Image Classification Techniques Research Articles

Quantum Computing Meets Deep Learning: A Promising Approach for Diabetic Retinopathy Classification

Diabetic retinopathy seems to be the cause of micro-vascular retinal alterations. It remains a leading reason for blindness and vision loss in adults around the age of 20 to 74. Screening for this disease has become vital in identifying referable cases that require complete ophthalmic evaluation and treatment to avoid permanent loss of vision. The computer-aided design could ease this screening process, which requires limited time, and assist clinicians. The main complexity in classifying images involves huge computation, leading to slow classification. Certain image classification approaches integrating quantum computing have recently evolved to resolve this. With its parallel computing ability, quantum computing could assist in effective classification. The notion of integrating quantum computing with conventional image classification methods is theoretically feasible and advantageous. However, as existing image classification techniques have failed to procure high accuracy in classification, a robust approach is needed. The present research proposes a quantum-based deep convolutional neural network to avert these pitfalls and identify disease grades from the Indian Diabetic Retinopathy Image Dataset. Typically, quantum computing could make use of the maximum number of entangled qubits for image reconstruction without any additional information. This study involves conceptual enhancement by proposing an optimized structural system termed an optimized multiple-qbit gate quantum neural network for the classification of DR. In this case, multiple qubits are regarded as the ability of qubits in multiple states to exist concurrently, which permits performance improvement with the distinct additional qubit. The overall performance of this system is validated in accordance with performance metrics, and the proposed method achieves 100% accuracy, 100% precision, 100% recall, 100% specificity, and 100% f1-score.

GAN Data Augmentation Methods in Rock Classification

In this paper, a data augmentation method Conditional Residual Deep Convolutional Generative Adversarial Network (CRDCGAN) based on Deep Convolutional Generative Adversarial Network (DCGAN) is proposed to address the problem that the accuracy of existing image classification techniques is too low when classifying small-scale rock images. Firstly, Wasserstein distance is introduced to change the loss function, which makes the training of the network more stable; secondly, conditional information is added, and the network has the ability to generate and discriminate image data with label information; finally, the residual module is added to improve the quality of generated images. The results demonstrate that by applying CRDCGAN to the augmented rock image dataset, the accuracy of the classification model trained on this dataset is as high as 96.38%, which is 13.39% higher than that of the classification model trained on the non-augmented dataset, and 8.56% and 6.27% higher than that of the traditional dataset augmented method and the DCGAN dataset augmentation method, respectively. CRDCGAN expands the rock image dataset, which makes the rock classification model accuracy effectively improved. The data augmentation method was found to be able to change the accuracy of the classification model to a greater extent.

Assessment of Land Use-Land Cover Changes in Samastipur District of Bihar (India) Using Geo-Informatics

The assessment and analysis of Land Use/Land Cover (LULC) changes are required to identify the land use changes from year to year which plays a critical role in planning and implementation of developmental activities. The present study aims to assess LULC changes in Samastipur district of Bihar using Remote Sensing (RS) and Geographical Information System (GIS). The LULC maps were prepared using LANDSAT-5 and LANDSAT-8 images by adopting object based image classification technique. Assessments of LULC changes were done @ 5 years, @ 10 years and @ 20 years during 2000-2020. The results indicated that the agriculture land coverage increased at high rate during 2000-2005 and 2005-2010; and after that it is increasing at slow rate. The natural vegetation coverage is continuously decreasing during years 2000-2020 while settlement is continuously increasing during this period with notable increase during 2000-2005 and 2015-2020. In the time interval of 10 years (2000-2010), the agriculture land area increased by 22.17%; natural vegetation area decreased by 38.04%; the water-bodies decreased by 46.69%; sand and barren land decreased by 61.27% and settlement area increased by 15.62%. Over the next 10 years (2010-2020), area covered by agriculture land, settlement, water-bodies and sand and barren land increased by 8.05%, 38.30%, 26.27% and 44.65% respectively while area covered by natural vegetation decreased by 75.24%. During time interval of 20 years (2000-2020), agriculture land area and settlement area increased by 32% and 59.91% respectively while natural vegetation, sand and barren land and water-bodies decreased by 84.66%, 43.98% and 32.68% respectively. The analysis of the results indicates that the natural vegetation has decreased at fast rate in the recent years. Therefore, proper attention is required towards stopping of cutting of natural vegetation in the district to save the environment.

