Object Image Classification Research Articles

Superclass-aware visual feature disentangling for generalized zero-shot learning

Zero-shot learning (ZSL) aims to learn a model trained on seen samples with the ability to recognize samples from unseen classes, while generalized ZSL (GZSL) takes a step closer to realistic scenarios by recognizing both of seen and unseen samples. The existing methods rely on the semantic descriptions as the side-information and conduct tight alignment between the visual and semantic spaces. However, the tight modality alignment may result in incomplete representations, leading to the loss of originally detailed and discriminative information. In this paper, we propose a simple yet effective superclass-aware visual feature disentangling method termed as SupVFD for GZSL. We use the neighbor relations of the semantic descriptions to define superclass and with the guide of superclass, our method disentangles visual features into discriminative and transferable factors. To this end, the semantic descriptions are used as implicit supervision, which preserves the valuable detailed and discriminative information in the visual features. The extensive experiments in both ZSL and GZSL settings prove our method outperforms the state-of-the-art methods for image object classification as well as video action recognition. Code is available at our github: https://github.com/changniu54/SupVFD-Master.

Screening COVID-19 from chest X-ray images by an optical diffractive neural network with the optimized F number

The COVID-19 pandemic continues to significantly impact people’s lives worldwide, emphasizing the critical need for effective detection methods. Many existing deep learning-based approaches for COVID-19 detection offer high accuracy but demand substantial computing resources, time, and energy. In this study, we introduce an optical diffractive neural network (ODNN-COVID), which is characterized by low power consumption, efficient parallelization, and fast computing speed for COVID-19 detection. In addition, we explore how the physical parameters of ODNN-COVID affect its diagnostic performance. We identify the F number as a key parameter for evaluating the overall detection capabilities. Through an assessment of the connectivity of the diffractive network, we established an optimized range of F number, offering guidance for constructing optical diffractive neural networks. In the numerical simulations, a three-layer system achieves an impressive overall accuracy of 92.64% and 88.89% in binary- and three-classification diagnostic tasks. For a single-layer system, the simulation accuracy of 84.17% and the experimental accuracy of 80.83% can be obtained with the same configuration for the binary-classification task, and the simulation accuracy is 80.19% and the experimental accuracy is 74.44% for the three-classification task. Both simulations and experiments validate that the proposed optical diffractive neural network serves as a passive optical processor for effective COVID-19 diagnosis, featuring low power consumption, high parallelization, and fast computing capabilities. Furthermore, ODNN-COVID exhibits versatility, making it adaptable to various image analysis and object classification tasks related to medical fields owing to its general architecture.

A Study on Maritime Object Image Classification Using a Pruning-Based Lightweight Deep-Learning Model

Deep learning models require high computing power due to a substantial amount of computation. It is difficult to use them in devices with limited computing environments, such as coastal surveillance equipments. In this study, a lightweight model is constructed by analyzing the weight changes of the convolutional layers during the training process based on MobileNet and then pruning the layers that affects the model less. The performance comparison results show that the lightweight model maintains performance while reducing computational load, parameters, model size, and data processing speed. As a result of this study, an effective pruning method for constructing lightweight deep learning models and the possibility of using equipment resources efficiently through lightweight models in limited computing environments such as coastal surveillance equipments are presented.

Comparative Analysis of CNN-Based Smart Pre-Trained Models for Object Detection on DOTA

In this paper, we proposed comparative research on the classification of various objects in satellite images using some pre-trained models of CNN (VGG-16, Inception-V3, ResNet-50, EfficientNet-B7) and R-CNN. In this research work, we have used the DOTA dataset, which combines data from 14 classes. We have implemented above mentioned pre-trained models of CNN, and R-CNN to achieve optimal results for accuracy as well as productivity. To detect objects like ships, tennis courts, swimming pools, vehicles, and harbors from remotely accessed images. In this study, we have used a convolutional neural network (CNN) as the base model. The transfer learning mechanism is employed to speed up the results and for complex computations. We have discovered with the help of experimental analysis that R-CNN and Inception-V3 are performing best out of the five pre-trained models.

