Computer Vision Based Deep Learning Approach for the Detection and Classification of Algae Species Using Microscopic Images

Object detection is a fundamental problem in computer vision, with applications spanning self-driving cars, surveillance systems, medical imaging, robotics, and smart cities. Among the myriad of algorithms developed for this task, the You Only Look Once (YOLO) family stands out for its ability to perform real-time and accurate object detection. This article provides a comprehensive analysis of the YOLO algorithm series, from YOLOv1 to YOLOv8, evaluating them across key performance metrics, including precision, recall, mean Average Precision (mAP), frames per second (FPS), and overall effectiveness. Unlike traditional two-stage detectors such as R-CNN, YOLO formulates object detection as a single regression problem: a single pass over the image simultaneously predicts bounding boxes and class probabilities. This end-to-end design enables YOLO to achieve high speed while maintaining a competitive accuracy-efficiency trade-off. We examine architectural innovations across YOLO versions, including batch normalization, anchor boxes, residual blocks, feature pyramid networks, and attention mechanisms, and discuss their impact on performance. Lightweight models (e.g., YOLOv5-Nano, YOLOv8-Small) are explored with a focus on their suitability for mobile and embedded systems, highlighting YOLO’s adaptability to resource-constrained environments. Challenges such as small object detection, occlusion, and domain-specific tuning are also addressed. This article serves as a practical guide for researchers, developers, and practitioners aiming to leverage YOLO for real-world object detection tasks.

Nursery plays an important role on starting chili cultivation, determining the crop health, fertility from disease, and growth performance. Early-stage germination detection is necessary to minimize nursery failure and improve plant health, but manual detection is challenging for large scale nursery in the greenhouse. The aim of this research was to develop an automatic detection model integrated with a You Only Look Once (YOLO) based deep learning algorithm using RGB camera to monitor the chili germination stages. Method to detect germination was YOLO with several steps, included: (1) early stages chili germination images acquisition, (2) datasets preparations, (3) dataset annotation and labeling, (4) model development using deep learning YOLO algorithms, and (5) model testing and validation. The training of 11,423 images was conducted utilizing the YOLOv5 and YOLOv8 algorithms, which categorized into, three classes (germinated, not germinated, and cotyledon appearance). The model was evaluated using mean Average Precision (mAP), precision, accuracy, and recall with the respective values of 0.697, 73%, 75%, and 73% for YOLOv8, and 0.664, 70%, 73%, and 70% for YOLOv5. Both model achieved high accuracy, but YOLOv8 was better to detect and classify chili seedling growth stages than YOLOv5. This study also demonstrated that model can be implemented in real applications integrated with automatic monitoring system included in the model. Keywords: Chili seedling, Deep learning, Detection system, Germination.

Automatic target recognition (ATR) is a challenging task for several computer vision applications. It requires efficient, accurate, and robust methods for target detection and target identification. Deep learning has shown great success in many computer vision applications involving color RGB images. However, the performance of these networks in ATR with infrared sensor data needs further investigation. In this paper, we propose a multistage automatic target detection and recognition (ATDR) system that performs both target detection and target classification on infrared (IR) imagery using deep learning. Our system processes large IR image frames where targets take <1 % of the total number of pixels. First, we train a state-of-the-art object detector you only look once (YOLO) to localize all potential targets in the input image frame. Then, we train a convolutional neural network (CNN) to identify these detections as targets or false alarms. In this second phase, we adapt and analyze the performance of three CNN architectures: a compact and fully connected CNN, VGG16 with batch normalization, and a wide residual neural network (WRN). We also explore the use of a loss function that optimizes directly the area under the receiver operating characteristic (ROC) curve (AUC), and adapt it to our ATR application. To enhance the robustness of the proposed ATR to perturbation and variations introduced during the detection stage, we train our CNN classifiers on automatically detected targets using YOLO, in addition to ground truth bounding boxes and apply selected data augmentation techniques. To simulate real testing environments, where the spatial location of the targets within the image frame is unknown, only YOLO-detected boxes are used during validation. We evaluate our ATDR on a real benchmark dataset that includes different vehicles captured at different resolutions. Our experiments have shown that YOLO can detect most of the targets at the expense of generating a high number of false alarms. We show that the VGG-16 network with batch normalization, which is the best performing model, can correctly identify the classes of the targets, as well as classify the majority of YOLO’s false detections into an additional nontarget class. We also show that the proposed training modification to optimize an AUC-based loss function for ATR proved to be advantageous mainly in identifying difficult targets.

