https://ar.iub.edu.bd/handle/11348/618 2026-06-27T12:05:01Z 2026-06-27T12:05:01Z Bhuiyan, Shakibur Rahman Kundu, Dip Siam, Md Tamzed Hossain https://ar.iub.edu.bd/handle/11348/1186 2026-05-11T04:30:17Z 2026-04-25T00:00:00Z

Machine-Vision-Based Bangladeshi Geographical Indication (GI) Dessert Recognition Bhuiyan, Shakibur Rahman; Kundu, Dip; Siam, Md Tamzed Hossain Geographical Indication (GI) certification preserves products whose identity and value are linked to their geographical origin. Despite the cultural and economic importance of Bangladeshi GI-certified desserts, no benchmark dataset or automated recognition system previously existed, creating risks of counterfeiting and mislabeling. This thesis addresses the gap by introducing BD-GI-Desserts13, a dataset of 11,692 images across 13 GI dessert classes, and proposing a machine-vision framework for fine-grained dessert recognition. The study develops a lightweight Custom Convolutional Neural Network (CCNN) and compares it with transfer-learning and traditional machine learning models. Experimental results show that the CCNN achieves 99.37% test accuracy while remaining computationally efficient for real-time web and mobile applications. The proposed framework provides a reproducible baseline for future GI food recognition research in Bangladesh and serves as a decision-support tool rather than a legal certification system.

2026-04-25T00:00:00Z Md Iftekharul, Alam https://ar.iub.edu.bd/handle/11348/1044 2026-06-27T07:03:40Z 2026-01-04T00:00:00Z

Dual-Task Real-Time Low-Light Lane and Pothole Detection for Resource-Constrained Environments Md Iftekharul, Alam Lane detection and road hazard awareness are crucial for ensuring safety in autonomous driving and Advanced Driver-Assistance Systems (ADAS). These systems rely heavily on clear visual cues, which are often compromised in low- light driving scenarios. The challenge is especially pronounced in low- and middle-income countries (LMICs), where poorly illuminated roads, faded lane markings, and unmaintained sur- faces frequently co-occur. Under such conditions, conventional single-model detectors trained for daytime environments degrade sharply, as lane cues and pothole textures often compete in the same field of view. To address this, we present a lightweight dual- model pipeline that integrates a low-light enhancement front end with an OpenCV-based lane delineation pipeline and a YOLOv12 detector for pothole localization. The models run in parallel on shared inputs, and their outputs are fused to generate a unified lane geometry and hazard map in a single pass. The architecture is optimized for modest compute and memory budgets, enabling deployment in resource-constrained settings while maintaining high throughput. Evaluated on evening-time urban road scenes from Bangladesh, achieves 88.7potholes and 89.3FPS on NVIDIA GTX 1050Ti, outperforming a single-detector baseline. These results highlight the potential of our approach for practical, real-time ADAS perception in underserved regions. Index Terms—Low-light imaging, Lane detection, Pothole de- tection, YOLOv12, OpenCV, Image enhancement, Edge comput- ing, Autonomous driving

2026-01-04T00:00:00Z Debnath, Tusher Uddin Ahmed, Shoeb https://ar.iub.edu.bd/handle/11348/945 2026-06-26T19:36:06Z 2024-04-21T00:00:00Z

Revolutionizing COVID-19 X-ray Diagnostics with CNN Model Debnath, Tusher; Uddin Ahmed, Shoeb The emergence of COVID-19 as a global health crisis has necessitated the development of effective detection strategies to combat its spread. The ability to identify infections at an early stage is vital for the timely treatment and recovery of affected individuals. In response to this need, the scientific community has been exploring various methods for diagnosing the virus, including cutting-edge software and deep learning techniques. Among these, the use of advanced deep learning models, such as those integrating Keras's ResNet50V2 and ResNet152V2, has shown promise in enhancing early detection efforts. Building on this foundation, our research introduces an innovative Convolutional Neural Network (CNN) model specifically designed for the automatic detection of COVID-19 through chest X-ray images. The focus of our study is to conduct a comprehensive comparison between this novel CNN model and traditional deep learning approaches in the context of COVID-19 diagnosis. The results of our investigation are highly encouraging, with our model achieving an exceptional accuracy rate of 99.97% and a precision rate of 99.99%. These findings underscore the significant potential of our model to be integrated into clinical workflows, offering a powerful tool for healthcare professionals in the fight against COVID-19. Through this work, we aim to contribute to the ongoing efforts to improve public health outcomes during this challenging time.

2024-04-21T00:00:00Z Shawon, Rafeya Khandaker https://ar.iub.edu.bd/handle/11348/812 2026-06-26T19:21:38Z 2022-09-14T00:00:00Z

IT Store Management System Shawon, Rafeya Khandaker An internship is characterized as gaining real-world experience from a variety of organizations, which aids in connecting academic theory with practical application. It is crucial since this is the first opportunity for a student to gain in-depth practical knowledge from various firms. I had the opportunity to work and learn with the developer team when I was given the opportunity to intern at PMT. The creation of a "IT Store Management System" was the project's main objective. This report covers the entire project that I gained knowledge of throughout my internship. Prior to beginning any projects, I had to finish my learning sessions. During this learning session, I was tasked with creating a landing page, a dashboard, several interfaces for various elements, and some back-end coding. Prior to being given the actual project, it was almost like a talent test. In my report, I've gone into detail about the knowledge I've picked up, the experiences I had, and the work I completed while an intern at Project Management Technology. The majority of my effort on a website application involved building the complete site.

2022-09-14T00:00:00Z