| dc.contributor.author | Waidyanayake, Kusal | |
| dc.date.accessioned | 2026-05-05T03:25:00Z | |
| dc.date.available | 2026-05-05T03:25:00Z | |
| dc.date.issued | 2025 | |
| dc.identifier.citation | Waidyanayake, Kusal (2025) Dermapecia: Hair Loss, Scalp Disease and Dandruff Detection System. BSc. Dissertation, Informatics Institute of Technology | en_US |
| dc.identifier.issn | 20210998 | |
| dc.identifier.uri | http://dlib.iit.ac.lk/xmlui/handle/123456789/3258 | |
| dc.description.abstract | One of the key parts of a human face is head and hair. Hair makes a face shine out more and any problems on the scalp and baldness can cause Anxiety and stress. Anxiety and stress are one of the causes of balding and other scalp problems which in turn is a vicious cycle. Being able to find out if people have these scalp diseases and if they are balding at the comfort of their own home is important. It can begin at any stage in life and can affect teens as well as adults. Although many Male Pattern Baldness is discussed highly, Female Pattern Baldness is not as highly discussed although it is also predominant. To tackle this problem, an image processing system using convolutional neural networks (CNNs) for image classification. By preprocessing images and enhancing feature extraction a model is trained to check for different scalp diseases such as alopecia areata, dandruff. Different architectures and different methodologies will also be attempted to see the benefits of each in aspect to these detections. A minimum of 3 types of models were tested for each of those different detection types. | en_US |
| dc.language.iso | en | en_US |
| dc.subject | Alopecia Areata | en_US |
| dc.subject | Machine Learning | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Image Recognition | en_US |
| dc.title | Dermapecia: Hair Loss, Scalp Disease and Dandruff Detection System | en_US |
| dc.type | Thesis | en_US |