YOLO Based Breast Masses Detection and Classification in Full-Field Digital Mammograms

Cigarettes are processed products from tobacco products which are used by burning and then smoked. Smoking activities are often found in everyday life, including in public infrastructure. The approach taken to prevent this activity generally uses manual information or human intervention. In terms of this approach, there are often many problems and failures due to the lack of manpower and supporting rules. Therefore, this study was structured with the aim of being able to detect smoking objects in real time using the You Only Look Once (YOLO) method. YOLO which is based on deep learning is very good at detecting objects, this model provides a single convolution neural network in assigning location and classification. So that in its application, YOLO is very fast in detecting and recognizing objects. This study conducted experiments on the training dataset in testing the YOLOv3, YOLOv3-Tiny and YOLOv4 models. The best training results were obtained in the YOLOv4 model with a composition of 80% training and 20% validation data sharing with a Mean Average Precision (mAP) of 92.54% and an F1-Score of 0.89. This study also conducted experiments on testing to detect cigarettes in real time, where the system can detect cigarettes up to a distance of 4.5 meters, and the highest detection accuracy is obtained at a distance of 1 meter, namely 99.03%.

and AI-assisted image manipulation tools, which The emergence of advanced image manipulation techniques in the digital age has made it extremely difficult to detect and categorize forged images. In order to identify and classify image forgeries, this study proposes a deep learning-based method that combines a Convolutional Neural Network (CNN) classifier with the You Only Look Once (YOLO) object detection model. The suggested system uses sophisticated feature extraction techniques to categorize images into authentic, copy-move, spliced, and deepfake forgeries after being trained on a custom dataset of manipulated images. While CNN-based classification offers accurate categorization, our experimental results show how reliable and effective YOLO is at locating forgery regions. Because of its high accuracy, the suggested model is a useful tool for security and digital forensics applications. Keywords: Image Forgery, YOLO, CNN, Deep Learning, Classification, Digital Forensics

Object detection from deep learning has performed better in many applications, and yet real images usually depict challenges such as noise blurring or jitter rotation. Such problems generally degrade the accuracy and the efficiency of object detection systems dramatically. The purpose of this work is to identify objects satisfactorily by applying a method called You Only Look Once (YOLO), which tackles numerous problems while it provides plenty of advantages over other solutions.Unlike other algorithms that are known as Convolutional Neural Networks (CNN)or Fast-Convolutional Neural Networks, process images partially by focusing on specific areas. YOLO is different from that; it looks at an entire image at once while predicting bounding boxes and class probabilities for objects within these boxes by making a single forward pass of the network. This holistic approach makes YOLO significantly faster and much more efficient than other algorithms that process parts of the image separately.For this project, we have used the YOLO algorithm for detecting all types of objects in a real-time scenario. Moreover, an Android Application has been developed incorporating YOLO-based object detection for enhancing user experience. This application does not only detect objects in images or live video feeds but also provides voice feedback to the user. Such an enhancement would make the system much more accessible for individuals with visual impairments because they could receive immediate auditory information about the objects detected in their environment.

Integrating advanced technologies such as artificial intelligence (AI) with traditional agricultural practices has changed how activities are developed in agriculture, with the aim of automating manual processes and improving the efficiency and quality of farming decisions. With the advent of deep learning models such as convolutional neural network (CNN) and You Only Look Once (YOLO), many studies have emerged given the need to develop solutions to problems and take advantage of all the potential that this technology has to offer. This systematic literature review aims to present an in-depth investigation of the application of AI in supporting the management of weeds, plant nutrition, water, pests, and diseases. This systematic review was conducted using the PRISMA methodology and guidelines. Data from different papers indicated that the main research interests comprise five groups: (a) type of agronomic problems; (b) type of sensor; (c) dataset treatment; (d) evaluation metrics and quantification; and (e) AI technique. The inclusion (I) and exclusion (E) criteria adopted in this study included: (I1) articles that obtained AI techniques for agricultural analysis; (I2) complete articles written in English; (I3) articles from specialized scientific journals; (E1) articles that did not describe the type of agrarian analysis used; (E2) articles that did not specify the AI technique used and that were incomplete or abstract; (E3) articles that did not present substantial experimental results. The articles were searched on the official pages of the main scientific bases: ACM, IEEE, ScienceDirect, MDPI, and Web of Science. The papers were categorized and grouped to show the main contributions of the literature to support agricultural decisions using AI. This study found that AI methods perform better in supporting weed detection, classification of plant diseases, and estimation of agricultural yield in crops when using images captured by Unmanned Aerial Vehicles (UAVs). Furthermore, CNN and YOLO, as well as their variations, present the best results for all groups presented. This review also points out the limitations and potential challenges when working with deep machine learning models, aiming to contribute to knowledge systematization and to benefit researchers and professionals regarding AI applications in mitigating agronomic problems.

