Digital Image Classification Research Articles

Some notes on the divergence and transformed divergence formulae in the remote sensing literature

ABSTRACT Divergence, and particularly Transformed Divergence, are key separability metrics in remote sensing, predominantly utilized for digital image classification to achieve thematic mapping. Despite the widespread use of Transformed Divergence, the mathematical expression of Divergence – essential for calculating Transformed Divergence – appears in the literature in two different formulations, leading to inconsistent results and confusion within the remote sensing community. This study addresses the original source of Divergence, clarifies its correct formulation, and examines implementations that calculate Divergence and/or Transformed Divergence based on the original formula. Additionally, it provides data to verify the accuracy of future implementations and quantitatively shows the erratic implications of incorrect calculations.

IMPROVEMENT OF NEURAL NETWORK MODEL TOPOLOGY FOR OBJECT SEGMENTATION IN DIGITAL IMAGES BASED ON CONVOLUTIONAL NEURAL NETWORKS

Nowadays, convolutional neural networks have demonstrated significant performance gains over traditional machine learning methods for various real-world computational intelligence tasks such as digital image classification. However, to achieve the best accuracy, the network topology should be modeled using different architectures with different number of filters, kernel size, number of layers, etc., which actualizes the problem of developing and justifying appropriate selection methods. Taking into account the above mentioned, the aim of the paper is to justify an approach that will improve the topology of the neural network model for object segmentation in digital images based on convolutional neural networks. The research methods are system analysis, modeling, machine learning and fuzzy logic theory, and decision-making theory. As a result of the analysis, the paper proposes an algorithm to improve the topology of the neural network model based on differential evolution to optimize the accuracy of image segmentation and the training time of the network. Differential evolution is applied to determine the optimal number of layers in the network topology, which promotes faster convergence. Within the proposed algorithm, an encoding step was identified to represent the structure of each network using a fixed-length integer array, after which it is proposed to utilize differential evolution processes (mutation, recombination, and selection) to efficiently explore the search space. Prospects for further research are to develop methods and techniques to encode a candidate solution using different numbers of hidden blocks in each convolution.

CINNAMON-GUI: Revolutionizing Pap Smear Analysis with CNN-Based Digital Pathology Image Classification

Background Medical imaging has seen significant advancements through machine learning, particularly convolutional neural networks (CNNs). These technologies have transformed the analysis of pathological images, enhancing the accuracy of diagnosing and classifying cellular anomalies. Digital pathology methodologies, including image analysis, have improved cervical cancer diagnostics. However, existing commercial platforms are often costly and restrictive, limiting customization and scalability. Methods CINNAMON-GUI is an open-source digital pathology tool based on CNNs for classifying Pap smear images. Transitioning to a Shiny app in Python, it offers enhanced user interface and interactivity. The application supports dynamic web interactions, advanced features for image analysis, and state-of-the-art CNN models tailored for digital pathology. Key features include intuitive UI components, real-time image and plot generation, memory-efficient data handling, and robust training capabilities with customizable CNN architectures. The tool also integrates with Labelme for defining regions of interest and allows testing on external biospecimens. Results Model A (seed 42, 100 epochs) and Model B (same architecture with adjusted augmentation parameters) were compared. Model A stabilized with training accuracy around 0.88 and validation accuracy around 0.913. Model B showed improved performance with training accuracy around 0.91 and validation accuracy around 0.95. Feature mapping highlighted critical morphological aspects, improving classification accuracy. Model B reduced misclassification errors significantly compared to Model A. Conclusions CINNAMON-GUI demonstrates the potential of an open-source platform in digital pathology, providing transparency and collaborative opportunities. The tool enhances diagnostic accuracy through feature map analysis and optimized CNN training. Future development aims to extend its application to other cancer types, leveraging its dynamic and user-friendly interface for broader use in diagnostics.

Detection of counterfeit images using SIFT and PNN

Manipulation of digital images presents a significant challenge, primarily due to the continuous advancement and sophistication of image enhancement tools. As a consequence, image feature extraction and matching have become pivotal areas of research in the field of image processing. Among the various techniques developed, the Scale-Invariant Feature Transform algorithm has gained widespread recognition for its robustness and superior performance in feature matching tasks when compared to other existing methods. In this context, our proposed method, which integrates the Scale-Invariant Feature Transform algorithm with a probabilistic neural network, offers a novel approach to digital image classification specifically aimed at counterfeit image detection. This integrated system not only enhances the accuracy of feature extraction but also leverages the probabilistic neural network to improve classification efficacy. Empirical results indicate that this hybrid approach achieves a remarkable relative error rate of just 0.666%, underscoring its potential as a reliable tool for combating digital image forgery. Such advancements are crucial for maintaining the integrity of digital media in various applications, from forensic analysis to digital content authentication.

