. Neuroevolution, a general and powerful technique for evolving the structure and weights of neural networks, has been successfully applied to binary classification. In this paper, we apply class binarization techniques to a neuroevolution algorithm, NeuroEvolution of Augmenting Topologies (NEAT), that are used to generate neural networks for multiclass classification. We propose a new method that applies Error-Correcting Output Codes (ECOC) to design the class binarization strategies on the neuroevolution for multiclass classification. The ECOC strategies are compared with the class binarization strategies of One-vs-One and One-vs-All on three well-known datasets of Digit, Satellite, and Ecoli. We analyse their performance from four aspects of multiclass classification degradation, accuracy, evolutionary efficiency, and robustness. The results show that the NEAT with ECOC performs high accuracy with low variance. Specifically, it shows significant benefits in a flexible number of binary classifiers and strong robustness.

Geometric feature statistics histogram for both real-valued and binary feature representations of 3D local shape

3D local feature description is now at the core of many 3D vision technologies. However, most of the existing 3D feature descriptors can't strike a balance among descriptiveness, robustness, compactness, and efficiency. To overcome the challenges, we propose a real-valued 3D local feature descriptor named Geometric Feature Statistics Histogram (GFSH) and its binary extension descriptor named B-GFSH. A GFSH descriptor first constructs an improved-weighted covariance matrix to solve a stable and reliable Local Reference Frame (LRF), and then achieves a comprehensive description of the 3D local surface by performing statistics on multiple geometric distribution features, namely voxel density, voxel centroid, and projection density. A particular trait of our GFSH descriptor is its seamless extension to the binary representation to reduce storage consumption and accelerate feature matching. For each sub-feature of GFSH, B-GFSH respectively adopts the corresponding binarization strategy, i.e., improved Gray code quantization, thresholding based on coordinates, and neighbor comparison. Extensive experiments on six public datasets prove that both GFSH and B-GFSH have high descriptiveness, strong robustness, and fast real-time performance. In addition, B-GFSH further has the characteristics of fast matching speed, low memory footprint, and high compactness. Finally, we conduct 3D scene registration and 3D object recognition experiments to visually demonstrate the actual effectiveness of GFSH and B-GFSH.

Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction

This paper presents an adaptive image sampling algorithm based on Deep Learning (DL). The adaptive sampling mask generation network is jointly trained with an image inpainting network. The sampling rate is controlled in the mask generation network, and a binarization strategy is investigated to make the sampling mask binary. Besides the image sampling and reconstruction application, we show that the proposed adaptive sampling algorithm is able to speed up raster scan processes such as the X-Ray fluorescence (XRF) image scanning process. Recently XRF laboratory-based systems have evolved to lightweight and portable instruments thanks to technological advancements in both X-Ray generation and detection. However, the scanning time of an XRF image is usually long due to the long exposures requires (e.g., $100 \mu s-1ms$ per point). We propose an XRF image inpainting approach to address the issue of long scanning time, thus speeding up the scanning process while still maintaining the possibility to reconstruct a high quality XRF image. The proposed adaptive image sampling algorithm is applied to the RGB image of the scanning target to generate the sampling mask. The XRF scanner is then driven according to the sampling mask to scan a subset of the total image pixels. Finally, we inpaint the scanned XRF image by fusing the RGB image to reconstruct the full scan XRF image. The experiments show that the proposed adaptive sampling algorithm is able to effectively sample the image and achieve a better reconstruction accuracy than that of the existing methods.

Clustering-Based Binarization Methods Applied to the Crow Search Algorithm for 0/1 Combinatorial Problems

Metaheuristics are smart problem solvers devoted to tackling particularly large optimization problems. During the last 20 years, they have largely been used to solve different problems from the academic as well as from the real-world. However, most of them have originally been designed for operating over real domain variables, being necessary to tailor its internal core, for instance, to be effective in a binary space of solutions. Various works have demonstrated that this internal modification, known as binarization, is not a simple task, since the several existing binarization ways may lead to very different results. This of course forces the user to implement and analyze a large list of binarization schemas for reaching good results. In this paper, we explore two efficient clustering methods, namely KMeans and DBscan to alter a metaheuristic in order to improve it, and thus do not require on the knowledge of an expert user for identifying which binarization strategy works better during the run. Both techniques have widely been applied to solve clustering problems, allowing us to exploit useful information gathered during the search to efficiently control and improve the binarization process. We integrate those techniques to a recent metaheuristic called Crow Search, and we conduct experiments where KMeans and DBscan are contrasted to 32 different binarization methods. The results show that the proposed approaches outperform most of the binarization strategies for a large list of well-known optimization instances.