The presence of chironomid larvae in tap water has sparked public concern regarding the water supply system in South Korea. Despite ongoing efforts to establish a safe water supply system, entirely preventing larval occurrences remains a significant challenge. Therefore, we developed a real-time chironomid larva detection system (RT-CLAD) based on deep learning technology, which was implemented in drinking water treatment plants. The acquisition of larval images was facilitated by a multi-spectral camera with a wide spectral range, enabling the capture of unique wavelet bands associated with larvae. Three state-of-the-art deep learning algorithms, namely the convolutional neural network (CNN), you only look once (YOLO), and residual neural network (ResNet), renowned for their exceptional performance in object detection tasks, were employed. Following a comparative analysis of these algorithms, the most accurate and rapid model was selected for RT-CLAD. To achieve the efficient and accurate detection of larvae, the original images were transformed into a specific wavelet format, followed by preprocessing to minimize data size. Consequently, the CNN, YOLO, and ResNet algorithms successfully detected larvae with 100% accuracy. In comparison to YOLO and ResNet, the CNN algorithm demonstrated greater efficiency because of its faster processing and simpler architecture. We anticipate that our RT-CLAD will address larva detection challenges in water treatment plants, thereby enhancing water supply security.

The objective of this study is to examine two powerful components: the YOLO (You Only Look Once) framework for object recognition on edge devices and the MobileNet architecture. With the rising demand for real-time, efficient, and accurate object detection in constrained environments, these models offer distinct advantages suited to different applications. YOLO is renowned for its high accuracy and speed, making it ideal for complex detection tasks, whereas MobileNet is optimized for efficiency, enabling deployment on devices with limited computational resources. The paper discusses the evolution of these models, their architectural differences, and their respective strengths and limitations when implemented on edge devices. Furthermore, we explore the feasibility of integrating these frameworks into a hybrid model that leverages the lightweight feature extraction of MobileNet and the robust detection capabilities of YOLO. Such a hybrid approach could significantly enhance real-time object detection performance across a wide range of hardware platforms.&nbsp; Researchers and practitioners seeking to deploy advanced object detection models in real-world applications, particularly where computational efficiency and accuracy are paramount may find this review as a valuable resource.

Exxon Valdez. Cuyahoga River. Sandoz and the Rhine River. The names trigger memories of human activities that devastated aquatic ecosystems. The magnitude of such disasters prompted many countries to develop regulatory frameworks to manage risks of chemical contaminants to the environment and human health. For example, pesticides are thoroughly tested for adverse ecological effects. When unacceptable risks are identified, a variety of management efforts may be employed to minimize damage, including adjusting the amount or timing of pesticide application to riparian habitat to reduce the pesticide’s contact with adjacent aquatic systems. In contrast to chemical contaminants, however, standard management approaches are poorly developed for the aquatic toxins produced by algae during harmful algal blooms (HABs), such as the infamous ‘‘red tide.’’ Algal blooms result from a period of rapid growth of algae in response to a variety of environmental factors, and HABs produce toxins that negatively impact other organisms, including other aquatic life and even humans. The global increase in frequency and magnitude of HABs over the past few decades has resulted in damaging effects that range frommassive fish kills to public health threats such as ciguatera poisoning. Although the majority of HAB research has occurred in marine systems, on species such as Pfiesteria sp., Gambierdiscus toxicus, and Karenia brevis, HABs are increasing in inland waters. Unfortunately, the environmental conditions that cause HABs are complex and often species-specific, making it difficult— if not impossible—to develop a universal approach for managing HABs.

شرایط اقلیمی به عنوان یکی از عوامل اصلی در شکل گیری بلوم جلبکی در اکثر نواحی دریاچه‌ای، دریایی و اقیانوسی دنیا مطرح است. هدف اصلی این تحقیق، شناسایی الگوهای نقشه ای اقلیمی در زمان توسعه و گسترش جلبکی در سطح دریا و تعیین شرایط اقلیمی آن می‌باشد. داده‌های مورد استفاده در این تحقیق شامل فشار هوا در تراز 1000 و 500 هکتوپاسکال، باد مداری و نصف النهاری و قائم، درجه دمای هوا و آب، کلروفیل است. روش تحقیق در این پژوهش به صورت الگوی محیطی به گردشی بوده است. برای انجام این تحقیق ابتدا زمان شکل گیری بلوم جلبکی تعیین و سپس عناصر اقلیمی همزمان با آن نقشه سازی شدند و در ادامه نیز تحلیل و نتیجه گیری انجام گرفت. نتایج این تحقیق حاکی از آن است که در زمان شکل گیری بلوم جلبکی بر روی خزر جنوبی، الگوی نقشه ای فشار هوا به صورت یک سامانه پرفشار با تداوم زمانی زیادی دیده می‌شود و منشا اصلی این پرفشار بر روی اقیانوس اطلس در حوالی پرفشار جنب حاره آزور قرار دارد. الگوی وزش باد به تبع این الگوی فشار در جهت عقربه ساعت برروی منطقه در حال گردش است. همچنین جریانات عمودی هوا حاکی از آن است که در حوالی جنوب غربی خزر نزول ضعیفی از هوا دیده می‌شود.