Transfer Learning based Image Classification of Diseased Tomato Leaves with Optimal Fine-Tuning combined with Heat Map Visualization

India is one of the leading countries in Tomato cultivation and production. Coimbatore, Dharmapuri, Salem,Krishnagiri are some of the foremost districts in tomato production. According to a survey, Tomato Leaf Curl virus is one of the most ravage class of disease and the maximum incidence of the disease is reported as 95.3% in Dharmapuri district of Tamil Nadu. The objective of the work is to identify the most recurrent tomato plant diseases using deep learning-based image classification techniques and to develop a plant disease classification web application. In this paper, Tomato based leaf disease images alone is used from Plant Village Dataset downloaded from Kaggle platform. Inception V3, a pre-trained transfer learning model is used to classify this multi-class tomato plant disease by using the leaf symptoms such as dark brown lesions, concentric rings etc. Data augmentation is performed while training the model on the images using Keras Image Data Generator on various layers and feature extraction is performed. The training accuracy and validation accuracy of the model before and after fine-tuning is 80.21%,76.29% and 81.72%,77.63% respectively. The highest precision, recall and F1 score is 95, 93 and 94 respectively is recorded for Tomato Yellow Leaf Curl Virus Disease for which the yield losses is severe. Further, activations are used to generate an attention map in the form of Heat Maps which is included as a post processing step before the classification of the output. Plant Leaf Disease Classification- A web application is deployed using Streamlit Python library and Ngrok services

A novel technique for texture description and image classification based in RGB compositions

AbstractAt present, facial recognition entertains great importance in performing authentication processes, because it prevents unauthorized access to devices and places. Additionally, it allows for the identification of persons. Henceforth, this paper proposes a novel texture descriptor calledCyclical Chromaand a new classification technique, which takes in consideration the sub‐pixel values of 0–255 for each RGB (Red, Green, Blue) channel that conforms the image. To verify the effectiveness of the proposed techniques, tests were performed with a database of images in a controlled environment and in one under uncontrolled conditions; additionally, Cyclical Chroma was tested with a different classifier, denominated the Multiclass Classifier, and the results were compared against other descriptors, including GLCM, SHDH, LQP, and CCR, demonstrating the effectiveness of the proposed techniques with 100% efficiency with controlled images and 78% effectiveness under uncontrolled conditions prior to the application of an equalization technique, increasing the efficiency to 100%.

Mining and reasoning of data uncertainty-induced imprecision in deep image classification

Existing deep image classification techniques strive to suppress data uncertainty for various reasons such as blur, occlusion, noise, and label error and advance to higher accuracy. However, they ignore data uncertainty-induced imprecision and thus do not work as intended. In this paper, we propose a deep open-source framework to mine and reason the imprecision of such training and test sets, which can present better performance and reduce the risk of misclassification. First, we design a label reassignment mechanism. It allows the network to reassign training labels and allow imperfect training samples with multiple labels. As a result, they are removed from the original classes and considered new imprecise samples to represent partial ignorance. Second, we propose a new imbalanced data enhancement architecture to learn a generalized representation of each (precise and imprecise) class. It helps the network fuse the auxiliary information from both precise and imprecise classes, which is beneficial to extract more distinctive class features from single-labeled samples and characterize uncertainty-induced imprecision in the test set by imprecise test samples. Afterward, methodological analyses and empirical evaluations are conducted. The proposed framework is demonstrated to present better performance on different typical networks (Resnet50, MobileNetV2, DenseNet121, EfficientNetB0, ShuffleNetV2, SENet, SqueezeNet, Xception) based on five publicly available datasets (Imagewoof-5, Flowers, Monkey, Butterfly, and Cifar-10). In addition, several targeted deep techniques for uncertain images or imprecise results are also employed as comparisons to prove the superiority of the proposed framework.

Railroad Sleeper Condition Monitoring Using Non-Contact in Motion Ultrasonic Ranging and Machine Learning-Based Image Processing.

An ultrasonic sonar-based ranging technique is introduced for measuring full-field railroad crosstie (sleeper) deflections. Tie deflection measurements have numerous applications, such as detecting degrading ballast support conditions and evaluating sleeper or track stiffness. The proposed technique utilizes an array of air-coupled ultrasonic transducers oriented parallel to the tie, capable of "in-motion" contactless inspections. The transducers are used in pulse-echo mode, and the distance between the transducer and the tie surface is computed by tracking the time-of-flight of the reflected waveforms from the tie surface. An adaptive, reference-based cross-correlation operation is used to compute the relative tie deflections. Multiple measurements along the width of the tie allow the measurement of twisting deformations and longitudinal deflections (3D deflections). Computer vision-based image classification techniques are also utilized for demarcating tie boundaries and tracking the spatial location of measurements along the direction of train movement. Results from field tests, conducted at walking speed at a BNSF train yard in San Diego, CA, with a loaded train car are presented. The tie deflection accuracy and repeatability analyses indicate the potential of the technique to extract full-field tie deflections in a non-contact manner. Further developments are needed to enable measurements at higher speeds.