Using Grayscale Photos to Introduce High School Statistics Teachers to Reasoning with Digital Image Data

Statistics teaching at the high school level needs modernizing to include digital sources of data that students interact with every day. Algorithmic modeling approaches are recommended, as they can support the teaching of data science and computational thinking. Research is needed about the design of tasks that support high school statistics teachers to learn new statistical and computational approaches such as digital image analysis and classification models. Using our design framework, the construction of a task is described that introduces classification modeling using grayscale digital images. The task was implemented within a teaching experiment involving six high school statistics teachers. Our findings from this exploratory study indicated that the task design seemed to support statistical and computational thinking practices related to classification modeling and digital image data.

Identification of mangrove forests using Sentinel-1 Synthetic Aperture Radar (SAR) satellite imagery in Medan Belawan District, Medan City

Mangroves are a forest ecosystem tolerant to salt (halophytic) and influenced by sea tides. Mangrove forests are producers of ecosystem services that all living things need. The use of remote sensing can be used to identify mangrove forests in large areas in a short time. Sentinel-1 is a satellite product widely used to monitor land cover, including mangrove forests. The research objective was to identify mangrove forests in the Medan Belawan District using Sentinel-1 satellite imagery. Land cover classification in digital images was done using supervised classification with the maximum likelihood and random forest method. The results showed that random forest methods are more accurate than the maximum likelihood of identifying mangrove forests in Medan Belawan. The kappa accuracy value of the digital satellite image classification using the random forest method is 85.09%, and the maximum likelihood method is 77.4%. Based on the random forest method, the mangrove forest area is 1,325.81 hectares or 43.64% of the Belawan District area.

Monolayer directional metasurface for all-optical image classifier doublet.

Diffractive deep neural networks, known for their passivity, high scalability, and high efficiency, offer great potential in holographic imaging, target recognition, and object classification. However, previous endeavors have been hampered by spatial size and alignment. To address these issues, this study introduces a monolayer directional metasurface, aimed at reducing spatial constraints and mitigating alignment issues. Utilizing this methodology, we use MNIST datasets to train diffractive deep neural networks and realize digital classification, revealing that the metasurface can achieve excellent digital image classification results, and the classification accuracy of ideal phase mask plates and metasurface for phase-only modulation can reach 84.73% and 84.85%, respectively. Despite a certain loss of degrees of freedom compared to multi-layer phase mask plates, the single-layer metasurface is easier to fabricate and align, thereby improving spatial utilization efficiency.

Ensemble Transfer Learning for Hand-sign Digit Image Classification

Hand sign classification is a challenging task in image processing and machine learning. Robust learning algorithms are essential to achieve optimal performance. Ensemble transfer learning, a technique that combines ensemble learning and transfer learning, is a promising approach to improve classification model performance. This study investigates the use of ensemble transfer learning for hand sign classification. The Sign Language Digits Dataset, which contains ten distinct handwritten image types, was used to evaluate the performance of three architectures: ResNet-50, VGG-19, and Ensemble Transfer Learning (a fusion of ResNet-50 and VGG-19). The results showed that all three architectures performed well, but Ensemble Transfer Learning achieved the best performance with an accuracy of 96.12%, precision of 96.06%, recall of 96.21%, and F1 score of 96.07%. This suggests that ensemble transfer learning can effectively enhance model performance in image hand sign classification. The study also found that combining ResNet-50 and VGG-19 in Ensemble Transfer Learning yielded superior results compared to individual models. This is because ensemble transfer learning can leverage the strengths of both models to improve the overall performance. The findings of this study highlight the significance of employing ensemble transfer learning techniques to enhance accuracy and reliability in hand sign image classification.

ANALYSIS AND CLASSIFICATION OF PATHOLOGY DIGITAL IMAGES USING DEEP LEARNING

ANALYSIS AND CLASSIFICATION OF PATHOLOGY DIGITAL IMAGES USING DEEP LEARNING

The Image Classification Algorithm Was Implemented on The MNIST Data Set

In the current era of rapid development of science and technology, the recognition and classification of digital images is the key to solving many problems, such as the application of license plate recognition, document digitization, and remote sensing image surface classification. Based on the MNIST handwritten numerical data set collected by the National Institute of Standards and Technology (NIST), this report uses Python language and PyTorch programming framework to construct a convolutional neural network (CNN) structure and practice and experience the image classification of handwritten digits in the MNIST data set.