Autonomous vehicles will establish their predominance in the near future and humans will experience a hassle-free travel as these vehicles do not demand human intervention. Autonomy diminishes disasters that may happen due to driver’s negligence. Emergency Vehicles (EVs) play a vital role in saving lives. An unobstructed path is to be provided to them to ease the mobility of EVs along busy roads. In this paper, the EVs are identified using Deep Learning (DL) based algorithms. Though they are driven by Neural Networks (NNs), there are some situations in which they have to mimic a human. The ability to perceive and respond to EVs is addressed in this paper. Self-Driving Vehicles (SDVs) are to be incorporated with the knowledge of a fast approaching EV using algorithms like Convolutional Neural Network (CNN), Fast Region-based Convolutional Network (Fast R-CNN) and You Only Look Once (YOLO) algorithm. It is seen that YOLO offers better results.

Cultural heritage sites are of great significance to human and they are the important treasures of mankind. They convey the culture of each nation and country. Therefore, protecting their safety and carrying on cultural inheritance has farreaching significance. At the present time, as the universality of surveillance systems continues to increase, almost all cultural heritage sites are equipped with surveillance cameras. These surveillance cameras allow the administrator to view a display screen at a specific place for remote monitoring. However, currently, in most of cultural heritage sites, the videos captured by these surveillance cameras are monitored artificially and considering the fatigue of people, this method is less efficient. In recent years, with the powerful support of big data and GPU, artificial intelligence technology with deep learning as the core has developed rapidly and has been widely used in many fields. Therefore, this paper proposes to apply the computer vision based on convolutional neural network (CNN) to monitor the number of tourists in an exhibition hall of the Forbidden City by analyzing the surveillance video and then calculate the tourist density in this exhibition hall. After applying the method to every open area in the Forbidden City, by comparing the distribution of the tourist density in each open area, the tourists can better plan their visiting routes and the managers can schedule personnel more easily. The deep learning algorithm used in this paper is You Only Look Once (YOLO) v3. One of the advantages of YOLO v3 is that it has a fast computing speed and the requirements for running platforms is relatively low, which can even be run on mobile terminals. And its accuracy is sufficient for human recognition

Real-time object detection and tracking in video streams has become a fundamental component of modern intelligent systems, enabling applications in surveillance, autonomous driving, robotics, healthcare monitoring, and smart cities. The rapid advancement of deep learning techniques has significantly improved the accuracy and efficiency of detecting and tracking multiple objects under complex and dynamic environments. This study presents a deep learning–based framework for real-time object detection and tracking in continuous video streams, emphasizing both computational efficiency and detection robustness.The proposed system integrates a state-of-the-art convolutional neural network (CNN)-based object detector with a reliable multi-object tracking algorithm. The detection module identifies objects of interest in each frame, while the tracking component maintains consistent identities across consecutive frames by utilizing motion prediction and feature association strategies. To achieve real-time performance, the model is optimized through lightweight network architectures and parallel processing on GPU hardware. Data augmentation and transfer learning techniques are employed to enhance generalization and reduce training time. Performance evaluation is conducted on benchmark video datasets using standard metrics such as precision, recall, mean Average Precision (mAP), and tracking accuracy. Experimental results demonstrate that the proposed framework achieves high detection accuracy while maintaining low latency, making it suitable for real-time deployment. Furthermore, the system effectively handles challenges such as occlusion, scale variation, and illumination changes. This research presents a comprehensive study on real-time object detection and tracking in video streams using deep learning techniques. The proposed framework integrates YOLO-based object detection with Deep SORT multi-object tracking to achieve robust spatial localization and temporal identity preservation. The study evaluates performance using benchmark datasets including COCO, MOT17, and KITTI. Mathematical formulations of detection loss, Kalman filtering, and data association are presented. Experimental analysis using precision, recall, mAP, MOTA, ROC-AUC, and PR-AUC demonstrates that the system achieves high detection accuracy while maintaining real-time performance above 35 frames per second. The findings confirm that deep learning-based frameworks provide scalable and efficient solutions for surveillance, autonomous vehicles, and intelligent monitoring systems.