Thresholding strategies to measure vessel density by optical coherence tomography angiography

ObjectiveA variety of binarization strategies have been used to measure vessel density by optical coherence tomography angiography (OCT-A), but it is uncertain if they produce similar results. The purpose of the study was to evaluate the impact of different thresholding methods and contrast and brightness adjustment on OCT-A vessel density metrics. DesignObservational, cross-sectional case series. ParticipantsConsecutive healthy volunteers. MethodsHealthy volunteers underwent fovea-centred 3 mm × 3 mm OCT-A scans using PlexElite 9000. Images of the superficial vascular plexus were generated using the instrument’s automated segmentation. Images were thresholded with 5 different threshold tools in ImageJ (Default, Huang, IsoDat, Mean, and Otsu), and the threshold grey level value defined by each method was recorded. Brightness and contrast were also increased or decreased by 50% compared with the default. Binarization was performed using the threshold values from each method, and vessel densities were computed and compared. Main outcome measuresSuperficial plexus vessel density was measured and compared using different adjust threshold tools and changing brightness and contrast. ResultsTwenty eyes of 20 healthy participants were included. Different threshold strategies produced measurements with different mean values (p < 0.0001). Pairwise comparisons revealed differences between all groups (p < 0.0001) except between the IsoData and Otsu thresholding approaches (p > 0.270). Increasing or decreasing the brightness or to 50% of the mean value also yielded statistically significant differences (p < 0.0001). ConclusionsThe method of thresholding and adjustments in contrast and brightness can significantly impact retinal vessel density measurements. These findings highlight the importance of using consistent thresholding strategies for clinical studies.

Optical Reservoir Computing Using Multiple Light Scattering for Chaotic Systems Prediction

Reservoir Computing is a relatively recent computational framework based on a large Recurrent Neural Network with fixed weights. Many physical implementations of Reservoir Computing have been proposed to improve speed and energy efficiency. In this study, we report new advances in Optical Reservoir Computing using multiple light scattering to accelerate the recursive computation of the reservoir states. Two different spatial light modulation technologies, namely, phase or binary amplitude modulations, are compared. Phase modulation is a promising direction already employed in other photonic implementations of Reservoir Computing. Additionally, we report a Digital-Micromirror-based Reservoir Computing at up to 640 Hz, more than double the previously reported frequency using a remotely controlled optical device developed by LightOn, and present new binarization strategies to improve the performance of binarized Reservoir Computing.

A selectional auto-encoder approach for document image binarization

Binarization plays a key role in the automatic information retrieval from document images. This process is usually performed in the first stages of document analysis systems, and serves as a basis for subsequent steps. Hence it has to be robust in order to allow the full analysis workflow to be successful. Several methods for document image binarization have been proposed so far, most of which are based on hand-crafted image processing strategies. Recently, Convolutional Neural Networks have shown an amazing performance in many disparate duties related to computer vision. In this paper we discuss the use of convolutional auto-encoders devoted to learning an end-to-end map from an input image to its selectional output, in which activations indicate the likelihood of pixels to be either foreground or background. Once trained, documents can therefore be binarized by parsing them through the model and applying a global threshold. This approach has proven to outperform existing binarization strategies in a number of document types.

Undirected cyclic graph based multiclass pair-wise classifier: Classifier number reduction maintaining accuracy

Supervised classification approaches try to classify correctly the new unlabelled examples based on a set of well-labelled samples. Nevertheless, some classification methods were formulated for binary classification problems and has difficulties for multi-class problems. Binarization strategies decompose the original multi-class dataset into multiple two-class subsets. For each new sub-problem a classifier is constructed. One-vs-One is a popular decomposition strategy that in each sub-problem discriminates the cases that belong to a pair of classes, ignoring the remaining ones. One of its drawbacks is that it creates a large number of classifiers, and some of them are irrelevant. In order to reduce the number of classifiers, in this paper we propose a new method called Decision Undirected Cyclic Graph. Instead of making the comparisons of all the pair of classes, each class is compared only with other two classes; evolutionary computation is used in the proposed approach in order to obtain suitable class pairing. In order to empirically show the performance of the proposed approach, a set of experiments over four popular Machine Learning algorithms are carried out, where our new method is compared with other well-known decomposition strategies of the literature obtaining promising results.