Reducing the volume of computations when building analogs of neural networks for the first stage of an ensemble classifier with stacking

The object of research in this work is ensemble classifiers with stacking, intended for the classification of objects in images with the presence of small sets of labeled data for training. To improve the quality of classification at the first stage of such a classifier, it is necessary to place more primary classifiers that differ in heterogeneous structured processing. However, the number of known neural networks with appropriate characteristics is limited. One approach to solving this problem is to build analogs of known neural networks that make classification errors on other images compared to the base network. The disadvantage of the known methods for constructing such analogs is the need to perform additional floating-point operations. The current paper proposes and investigates a new method to form analogs through random cyclic shifts of rows or columns of input images. This has made it possible to completely eliminate additional floating-point operations. The effectiveness of using this method is explained by the structured processing of input images in basic neural networks. The use of analogs obtained by the proposed method does not impose additional restrictions in practice. This is because the heterogeneity of structured processing in basic neural networks is a typical requirement for them in an ensemble classifier with stacking. The simulation for the CIFAR-10 data set demonstrated that the proposed technique for constructing analogs allows for a comparative quality of classification by the ensemble classifier. Using MLP-Mixer analogs provided an improvement of 4.6 %, and CCT analogs – 5.9 %

Comprehensive Review on Plant Disease Detection and Identification

Image Agriculture is a major contributor to financial development and is the main source of income in many countries. The primary goal of disease prevention and treatment, notwithstanding the different challenges farmers face, including plant diseases, is to precisely identify and evaluate the disease while the plant is still growing. Object recognition and classification in images has been made possible by rapid advancements in deep learning, or DL, techniques. Recently, DL approaches have been applied to farming and other agricultural applications and have showed potential in a variety of areas. These plants are commonly affected by diseases such as Septoria leaf spots, bacterial spots, late plant blight, and curled yellow leaves. Our work presents a hybrid approach to early illness detection that applies region-based full convolutional networks (RFCN) for early disease identification and region-based convolutional neural networks (RCNN) for diseases classification. We construct a network model based on the EfficientNetB7 model that optimizes at several scales via dilated convolution. The network is constructed layer by layer, top-down, with several optimizations. Real-time crop images taken from crop fields are used in the experiment, and Efficient Net B7 and hybrid convolution models are used. When the suggested ensemble model is implemented in Python, the outcome demonstrates that it has high accuracy and low loss when compared to other current methodologies.

A comparison of deep learning-based object detection for unmanned aerial vehicle

Unmanned aerial vehicle (UAV) plays a critical role in the field of object detection, and machine learning techniques have significantly advanced the field in recent years. This paper provides a comprehensive overview of machine learning developments for UAV object detection. The process involves multiple steps. Firstly, deep learning and Convolutional Neural Network (CNN) are widely utilized to extract precise features and train object detection models for accurate classification and efficient recognition of target objects in images and videos. Secondly, classical object detection algorithms such as Faster R-CNN, You Only Look Once (YOLO), and Single Shot MultiBox Detector (SSD), have been enhanced to improve accuracy and real-time performance. In this review, we primarily focus on comparing the principles of CNN and YOLOv5 themselves, as well as their applications in object detection and image recognition. Ultimately, it becomes apparent that CNN is better suited for processing image data, automatically extracting features, and achieving more accurate classification and detection. On the other hand, YOLOv5 directly performs detection on large images, significantly reducing computation time compared to CNN.

Study of methods for searching and localizing objects in images from aircraft using convolutional neural networks

The use of unmanned and manned aerial vehicles for remote object localization and classification is very common. These methods are used in various systems, ranging from territory surveys to law enforcement. Methods of object localization and classification using neural networks require a detailed study and research of the quality of their work on data that has certain specifics, such as vehicle detection. The use of neural networks to detect certain types of objects using images obtained from aircraft can also help in the study of hard-to-reach locations. Therefore, the main subject of this paper is the localization and classification of objects in images obtained using digital cameras mounted on aircraft. The main focus is on determining the accuracy of object localization and detection using selected types of neural networks, which are the most important indicators of neural network efficiency. The speed of a neural network is also an equally important characteristic as it directly affects its ability to be used in tasks that require fast object localization, such as video surveillance or automated car control systems. The main goal of this study is to study the accuracy of object localization and classification in images obtained with the help of cameras mounted on aircraft, as well as to study the speed of neural networks and determine the effectiveness of their application in real-world conditions. The objectives of this study are to train YOLO v5, SSD, and Faster RCNNs on the VisDrone dataset and to further study them on the vehicle localization dataset. The main goal of this work is to obtain statistics on the performance of neural networks trained on the VisDrone dataset. On the basis of the obtained statistics, conclusions are drawn about the effectiveness of the considered neural networks. The conclusions are drawn by considering the speed of the model, localization (IoU), and classification (Precision, Recall) metrics. Possible directions for further development of the topic under study are presented as conclusions.

