Sürdürülebilir Kalkınma Amaçları

• 1

• BildiriYalnız künye2025/r/kostu/10583
  Hand vein recognition using Mask R-CNN

  Kiyak, Mehmeat; Savas, Burcu Kir; Akdeniz, Fulya

  Medical imaging technologies play a crucial role in critical applications such as dorsal hand vein detection. Traditional methods for locating veins can pose challenges in treatment and diagnosis, particularly for children, elderly individuals, obese patients, and individuals with darker skin tones. In this study, an automatic dorsal hand vein detection system was developed using a deep learning-based Mask R-CNN model for dorsal hand vein segmentation. A dataset provided by Boǧaziçi University, consisting of 1,575 dorsal hand vein images collected from 100 individuals, was utilized. To enhance vein structures, contrast-enhancing image processing techniques were applied, and the vein networks were manually annotated in detail. The Mask R-CNN model was then trained on this dataset to perform segmentation, and its accuracy was optimized. The study achieved an accuracy rate of 75.3%. The obtained results demonstrate the potential of this method to provide a practical and reliable solution in clinical settings..

  • 
  AtıfWoS1·OpenAlex1

  İncele
• BildiriYalnız künye2025/r/kostu/10511
  Impact of Silent Regions on Spoofed Speech Detection: A Deep Learning Based Analysis

  Irmak, Muhammed Ali; Akdeniz, Fulya; Savas, Burcu Kir

  Silent regions in speech signals can significantly impact the training performance of spoofing detection models. The literature suggests that models primarily rely on silent regions to distinguish between genuine and spoofed speech, as genuine speech typically contains more silence segments. This study analyzes the effect of silent regions on the training and generalization capability of developed models by evaluating test results from various deep learning models and presenting the findings comparatively. A balanced subset was created from the ASVSpoof 2019 LA dataset, ensuring an equal number of genuine and spoofed speech samples. The speech files in this subset were processed using a Voice Activity Detection (VAD) algorithm to remove silent regions. For the experimental study, Spoofing Detection (SD) models were trained and evaluated using baseline models (RawNet2 and LFCC-LCNN) developed for the ASVSpoof 2021 LA dataset, along with Wav2Vec2-ResNet18 models. The results demonstrated a significant degradation in model performance when silent regions were removed from the dataset: LFCC-LCNN exhibited a 15.1% decrease in performance, RawNet2 showed a 69.8% decline, Wav2Vec2-ResNet18 experienced a 30.1% drop. These findings confirm that silent regions play a critical role in the performance of spoofing detection models. The study further reveals that removing silence information significantly reduces the models' ability to distinguish between genuine and spoofed speech.

  AtıfScopus1·WoS1

  İncele