Hologram Noise Model for Data Augmentation and Deep Learning

This paper introduces a noise augmentation technique designed to enhance the robustness of state-of-the-art (SOTA) deep learning models against degraded image quality, a common challenge in long-term recording systems. Our method, demonstrated through the classification of digital holographic images, utilizes a novel approach to synthesize and apply random colored noise, addressing the typically encountered correlated noise patterns in such images. Empirical results show that our technique not only maintains classification accuracy in high-quality images but also significantly improves it when given noisy inputs without increasing the training time. This advancement demonstrates the potential of our approach for augmenting data for deep learning models to perform effectively in production under varied and suboptimal conditions.

A twin convolutional neural network with hybrid binary optimizer for multimodal breast cancer digital image classification

There is a wide application of deep learning technique to unimodal medical image analysis with significant classification accuracy performance observed. However, real-world diagnosis of some chronic diseases such as breast cancer often require multimodal data streams with different modalities of visual and textual content. Mammography, magnetic resonance imaging (MRI) and image-guided breast biopsy represent a few of multimodal visual streams considered by physicians in isolating cases of breast cancer. Unfortunately, most studies applying deep learning techniques to solving classification problems in digital breast images have often narrowed their study to unimodal samples. This is understood considering the challenging nature of multimodal image abnormality classification where the fusion of high dimension heterogeneous features learned needs to be projected into a common representation space. This paper presents a novel deep learning approach combining a dual/twin convolutional neural network (TwinCNN) framework to address the challenge of breast cancer image classification from multi-modalities. First, modality-based feature learning was achieved by extracting both low and high levels features using the networks embedded with TwinCNN. Secondly, to address the notorious problem of high dimensionality associated with the extracted features, binary optimization method is adapted to effectively eliminate non-discriminant features in the search space. Furthermore, a novel method for feature fusion is applied to computationally leverage the ground-truth and predicted labels for each sample to enable multimodality classification. To evaluate the proposed method, digital mammography images and digital histopathology breast biopsy samples from benchmark datasets namely MIAS and BreakHis respectively. Experimental results obtained showed that the classification accuracy and area under the curve (AUC) for the single modalities yielded 0.755 and 0.861871 for histology, and 0.791 and 0.638 for mammography. Furthermore, the study investigated classification accuracy resulting from the fused feature method, and the result obtained showed that 0.977, 0.913, and 0.667 for histology, mammography, and multimodality respectively. The findings from the study confirmed that multimodal image classification based on combination of image features and predicted label improves performance. In addition, the contribution of the study shows that feature dimensionality reduction based on binary optimizer supports the elimination of non-discriminant features capable of bottle-necking the classifier.

Land Use and Land Cover Dynamics: Deriving Forces and Perceptions of Local Community in Derashe, Southern Ethiopia.

Changes in land use and land cover (LULC) reached a point where we must reconcile. Thus, this study was conducted to assess the LULC changes, deriving forces, and the local community perceptions in Derashe, Southern Ethiopia. Landsat Series sensors' 4, 5, and 8 imagery was used to analyze the LULC over the year. Focus group discussions (FGDs) and key informant interviews (KIIs) were used to assess the deriving force and perceptions. Maximum likelihood of the supervised digital image classification technique was employed. Postclassification was used to detect and quantify changes. Deriving force and perception data were analyzed through descriptive statistics and narration. Five major LULC classes were identified. A major increase was observed in settlement and agricultural land by displacing forest and bush lands. However, the water body was fluctuated. According to the local community, the agricultural land expansion and growing population pressure are the major proximate and underlying deriving forces, respectively. Therefore, proper design for efficient use is necessary.

ProMIL: A weakly supervised multiple instance learning for whole slide image classification based on class proxy

