http://hdl.handle.net/123456789/98 Sat, 22 Aug 2026 06:57:51 GMT 2026-08-22T06:57:51Z http://hdl.handle.net/123456789/21512 AGRITECH: EMPOWERING FARMERS WITH SEAMLESS MARKET ACCESS Ihsan, Muhammad Asad Reg # 79002; Alam, Muhammad Ateeb Reg # 79011; Iram, Benish Reg # 79253 AGRITECH: Empowering Farmers is a transformative web application that endeavors to bridge the growing disconnect between local fanners and consumers, with a primary focus on fostering sustainable agricultural practices. This innovative platform to the formidable challenges faced by local farmers, chiefly emerges as a response attributed to the ascendancy of large-scale agriculture and the retail industry’s facilitate direct interactions and transactions consolidation. In essence, Agritech aspires to between farmers and consumers, thereby promoting environmentally conscious livelihoods of our dedicated agriculture, fostering local communities, and enhancing the farmers. The implementation of Agritech unfolds through a meticulous sequence of steps. interface and the Commencing with the development of the application's user establishment of a robust backend infrastructure, we actively collaborate with farmers and other stakeholders to ensure that the web app aligns seamlessly with their requirements. Simultaneously, an all-encompassing marketing and outreach strategy will be crafted to raise awareness about the application and entice a diverse user base. Lastly, Agritech will partnerships with local farmers, cooperatives, and like-minded actively pursue organizations to forge a resilient network of users and ardent supporters. As Agritech embarks on this transformative journey, it becomes increasingly evident that its contribution extends beyond mere technological advancement. It signifies sustainable and equitable agricultural ecosystem, a more a paradigm shift towards underlining the importance of community and collective action in addressing the pressing challenges faced by our local farmers. Agritech promises to be a beacon of hope for those and sustainable future who till the land, offering them a lifeline to a more prosperous while enriching the choices available to consumers. Supervised by Azeema Sadia Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/123456789/21512 2025-01-01T00:00:00Z http://hdl.handle.net/123456789/21508 AUGMENTED REALITY BASED ASSEMBLY GUIIDE Junaid, Shayan Reg # 79009; Irtaza, Syed Muhammad Reg # 79908; Kamran, Huzaifa Reg # 79739 The goal of this project is to create an augmented reality (AR) application that offers a smooth solution for interior design and assembly assistance. This report highlights the initial phase of the project, focusing on the interior design component, where users interactively position 3D furniture models within their actual surroundings. Utilizing Unity as the development platform, the project takes advantage of its XR framework along with AR Core and AR Kit APIs to ensure it works seamlessly on both Android and iOS devices. To enable real-time furniture placement, we make use of AR's plane detection features to estimate room sizes and identify flat surfaces such as floors and tables. By projecting a spatial mesh, the application can recognize horizontal planes and adjust the scale of 3D objects, accordingly, ensuring they appear proportionate and aligned. The system offers visual cues to help useis preview placements, thereby improving accuracy and enhancing the overall user experience. For creation of the catalog of 3D models a user can view, we will be making a custom algorithm that can use depth estimation and mesh reconstruction techniques to accurately generate a 3D model of an object from a single picture of the object. The NoSQL database, powered by Firebase Firestore, supports the efficient storage and retrieval of furniture models and user preferences. By merging real-time spatial mapping with advanced AR features—such as on-the-fly conversion of 2D images into fully manipulate 3D assets—the application turns interior design into an engaging and immersive experience. Future phases will look to add AR-based assembly guidance, broadening the application’s functionality for practical use by end users. Supervised by Dr. Raheel Siddiqui Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/123456789/21508 2025-01-01T00:00:00Z http://hdl.handle.net/123456789/21506 LEAFINSIGHT: A SMART DETECTION OF VEGETABLE DISEASES USING DEEP VISION Samad, Abdul Reg # 78982; Bakhtiar, Shalal Reg # 79904; Qureshi, Anas Ahmed Reg # 79245 In the modern agricultural world, early detection of plant diseases is critical for growing healthy crop and reducing losses. Old and traditional methods to identify a plant disease are often time consuming and requires a expert knowledge, which makes them less accessible to regular farmers and people. This project focuses on the development of a mobile based disease detection system that uses an advanced deep vision techniques to accurately identify diseases in vegetable plants very specifically Tomato, and Bell Pepper (Capsicum) crops. This system focuses on key leaf Potato, diseases, including Late Blight and Early Blight of Potatoes, Tomato Mosaic Virus of We studied various Convolutional Tomatoes, and Bacterial Spot of Bell Peppers. Neural Network (CNN) architectures, like MobileNetV2, VGG16, ResNet50, EfficientNetBO, and InceptionV2 to select model that is suitable for our project and gain good knowledge about the overall model accuracy, efficiency, and behaviour. This deep analysis significantly contributed to our understanding of machine learning and deep vision techniques. Based on our findings, we used MobileNetV2 model which is suitable for mobile application. Our model achieved an accuracy of 95.5%. different Environmental conditions. cameras. This allows plant disease detection from many This model communicates with the custom mobile application we developed through fastAPI, which allows users to scan plant leaves for diseases using their smartphone The mobile app, along with the FastAPI based backend, is deployed cloud service to make sure smooth, reliable, and efficient system performance Supervised by Fatima Basheer Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/123456789/21506 2025-01-01T00:00:00Z http://hdl.handle.net/123456789/21509 AUTOMATIC DETECTION OF DIABETIC RETINOPATHY Atta, Saheal Reg # 79022; Sajid, Muhammad Mohid Reg # 79003; Ahmed, Shoaib Reg # 54276 Diabetic retinopathy (DR) is the leading reasons for people losing their sight across the world, particularly for those suffering from diabetes. Traditional diagnosis processes are slow and rely heavily on human interaction which can lead to errors. Advances in technology have made it possible to develop systems that automate processes, much like the one this project aims to create. Through great research in neuroimaging data now scan retinal images and processing, CNNs (Convolutional Neural Networks) categorize the extent of DR damage £4]. model as accuracy can This project will first integrate both AI image Processing and deep learning techniques to achieve maximum accuracy when developing algorithms. After refining and testing them extensively, Such evaluation with performance indicators will be used for the final , sensitivity, specificity, and many more, by taking advantage of the vast repositories available online. Some of the datasets provided online include the EyePACS database on Kaggle and Messidor [2]. In the most effective and optimal use of this DR detection project, less populated regions lacking ophthalmologists will have improved accuracy of diabetic patient treatment prior to them reaching a stage needing eyesight surgery. With this non-invasive system, patients will be able to receive timely treatment, greatly reducing die risk of blindness. On a larger scope, abundant possibilities for deeper research will be provided Supervised by Dr. Asif Aziz Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/123456789/21509 2025-01-01T00:00:00Z