Spectrally Segmented-Enhanced Neural Network for Precise Land Cover Object Classification in Hyperspectral Imagery

The paradigm shift brought by deep learning in land cover object classification in hyperspectral images (HSIs) is undeniable, particularly in addressing the intricate 3D cube structure inherent in HSI data. Leveraging convolutional neural networks (CNNs), despite their architectural constraints, offers a promising solution for precise spectral data classification. However, challenges persist in object classification in hyperspectral imagery or hyperspectral image classification, including the curse of dimensionality, data redundancy, overfitting, and computational costs. To tackle these hurdles, we introduce the spectrally segmented-enhanced neural network (SENN), a novel model integrating segmentation-based, multi-layer CNNs, SVM classification, and spectrally segmented dimensionality reduction. SENN adeptly integrates spectral–spatial data and is particularly crucial for agricultural land classification. By strategically fusing CNNs and support vector machines (SVMs), SENN enhances class differentiation while mitigating overfitting through dropout and early stopping techniques. Our contributions extend to effective dimensionality reduction, precise CNN-based classification, and enhanced performance via CNN-SVM fusion. SENN harnesses spectral information to surmount challenges in “hyperspectral image classification in hyperspectral imagery”, marking a significant advancement in accuracy and efficiency within this domain.

Transfer Learning and Few-Shot Learning Based Deep Neural Network Models for Underwater Sonar Image Classification With a Few Samples

Acoustic imaging sonar systems are widely used for long-range underwater surveillance in various civilian and military applications. They provide 2-D images of underwater objects, even in turbid water conditions where optical underwater imaging systems fail. Achieving high accuracy in automatic deep learning based underwater image classification remains an open problem due to insufficient data availability, poor image resolution, low signal-to-noise ratio surroundings, etc. In this study, we conduct a comparative analysis of different advanced deep learning approaches, i.e., transfer learning and few-shot learning, to address the problem of automatic object classification in sonar images, using a few samples of data. Specifically, two metric learning-based approaches, i.e., siamese network and triplet network as well as library-based approaches, are studied under the few-shot learning paradigm. Extensive experiments are conducted on a novel custom-made dataset developed in-house, along with the publicly available SeabedObjectsKLSG dataset. In addition, the effectiveness of the sampling technique in handling class imbalance during model training is also investigated in this work. Our experimental results highlight that the few-shot learning based approach is a promising direction for future research on underwater image classification with a few samples.

Accuracy potential of the Convolutional Neural Network (CNN) in recognizing traditional clothing

The diversity of cultures in Indonesia is proof that Indonesia is a country that is rich in cultural diversity. Many foreign tourists who want to know about culture in Indonesia are not directly proportional to the media to introduce culture in Indonesia. Therefore, this study aims to classify images of traditional clothing by detecting images of traditional clothing sent to the application to determine the name of the traditional soldier. These images will be converted into vectors and processed to find the closest similarity level. The Deep Learning method which currently has the most significant results in image recognition is the Convolutional Neural Network (CNN). The analysis carried out resulted in an accuracy of 0.7934 with an epoch of 20 and a data set of 700 data. The accuracy value is 0.7934 which is a large enough number to determine the correct classification of image objects. This is proven by testing on 10 different images and only 1 image is inaccurate with 90% accuracy.

DEEP LEARNING ARCHITECTURE BASED ON CONVOLUTIONAL NEURAL NETWORK (CNN) IN IMAGE CLASSIFICATION

In current technological developments, Deep Learning is one of the most popular studies today, especially in the fields of machine learning and computer vision, GPU Acceration Technology is one of the reasons for the development of Deep Learning. Deep Learning has a very good ability to solve classic problems in the field of computer vision, one of which is in the case of object classification in images. one of the deep learning methods that is often used in image processing is the Convolution Neural Network (CNN) which is a development of the Multi Layer Perceptron method. This study uses the CNN architecture which consists of a convolution layer, as well as a fully connected layer, and will also determine the appropriate Optimizer and Loss function for CNN. The implementation of this method uses Google Colab (Tensorflow and Keras) with the Python programming language. In the training process using CNN, setting the number of epochs is done to improve accuracy in image classification, in the first scenario using epoch 20 produces an average accuracy of 99.45 with a loss value of 1.66. In the second scenario using epoch 15 produces an average accuracy value of 99.00 with a loss value of 2.92. then in the third scenario with a number of epochs 10 it produces an average accuracy value of 95.55 with a loss value of 95.55, while in the last scenario with a number of epochs 5 it produces an average accuracy value of 73.6 with a loss value of 51.92. From the 4 trial scenarios using the CNN method gives effective results and produces a fairly good accuracy value with an average accuracy and loss value of 99.99%. As well as the results of an average loss of 4.