Dynamic selection of the best base classifier in One versus One

Class binarization strategies decompose the original multi-class problem into several binary sub-problems. One versus One (OVO) is one of the most popular class binarization techniques, which considers every pair of classes as a different sub-problem. Usually, the same classifier is applied to every sub-problem and then all the outputs are combined by some voting scheme. In this paper we present a novel idea where for each test instance we try to assign the best classifier in each sub-problem of OVO. To do so, we have used two simple Dynamic Classifier Selection (DCS) strategies that have not been yet used in this context. The two DCS strategies use K-NN to obtain the local region of the test-instance, and the classifier that performs the best for those instances in the local region, is selected to classify the new test instance. The difference between the two DCS strategies remains in the weight of the instance. In this paper we have also proposed a novel approach in those DCS strategies. We propose to use the K-Nearest Neighbor Equality (K-NNE) method to obtain the local accuracy. K-NNE is an extension of K-NN in which all the classes are treated independently: the K nearest neighbors belonging to each class are selected. In this way all the classes take part in the final decision. We have carried out an empirical study over several UCI databases, which shows the robustness of our proposal.

Formula omitted] method: NOV@

Binarization strategies decompose the original multi-class dataset into multiple two-class subsets, learning a different binary model for each new subset. One-vs-All (OVA) and One-vs-One (OVO) are two of the most well-known techniques: One-vs-One separates a pair of classes in each binary sub-problem, ignoring the remaining ones; and One-vs-All distinguishes one class from all the other classes. In this paper, we present two new OVA and OVO combinations where the best base classifier is applied in each sub-problem. The first method is called OVA+OVO since it combines the outputs obtained by OVA and OVO decomposition strategies. The second combination is named NewOneVersusOneAll (NOV@), and its objective is to solve the problems found in OVA when different base classifiers are used in each sub-problem. In order to validate the performance of the new proposal, an empirical study has been carried out where the two new methods are compared with other well-known decomposition strategies from the literature. Experimental results show that both methods obtain promising results, especially NOV@.

A One-Versus-All Class Binarization Strategy for Bearing Diagnostics of Concurrent Defects

In bearing diagnostics using a data-driven modeling approach, a concern is the need for data from all possible scenarios to build a practical model for all operating conditions. This paper is a study on bearing diagnostics with the concurrent occurrence of multiple defect types. The authors are not aware of any work in the literature that studies this practical problem. A strategy based on one-versus-all (OVA) class binarization is proposed to improve fault diagnostics accuracy while reducing the number of scenarios for data collection, by predicting concurrent defects from training data of normal and single defects. The proposed OVA diagnostic approach is evaluated with empirical analysis using support vector machine (SVM) and C4.5 decision tree, two popular classification algorithms frequently applied to system health diagnostics and prognostics. Statistical features are extracted from the time domain and the frequency domain. Prediction performance of the proposed strategy is compared with that of a simple multi-class classification, as well as that of random guess and worst-case classification. We have verified the potential of the proposed OVA diagnostic strategy in performance improvements for single-defect diagnosis and predictions of BPFO plus BPFI concurrent defects using two laboratory-collected vibration data sets.

An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes

Classification problems involving multiple classes can be addressed in different ways. One of the most popular techniques consists in dividing the original data set into two-class subsets, learning a different binary model for each new subset. These techniques are known as binarization strategies. In this work, we are interested in ensemble methods by binarization techniques; in particular, we focus on the well-known one-vs-one and one-vs-all decomposition strategies, paying special attention to the final step of the ensembles, the combination of the outputs of the binary classifiers. Our aim is to develop an empirical analysis of different aggregations to combine these outputs. To do so, we develop a double study: first, we use different base classifiers in order to observe the suitability and potential of each combination within each classifier. Then, we compare the performance of these ensemble techniques with the classifiers' themselves. Hence, we also analyse the improvement with respect to the classifiers that handle multiple classes inherently. We carry out the experimental study with several well-known algorithms of the literature such as Support Vector Machines, Decision Trees, Instance Based Learning or Rule Based Systems. We will show, supported by several statistical analyses, the goodness of the binarization techniques with respect to the base classifiers and finally we will point out the most robust techniques within this framework.