The histopathological analysis of a suspected region is critical for cancer diagnosis, treatment, and management. Histopathological diagnosis consists in analyzing the characteristics of the lesions using tissue sections stained with hematoxylin and eosin. Classification of digital tumor pathology images, called whole slide images (WSIs), is a great challenge since WSIs usually have huge resolutions while lacking localized annotations. Multiple instance learning (MIL) is a commonly used method applied to pathological image analysis. However, most MIL methods often focus only on the global representation of WSIs, ignoring whether the category labels play other roles in the model training besides being a supervision signal. In addition, feature confusion is also a problem that should be avoided for the analysis of WSIs with weakly supervised methods. To address these problems, we propose a novel algorithm of classifying WSI for cancer diagnosis. The proposed model, ProMIL, uses only slide-level labels rather than localized annotations for analysis. There are three innovations in this work. Firstly, we present the concept of class proxy which is the representation of the intrinsic feature of each category, and plays a key role in guiding the training of the model. Secondly, we design a novel WSI representation learning module that utilizes a multi-scale feature extraction strategy to represent each patch in a WSI and then aggregates these representations using an attention mechanism to encode the WSI. Thirdly, we design a metric-learning-based weakly supervised multiclass-classifier by measuring the similarity between each WSI embedding and class proxies. The proposed ProMIL can effectively alleviate the side effect of feature confusion, and carry intuitive interpretability and scalability. To evaluate the performance of ProMIL, we conduct a series of experiments on several datasets of WSIs with different types of cancer from open data sources. It can be observed from the experimental results that ProMIL outperforms most of the compared methods and achieves better performance on a various type of cancer image data for classification, thus suggesting the proposed method is suitable for classifying different categories of cancer rather than a specific kind of cancer. Therefore, it is expected to act as a general framework to be extended to more cancer diagnoses.

Sol-Gel-Processed Y2O3 Multilevel Resistive Random-Access Memory Cells for Neural Networks.

Yttrium oxide (Y2O3) resistive random-access memory (RRAM) devices were fabricated using the sol-gel process on indium tin oxide/glass substrates. These devices exhibited conventional bipolar RRAM characteristics without requiring a high-voltage forming process. The effect of current compliance on the Y2O3 RRAM devices was investigated, and the results revealed that the resistance values gradually decreased with increasing set current compliance values. By regulating these values, the formation of pure Ag conductive filament could be restricted. The dominant oxygen ion diffusion and migration within Y2O3 leads to the formation of oxygen vacancies and Ag metal-mixed conductive filaments between the two electrodes. The filament composition changes from pure Ag metal to Ag metal mixed with oxygen vacancies, which is crucial for realizing multilevel cell (MLC) switching. Consequently, intermediate resistance values were obtained, which were suitable for MLC switching. The fabricated Y2O3 RRAM devices could function as a MLC with a capacity of two bits in one cell, utilizing three low-resistance states and one common high-resistance state. The potential of the Y2O3 RRAM devices for neural networks was further explored through numerical simulations. Hardware neural networks based on the Y2O3 RRAM devices demonstrated effective digit image classification with a high accuracy rate of approximately 88%, comparable to the ideal software-based classification (~92%). This indicates that the proposed RRAM can be utilized as a memory component in practical neuromorphic systems.

Using Local Knowledge and Remote Sensing in the Identification of Informal Settlements in Riyadh City, Saudi Arabia

Urban planning within Riyadh, the capital of Saudi Arabia, has been impacted by the presence of informal settlements. An understanding of the spatial distribution of these settlements is essential in developing urban policies. This study used remotely sensed imagery to evaluate and characterize informal settlements within the city, both with and without expert knowledge of the study area (defined as expert knowledge, EK). An informal settlement ontology for four study sites within Riyadh City was developed using an analytical hierarchy process (AHP). Local knowledge was translated into a ruleset to identify and map settlement areas using spatial, spectral, textural, and geometric techniques. These were combined with an object-based image analysis (OBIA) approach. The study demonstrated that combining expert knowledge and remotely sensed data can efficiently and accurately identify informal settlements. Two classified images were produced, one with EK, and one without EK, to investigate how a detailed understanding of local conditions could affect the final image classification. Overall accuracy when using EK was 94%, with a kappa coefficient of 89%, while without EK accuracy was 68% (kappa coefficient of 61%). The final OBIA classes included formal and informal settlements, road networks, vacant blocks, shaded areas, and vegetation. This study demonstrated that local expert knowledge and OBIA helpful in urban mapping. It also indicated the value of integrating a local ontological process during digital image classification. This work provided improved techniques for mapping informal settlements in Middle Eastern cities.