Improving the Performance of Object Detection by Preserving Balanced Class Distribution

Object detection is a task that performs position identification and label classification of objects in images or videos. The information obtained through this process plays an essential role in various tasks in the field of computer vision. In object detection, the data utilized for training and validation typically originate from public datasets that are well-balanced in terms of the number of objects ascribed to each class in an image. However, in real-world scenarios, handling datasets with much greater class imbalance, i.e., very different numbers of objects for each class, is much more common, and this imbalance may reduce the performance of object detection when predicting unseen test images. In our study, thus, we propose a method that evenly distributes the classes in an image for training and validation, solving the class imbalance problem in object detection. Our proposed method aims to maintain a uniform class distribution through multi-label stratification. We tested our proposed method not only on public datasets that typically exhibit balanced class distribution but also on private datasets that may have imbalanced class distribution. We found that our proposed method was more effective on datasets containing severe imbalance and less data. Our findings indicate that the proposed method can be effectively used on datasets with substantially imbalanced class distribution.

Yoga Pose Estimation Using YOLO Model

Yoga, an historic exercise for every person and intellectual nicely-being, has gained large recognition in todays world . Monitoring yoga postures is essential for ensuring proper form, but yoga without an yoga professional is not good for person. In this research, we go deeply into the area of video processing ,image processing and deep learning, providing a new approach to yoga pose estimation. Leveraging the modern day YOLO (You Only Look Once) pose version, we suggest an revolutionary answer for real-time yoga pose detection in both images and video. The YOLO structure is customized and adaptative to recognizing and detecting yoga postures, maximizing accuracy and performance. YOLO is a popular deep learning algorithm used for object detection and classification in images and videos. It's known for its speed and efficiency. We inspect the result with in the parameter and also use customize data. We specially design this model for yoga Beginner and Intermediate those who cannot afford personal trainer or not able to mange time. Additionally, we renowned the limitations encountered in the course of our studies, also covering the way for future investigations. Keywords: Pose Estimation,YOLO,KeyPoints Detection,Virtual yoga ,ML models

A Deep Learning-Based Hyperspectral Object Classification Approach via Imbalanced Training Samples Handling

Object classification in hyperspectral images involves accurately categorizing objects based on their spectral characteristics. However, the high dimensionality of hyperspectral data and class imbalance pose significant challenges to object classification performance. To address these challenges, we propose a framework that incorporates dimensionality reduction and re-sampling as preprocessing steps for a deep learning model. Our framework employs a novel subgroup-based dimensionality reduction technique to extract and select the most informative features with minimal redundancy. Additionally, the data are resampled to achieve class balance across all categories. The reduced and balanced data are then processed through a hybrid CNN model, which combines a 3D learning block and a 2D learning block to extract spectral–spatial features and achieve satisfactory classification accuracy. By adopting this hybrid approach, we simplify the model while improving performance in the presence of noise and limited sample size. We evaluated our proposed model on the Salinas scene, Pavia University, and Kennedy Space Center benchmark hyperspectral datasets, comparing it to state-of-the-art methods. Our object classification technique achieves highly promising results, with overall accuracies of 99.98%, 99.94%, and 99.46% on the three datasets, respectively. This proposed approach offers a compelling solution to overcome the challenges of high dimensionality and class imbalance in hyperspectral object classification.