Spatial prediction of the urban inter-annual land surface temperature variability: An integrated modeling approach in a rapidly urbanizing semi-arid region

The inter-annual land surface temperature (LST) is a meteorological indicator of urban environments, affecting energy consumption and quality of life. In this study, the annual LST variability (ALSTV) of a rapidly urbanizing region in Iran including Karaj, Shahriar and Mohammad-Shahr cities and their surrounding suburbs was estimated using Landsat-8 images. Pixel-based image classification and object-based segmentation techniques were employed to extract built-up patches and spectrally homogeneous regions. Using the multiple regression analysis, the ALSTV of built-up patches was modeled as a function of their structure and the spatial characteristics of other land-use patches located in their respective segments (as neighborhood factors). A Cellular Automata model was utilized to simulate the expansion of built-up area up to 5% and, therefore, estimate their future ALSTV. The mean ALSTV was highest in urban areas (33.25± 7.41 °C), while the lowest mean value of 24.12± 3.24 °C was in green covers. The ALSTV of built-up patches were positively associated with their area and the percentage and size of neighborhood built-up patches, while negatively with the percentage of neighborhood green patches. To create a thermally comfortable landscape, additional green patch allocation and preventing excessive urban patch growth are required in all large built-up segments.

Crop acreage and yield mapping of groundnut crop in erstwhile Mahabubnagar District using RS and GIS

An investigation was carried in the erstwhile Mahabubnagar district of Telangana during rabi 2019-20 aiming the estimation of groundnut crop acreage and yield. The crop area was estimated using the satellite images of Landsat-8-OLI sensor from September to February covering the entire crop growth period by performing an unsupervised image classification technique with 300 classes, 300 iterations and a convergence threshold of 0.99. The groundnut yield was estimated by developing the regression equation using crop-cut yield data and NDVI values of the corresponding GPS locations. The crop area was estimated to be 57,865 ha with producer’s and user’s accuracy of 100 and 90% respectively, and a relative deviation of 28.6% when compared with actual ground estimates of the Department of agriculture. The crop yields were estimated with an R2 value of 0.71 and a correlation coefficient of 0.87

Multimodal biomedical image retrieval and indexing system using handcrafted with deep convolution neural network features

The advances in biomedical imaging equipment have produced a massive amount of medical images that are generated by the different modalities. Consequently, a huge volume of data has been produced and caused a complex and time-consuming retrieving process of the relevant cases. To resolve this issue, the Content-Based Biomedical Image Retrieval (CBMIR) system is applied to retrieve the related images from the earlier patients’ databases. However, the previous handcrafted features methods that applied the CBMIR model have shown poor performance in many multimodal databases. In this paper, we focus on designing CBMIR technique using Deep Learning (DL) models. We present a new Multimodal Biomedical Image Retrieval and Classification (M-BMIRC) technique for retrieving and classifying the biomedical images from huge databases. The proposed M-BMIRC model involves three dissimilar processes as following: feature extraction, similarity measurement, and classification. It uses an ensemble of handcrafted features from Zernike Moments (ZM) and deep features from Deep Convolutional Neural Networks (DCNN) for feature extraction process. Additionally, the Hausdorff Distance based similarity measure is employed to identify the resemblance between the queried image and the images that exist in the database. Moreover, the classification process gets executed on the retrieval images using the Probabilistic Neural Network (PNN) model, which allocates the class labels of the tested images. Finally, the experimental studies are conducted using two benchmark medical datasets and the results ensure the superior performance of the proposed model in terms of different measures include Average Precision Rate (APR), Average Recall Rate (ARR), F-score, accuracy, and Computation Time (CT).