Study urban expansion in Mosul city using remote sensing data

Mosul city considered as the second largest city in Iraq after the capital, Baghdad, in terms of population and urban areas (residential neighborhoods) in terms of number and high population density, which requires the need to monitor the changes that occur in the city as a result of random expansion, unplanned construction in large areas. Knowing about these changes is importance to the authorities in planning and providing services for the city. The current research deals with the study of urban expansion of Mosul city using Landsat 8 satellite data for the three different years 2009, 2014, 2019, respectively. Digital processing and image classification were used to prepare and draw three urban maps to track urban growth patterns for the three different time periods, using remote sensing software. Where the results showed that significant changes occurred in the structure of the city, represented in a significant increase in residential areas at the expense of a significant decline in agricultural lands and forest lands, as the residential areas reached 96.30 km2 in 2009 and according to the study became 166.42 km2 in 2019, an increase of 70.12 km2 within ten years. This warns the authorities to take legal and planning measures to preparation to this increase and try to provide the necessary services and infrastructure for this increase rate, in addition to preventing encroachments on agricultural areas. Government departments and local authorities can benefit from this research in developing service strategies and future infrastructure projects and updating the city's base map based on the expansion rates derived from the research results.

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Different kinds of techniques are evaluated and analyzed for various classification models for the detection of diseases of citrus fruits. This paper aims to systematically review the papers that focus on the prediction, detection, and classification of citrus fruit diseases that have employed machine learning, deep learning, and statistical techniques. Additionally, this paper explores the present state of the art of the concept of image acquisition, digital image processing, feature extraction, and classification approaches, and each one is discussed separately. A total of 78 papers are selected after applying primary selection criteria, inclusion/exclusion criteria, and quality assessment criteria. We observe that the following are widely used in the selected studies: hyperspectral imaging systems for the image acquisition process, thresholding for image processing, support vector machine (SVM) models as machine learning (ML) models, convolutional neural network (CNN) architectures as deep learning models, principal component analysis (PCA) as a statistical model, and classification accuracy as evaluation parameters. Moreover, the color feature is the most popularly used feature for the RGB color space. From the review studies that performed comparative analyses, we find that the best techniques that outperformed other techniques in their respective categories are as follows: SVM among the ML methods, ANN among the neural network networks, CNN among the deep learning methods, and linear discriminant analysis (LDA) among the statistical techniques.This study concludes with meta-analysis, limitations, and future research directions.

Optimized Artificial Neural Network for the Classification of Urban Environment Comfort using Landsat-8 Remote Sensing Data in Greater Jakarta Area, Indonesia

The development of computer vision technology as a type of artificial intelligence is increasing rapidly in various fields. This method uses deep learning methods based on artificial neural networks, a well-performed algorithm in multi-parameter analysis. One of the development of computer vision models and algorithms is for a thematic digital image classification, such as environmental analysis. Remote sensing based digital image classification is one of the reliable tools for environmental quality analysis. This study aims to perform neural network optimization for the analysis of the urban environment comfort based on satellite data. The input data used are 4 types of geobiophysical indexes as urban environmental comfort parameters derived from cloud-free annual mosaics Landsat-8 remote sensing satellite data. The results obtained in this study indicate that the 1 hidden layer neural network architecture with 16 neurons for the classification of urban environmental comfort and 10 other land cover classes is quite good. The result of the classification using this optimized artificial neural network shows that the distribution of classes is very uncomfortable which dominates the Greater Jakarta area and its surroundings. For other classes in the study area, some are uncomfortable and rather comfortable. By using this method, we obtained a fast classification training time of 18 seconds for 145 iterations to achieve an RMS Error of 0.01, and has a fairly high classification accuracy overall 89% with a Kappa coefficient of 0.88, while the 2 hidden layer neural network architecture does not succeed in achieving convergence

CsPbBr3 Perovskite Quantum Dots Embedded in Polystyrene-poly2-vinyl Pyridine Copolymer for Robust and Light-Tunable Memristors

The development of a reliable optoelectronic memristor is crucial for the success of neuromorphic vision systems, but current devices are limited by stochastic resistance switching and uncontrollable ion dynamics. To address these challenges, a core–shell nanosphere composite was synthesized using CsPbBr3 quantum dots and block copolymer polystyrene-poly2-vinyl pyridine. This memristor exhibits both negative differential resistance and resistive switching memory behavior and has demonstrated exceptional stability, withstanding over 5000 cycles and remaining stable for over 5 million seconds. It is also tunable by light irradiation, making it ideal for optoelectronic logic operations and multi-derivative state applications. The memory behavior is attributed to an electrochemical metalization mechanism involving the formation and annihilation of pyridine groups, conductive metal filaments, and bromide ion vacancies in S2VP filaments. This work presents an effective method for fabricating robust multi-derivative perovskite optoelectronic devices for neuromorphic computing systems. Additionally, machine learning algorithms have demonstrated accurate digital image classification and recognition using photoelectric pulse-driven neuromorphic computation with an accuracy of over 97%.