Browsing by Subject "deep learning"
Now showing items 1-4 of 4
-
Accuracy Improvement for Segmentation and Classification of Wound Tissues through Region-Focus Training
Collection: Theses (Master's degree) - Information Technology and Digital Innovation / วิทยานิพนธ์ - เทคโนโลยีสารสนเทศและนวัตกรรมดิจิทัลType: Thesis(Silpakorn University, 18/6/2021)Segmentation of chronic wound regions from an image aids in following up a wound-healing process without a wound contact. Unlike a wound tracing method, the image-based method imposes no risk of infection. This method is ... -
Color Data Augmentation through Learning Color-Mapping Parameters between Cameras
Collection: Theses (Master's degree) - Information Technology and Digital Innovation / วิทยานิพนธ์ - เทคโนโลยีสารสนเทศและนวัตกรรมดิจิทัลType: Thesis(Silpakorn University, 12/7/2019)In order to achieve a more accurate deep learning model, we need large amount of data. For imaging application, color data augmentation is usually required. Color jittering is a common current practice for such augmentation ... -
Deep Question Classifier and Explainable AI for Detection of Potential Problems in Training Data
Collection: Theses (Master's degree) - Information Technology and Digital Innovation / วิทยานิพนธ์ - เทคโนโลยีสารสนเทศและนวัตกรรมดิจิทัลType: Thesis(Silpakorn University, 24/11/2023)Currently, the processing of natural language holds diverse applications with distinct limitations. A common issue in specialized tasks is the limited availability of data, necessitating the search for appropriate models ... -
Wound-Region Segmentation from Image by Using Deep Learning and Various Data Augmentation Methods
Collection: Theses (Master's degree) - Information Technology and Digital Innovation / วิทยานิพนธ์ - เทคโนโลยีสารสนเทศและนวัตกรรมดิจิทัลType: Thesis(Silpakorn University, 12/7/2019)Chronic wound segmentation is an essential task for evaluating wound and its healing progress. However, accuracy of wound size measurement depends on expertise of the measurer. The measurement result may be significantly ...