Feature Extraction and Classification Techniques for Wireless Endoscopy Images: A Review

Feature Extraction and Classification Techniques for Wireless Endoscopy Images: A Review

Handwritten Text Classification Based on Convolutional Neural Network

The convolutional neural network (CNN) is a popular and highly effective deep learning technique for image classification. As the popularity of CNNs grew, the model has become popular in several machine learning problems. This paper utilizes a CNN model and the popular LeNet-5 transfer learned model to classify texts after the words are preprocessed and segmented from an image. The EMNIST database is used to train the models. The paper achieves an 89.36% validation accuracy on the EMNIST Balanced dataset and an 86.64% on the EMNIST By_Class dataset for the CNN model of four convolutional layers and one dense layer. Similarly, the LeNet-5 model obtained a validation accuracy of 85.88% on the EMNIST Balanced dataset and 85.01% accuracy on the EMNIST By_Class dataset. However, despite a higher accuracy in the EMNIST Balanced dataset, the EMNIST By_Class dataset achieves better results in real-world handwritten texts.

Assessing impacts of land use/land cover changes on the hydrology of Upper Gilgel Abbay watershed using the SWAT model

Population and economic growth, and the consequent increase in food demands have put great pressures on environmental resources and they are driving rapid LULC changes. This study is aimed to examine the impacts of land use/land cover LULC changes on the hydrology of the Upper Gilgel Abay watershed. Landsat images (Landsat 5 TM 1986, Landsat ETM+ 2003, and Landsat 8 OLI-TIRS 2021) were categorized into LULC classes following the supervised image classification technique, and the Soil and Water Assessment Tool (SWAT) model was used to evaluate the hydrological impacts of LULC changes. The result of image analysis revealed an increase in cultivated land (11.7%) and a decrease in forest (39.6%), shrubland (17.5%), grassland (5.6%), and water bodies (25%) during 1986–2003 periods. On the other hand, between 2003 and 2021 periods, cultivated land, grassland and water bodies were decreased while woodland and shrubland were grew up. Consequent to the LULC changes taking place between 1986 and 2003 periods, surface runoff (6%) and water yield (1.8%) were increased, but groundwater flow (37.9), lateral flow (4.1), soil water (1.85), and evapotranspiration (2.2%) were decreased at a watershed-scale. In contrast, the average watershed surface runoff and water yield were decreased between 2003 and 2021 time scales, while lateral flow, groundwater flow, soil water, and evapotranspiration increased, owing to the growth of forest and shrubland and the decline of cultivated land. The study also indicated the hydrological impacts of the LULC changes at the sub-watershed scales. The impacts of LULC change on status of hydrological components during 1986–2003 and 2003–2021 periods were different compared with the findings at the watershed scale. The findings suggests improvements of vegetation covers to reduce surface runoff and increase groundwater flow and soil water content in the study area in particular and in the Ethiopian Highlands in general.

Technical review of supervised machine learning studies and potential implementation to identify herbal plant dataset

Abstract The use of technology in everyday life is unavoidable, considering that technological advancement occurs very quickly. The current era is also known as industry 4.0. In the industry 4.0 era, there is a convergence between the industrial world and information technology. The use of modern machines in the industry makes it possible for business actors to digitize their production facilities and open up new business opportunities. One of the developments in information technology that is being widely used in its implementation is machine learning (ML) technology and its branches such as computer vision and image recognition. In this work, we propose a customized convolutional neural network-based ML model to perform image classification technique for Indonesian herb image dataset, along with the detailed review and discussion of the methods and results. In this work, we use the transfer learning method to adopt the opensource pre-trained model, namely, Xception, developed by Google.

Deep Learning Techniques for Early Detection of Autism Spectrum Disorder - Systematic Study

This paper narrates the various categories of image classification techniques. Image classification is an important tool for extracting information from digital images. The purpose of this research article is to summarize information on several image classification techniques.

Optimal guidance whale optimization algorithm and hybrid deep learning networks for land use land cover classification

Satellite Image classification provides information about land use land cover (LULC) and this is required in many applications such as Urban planning and environmental monitoring. Recently, deep learning techniques were applied for satellite image classification and achieved higher efficiency. The existing techniques in satellite image classification have limitations of overfitting problems due to the convolutional neural network (CNN) model generating more features. This research proposes the optimal guidance-whale optimization algorithm (OG-WOA) technique to select the relevant features and reduce the overfitting problem. The optimal guidance technique increases the exploitation of the search technique by changing the position of the search agent related to the best fitness value. This increase in exploitation helps to select the relevant features and avoid overfitting problems. The input images are normalized and applied to AlexNet–ResNet50 model for feature extraction. The OG-WOA technique is applied in extracted features to select relevant features. Finally, the selected features are processed for classification using Bi-directional long short-term memory (Bi-LSTM). The proposed OG-WOA–Bi-LSTM technique has an accuracy of 97.12% on AID, 99.34% on UCM, and 96.73% on NWPU, SceneNet model has accuracy of 89.58% on AID, and 95.21 on the NWPU dataset.

