Pasupa, Kitsuchart

Loading...
Thumbnail Image
Preferred name
Pasupa, Kitsuchart
Main Affiliation
Email
kitsuchart.pa@kmitl.ac.th

Settings

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Evaluation of deep learning algorithms for semantic segmentation of car parts
    (2022-10-01)
    Pasupa, Kitsuchart
    ;
    Kittiworapanya, Phongsathorn
    ;
    Hongngern, Napasin
    ;
    Woraratpanya, Kuntpong
    Evaluation of car damages from an accident is one of the most important processes in the car insurance business. Currently, it still needs a manual examination of every basic part. It is expected that a smart device will be able to do this evaluation more efficiently in the future. In this study, we evaluated and compared five deep learning algorithms for semantic segmentation of car parts. The baseline reference algorithm was Mask R-CNN, and the other algorithms were HTC, CBNet, PANet, and GCNet. Runs of instance segmentation were conducted with those five algorithms. HTC with ResNet-50 was the best algorithm for instance segmentation on various kinds of cars such as sedans, trucks, and SUVs. It achieved a mean average precision at 55.2 on our original data set, that assigned different labels to the left and right sides and 59.1 when a single label was assigned to both sides. In addition, the models from every algorithm were tested for robustness, by running them on images of parts, in a real environment with various weather conditions, including snow, frost, fog and various lighting conditions. GCNet was the most robust; it achieved a mean performance under corruption, mPC = 35.2, and a relative degradation of performance on corrupted data, compared to clean data (rPC), of 64.4%, when left and right sides were assigned different labels, and mPC = 38.1 and rPC = 69.6 % when left- and right-side parts were considered the same part. The findings from this study may directly benefit developers of automated car damage evaluation system in their quest for the best design.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An Image Segment-based Classification for Chest X-Ray Image
    (2020-11-19)
    Kittiworapanya, Phongsathorn
    ;
    Pasupa, Kitsuchart
    In late 2019, the first case of COVID-19 was confirmed in Wuhan, China. The number of cases has been rapidly growing since then. Molecular and antigen testing methods are very accurate for the diagnosis of COVID-19. However, with sudden increases of infected cases, laboratory-based molecular test and COVID-19 test kits are in short supply. Because the virus affects an infected patient's lung, interpreting images obtained from Computed Tomography Scanners and Chest X-ray Radiography (CXR) machines can be an alternative for diagnosis. However CXR interpretation requires experts and the number of experts is limited. Therefore, automatic detection of COVID-19 from CXR images is required. We describe a system for automatic detection of COVID-19 from CXR images. It first segmented images to select only the lung. The segmented part was then fed into a multiclass classification module, which worked well with samples obtained from various sources, which had different aspect ratios, contrast and viewpoints. The system also handled the unbalanced dataset-only a small fraction of images showed COVID-19. Our system achieved 92% of F1-score and 88.1% Marco F1-score on the 3rd Deep Learning and AI Summer/Winter School Hackathon Phase 3-Multi-class COVID-19 Chest X-ray challenge public leaderboard.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Particle Size Estimation in Mixed Commercial Waste Images Using Deep Learning
    (2021-06-29)
    Kittiworapanya, Phongsathorn
    ;
    Pasupa, Kitsuchart
    ;
    Auer, Peter
    We assessed several state-of-the-art deep learning algorithms and computer vision techniques for estimating the particle size of mixed commercial waste from images. In waste management, the first step is often coarse shredding, using the particle size to set up the shredder machine. The difficulty is separating the waste particles in an image, which can not be performed well. This work focused on estimating size by using the texture from the input image, captured at a fixed height from the camera lens to the ground. We found that EfficientNet achieved the best performance of 0.72 on F1-Score and 75.89% on accuracy.