Tools
Tools
Ravur, Bharadwaj (2023) Sorting Clothes using Image Segmentation and Object Detection. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (741kB) | Preview |
Abstract
This research delves into the intricate challenges associated with categorizing apparel for both genders in the dynamic landscape of the fashion industry. The study introduces a novel approach by harnessing the power of image segmentation and object identification techniques, specifically Mask R-CNN and YOLOv5s, to automate the apparel sorting process. The application of these advanced methods aims to streamline the classification process and enhance accuracy in apparel categorization.
The investigation employs the DeepFashion2 dataset, a comprehensive repository containing meticulously annotated examples of both consumer and commercial fashion photography, encompassing diverse categories of apparel. Leveraging this dataset for training and evaluation, the research unveils a systematic approach that addresses the complexities of identifying and categorizing fashion items.
The core of the research lies in the development of a robust and dependable system. By seamlessly integrating Mask R-CNN and YOLOv5s, the study showcases the efficacy of these models in achieving accurate apparel sorting. The comparative analysis of these techniques sheds light on their respective strengths and limitations, contributing to a holistic understanding of their applicability.
The research extends its scope beyond theoretical exploration. Practical viability is a central focus, and the study evaluates the proposed system's performance against real-world challenges. In a fashion landscape characterized by rapidly evolving trends and design intricacies, the research seeks to enhance efficiency and accuracy in apparel sorting.
In conclusion, this research underscores the significance of tackling unique challenges presented by the fashion industry. By harnessing the capabilities of Mask R-CNN and YOLOv5s, the study introduces an automated system capable of effectively categorizing gender-specific apparel. The research not only presents a technologically advanced solution but also highlights the broader implications of such advancements in streamlining fashion processes.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Siddig, Abubakr UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Fashion Industry |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 28 Dec 2024 15:50 |
| Last Modified: | 28 Dec 2024 15:50 |
| URI: | https://norma.ncirl.ie/id/eprint/7259 |
Actions (login required)
 |
View Item |