Improving the quality of object classification in images by ensemble classifiers with stacking

The object of research is the process of classifying objects in images. The quality of classification refers to the ratio of correctly recognized objects to the number of images. One of the options for improving the quality of classification is to increase the depth of neural networks used. The main difficulties along the way are the difficulty of training such neural networks and a large amount of computing that makes it difficult to use them on conventional computers in real time. An alternative way to improve the quality of classification is to increase the width of the neural networks used, by constructing ensemble classifiers with staking. However, they require the use of classifiers at the first stage with different structured processing of input images, characterized by high quality classification and relatively low volume of calculations. The number of known such architectures is limited. Therefore, the problem arises of increasing the number of classifiers at the first stage of the ensemble classifier by modifying known architectures. It is proposed to use blocks of rotation of images at different angles relative to the center of the image. It is shown that as a result of structured image processing by the starting classifier, processing of rotated image leads to redistribution of errors on image set. This effect makes it possible to increase the number of classifiers in the first stage of the ensemble classifier. Numerical experiments have shown that adding two analogs of the MLP-Mixer algorithm to known configurations of ensemble classifiers reduced the error from 1 to 11 % when working with the CIFAR-10 dataset. Similarly, for CCT, the error reduction was between 2.1 and 10 %. In addition, it has been shown that increasing the MLP-Mixer configuration in width gives better results than increasing in depth. A prerequisite for the success of using the proposed approach in practice is the structured image processing by the starting classifier

Identifikasi Nominal Mata Uang Rupiah Bagi Penyandang Tunanetra Dengan Algoritma Convolutional Neural Network Berbasis Android

What frequently occurs in today's life is the process of economic transactions, particularly during buying and selling. When engaging in these transactions, people always utilize money as the payment method. This implies that money serves a rather crucial function during transactions. However, for visually impaired individuals, the transaction process becomes problematic because they face difficulties in recognizing the denominations on banknotes. Deep Learning is a burgeoning field within Machine Learning that has shown significant development. Among data practitioners, Deep Learning is widely popular due to its exceptional capabilities in computer vision. One notable application is object classification in images. By implementing one of the Machine Learning methods that can be employed to classify Indonesian rupiah currency, Convolutional Neural Network (CNN) can be utilized. Based on the constructed architecture, the Convolutional Neural Network (CNN) method encompasses various types, with VGG-16 being one of them. In this study, 7 classes of Indonesian rupiah currency images were employed, each consisting of 190 images. The obtained accuracy rate is 83% when utilizing the VGG-16 architecture.

DETEKSI PENYAKIT BERCAK COKLAT, COKLAT SEMPIT DAN HAWAR MELALUI SPEKTRUM WARNA CITRA DIGITAL DAUN PADI MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

Rice is a prominent food crop commodity and has high potential in the agricultural sector, where rice is a staple food source for Indonesian people. This rice plant certainly has several obstacles, one of which is the presence of rice plant disease attacks through rice leaf spot which can cause crop failure, causing farmers to experience many losses and resulting in poor crop quality, namely empty or empty rice. The long identification process and if the treatment for this disease is very slow will cause the cost of treatment to swell. The use of digital image processing technology in solving problems in this study is to identify rice diseases through digital images based on the morphology of rice leaf spots. One way is by image classification or object classification in the image. The method that can be used in classifying this image is the Convolutional Neural Network (CNN). The accuracy obtained from the Convolutional Neural Network method is based on the 2 types of architecture used, namely the Letnet-5 architecture produces an accuracy of 85% and the Custom architecture produces an accuracy of 90%.

Vehicle Detection Using YOLOv5

Object detection is a computer vision method that allows for the identification and localization of specific classes of objects in images or videos. It goes beyond simple object classification and helps provide a better understanding of the object in question. Object detection has numerous applications, including automating business processes like inventory management in retail. It can detect objects that occupy between 2% and 60% of an image's area and clusters of objects as a single entity. Additionally, it can localize objects at high speeds, typically greater than 15 frames per second. Vehicle detection is a crucial component in the development of autonomous vehicles, enabling them to identify and perceive objects in their environment. It involves identifying and locating vehicles in image or video frames and has various applications in surveillance and security systems. There are different techniques and models for object detection, including traditional image processing methods and modern deep learning networks. Traditional methods like Viola- Jones, SIFT, and histogram of oriented gradients do not require historical data for training and are unsupervised. Popular image processing tools like OpenCV can be used for these techniques. On the other hand, modern deep learning networks like CNN, RCNN, YOLO, ResNet, RetinaNet, and MANet are supervised and efficient for object detection.

A hybrid Fuzzy Logic and Convolution Neural Network (FIS-CNN) for automatic detection and classification of objects in comet assay images

A hybrid Fuzzy Logic and Convolution Neural Network (FIS-CNN) for automatic detection and classification of objects in comet assay images