A Novel Method for Fashion Clothing Image Classification Based on Deep Learning

Image recognition and classification is a significant research topic in computational vision and widely used computer technology. Themethods often used in image classification and recognition tasks are based on deep learning, like Convolutional Neural Networks(CNNs), LeNet, and Long Short-Term Memory networks (LSTM). Unfortunately, the classification accuracy of these methods isunsatisfactory. In recent years, using large-scale deep learning networks to achieve image recognition and classification canimprove classification accuracy, such as VGG16 and Residual Network (ResNet). However, due to the deep network hierarchyand complex parameter settings, these models take more time in the training phase, especially when the sample number is small, which can easily lead to overfitting. This paper suggested a deep learning-based image classification technique based on a CNN model and improved convolutional and pooling layers. Furthermore, the study adopted the approximate dynamic learning rate update algorithm in the model training to realize the learning rate’s self-adaptation, ensure the model’s rapid convergence, and shorten the training time. Using the proposed model, an experiment was conducted on the Fashion-MNIST dataset, taking 6,000 images as the training dataset and 1,000 images as the testing dataset. In actual experiments, the classification accuracy of the suggested method was 93 percent, 4.6 percent higher than that of the basic CNN model. Simultaneously, the study compared the influence of the batch size of model training on classification accuracy. Experimental outcomes showed this model is very generalized in fashion clothing image classification tasks.

Assessment of Forest Covers Change in the Central Highlands of Ethiopia: The Case of Walmara District: Centeral Oromia (1985-2017)

In Ethiopia, forest cover changes were registered at local level that adds up to the changes observed at the national level. Likewise other part of the country the rapid advance of deforestation over recent decades has resulted in the conversion of the majority of the Walmara district forest in isolated patches. Geographic information system (GIS) techniques and remote sensing (RS) from satellite platforms offer a best way to identify forest cover change. The main objectives of the study were to examine and map the trends and extents of the forest cover changes and to identify the possible proximate causes during the study periods. Quantum GIS, ENVI and SPSS 16.0 were used for the analysis of the spatial and temporal forest cover change. A supervised image classification technique with Maximum likelihood classification algorism was applied on Landsat 5, 7 and 8 satellite images of 1985, 2000 and 2017 respectively. The result from the satellite image classifications were demonstrated that forest cover of the district was exhibited area decrement consistently. From the result the area of the forest cover was 9238.41, 4748.13 and 1497.87 whereas non-forest experiences area increment consistently with 58219.47, 62710.11 and 65960.37 in 1985, 2000 and 2017 respectively.

Long-Tailed Recognition by Hierarchical Rebalancing Dual-Classifier

Image classification techniques have succeeded greatly on various large-scale visual datasets using deep convolution neural networks. However, previous deep models usually suffer severe performance degradation in highly skewed datasets, which restricts their practical application. In this paper, we propose a novel Hierarchical Rebalancing Dual-Classifier model for long-tailed recognition. To better identify the tail samples and maintain the performance of head classes, we propose a dual-classifier framework with a uniform sampler for performing their duties. For balancing the learning of feature representation and classifiers, a dynamic weight is introduced to adjust the model’s attention. To alleviate the feature deviation between training data and testing data, a hierarchical rebalancing loss is designed for the re-weighting branch, which adjusts the decision values in predicted logits to facilitate the model actively compensating for tail categories. Finally, we conduct extensive experiments on standard long-tailed benchmarks Cifar10-LT, Cifar100-LT, ImageNet-LT, and iNaturalist2018, demonstrating the effectiveness and superiority of our HRDC.

Deep Learning-Based Ocular Disease Recognition

This study investigates the use of image classification methods to identify eye disorders using fundus images. Ocular disorders can significantly affect a person's quality of life, but frequent eye exams can help identify them early and prevent vision loss. Manual diagnosis, however, can take a while and is prone to mistakes made by humans. This study suggests utilising deep learning methods to automatically identify eye disorders from fundus photos. To classify several eye disorders, such as age-related macular degeneration, cataracts, and glaucoma, a convolutional neural network (CNN) model is created and trained using a sizable dataset of fundus images. The proposed CNN model achieves high accuracy in the classification of ocular diseases, demonstrating the potential of automated diagnosis for early detection and prevention of vision loss. The results of this research indicate that image classification techniques can significantly improve the accuracy and speed of ocular disease recognition, paving the way for improved ocular health management.