KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Tongloy, TeerawatSubject: search.filters.subject.Classification

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Images Retrieval and Classification for Acute Myeloid Leukemia Blood Cell Using Deep Metric Learning
    (2023-01-01)
    Naing, Kaung Myat
    ;
    Kittichai, Veerayuth
    ;
    Tongloy, Teerawat
    ;
    Chuwongin, Santhad
    ;
    Boonsang, Siridech
    Deep metric learning-based image retrieval systems have recently been used in medical applications because they provide clinically relevant information-based similar images based on prior knowledge. Although train examiners and deep learning models successfully analyze leukocyte cells, there are still numerous difficult challenges due to biological variation, time constraints, and a variety of image-related aspects. In this study, we propose a deep metric learning model-based image retrieval and classification system for acute myeloid leukemia blood cells to address these issues and assist physicians. The proposed model utilizes the pre-trained ResNet-34 model as the backbone network, embedding loss with multi similarity miner, and M-Per-Class sampling strategy to learn an embedding function. The five embedding losses were also applied to compare the four performances in order to determine the best loss-based model. Based on the best loss-based model, the class-wise precision and sensitivity using a neighborhood size are also presented. The results show that the contrastive loss-based deep metric learning model achieved the highest precision of 94.90%, sensitivity of 94.85%, specificity of 99.64%, and accuracy of 99.32% in model comparison. Except for a few failures in small classes, the class-wise precision and sensitivity scores looked to be impressive in all classes. Therefore, this proposed system can highly be effective in screening and diagnosing of AML-related white blood cell stages that cause serious cancer.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Classification model of optical character recognition failures in unrecovered slider serial numbers in hard disk drive manufacturing and image capture processes
    (2022-01-01)
    Chousangsuntorn, Chousak
    ;
    Tongloy, Teerawat
    ;
    Chuwongin, Santhad
    ;
    Boonsang, Siridech
    In hard disk drive (HDD) manufacturing processes, there are unrecovered serial number images about 0.01% from the standard optical character recognition (OCR) reading and deep learning approach. We found several failures from two main causes, i.e. manufacturing process and image capture process during standard OCR reading. We proposed classification model used for recognizing the serial number reading failures based on object detection You-Only-Look- Once (YOLO) algorithm and EfficientNet-B0 classification network as well as histogram analysis. The 1000 images captured by digital camera were used for training (600 images) and validation (400 images) the ROI detection model. The other 2100 captured images were used for training and testing classification OCR failure from manufacturing process model. The model testing was performed in 900 images contained 9 causes (classes) of failures. The proposed model reaches F1 score = 0.94.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Three-stage deep learning system for recognizing contaminated serial numbers in hard disk drive: A comparison study with two-stage deep learning model
    (2022-01-01)
    Chousangsuntorn, Chousak
    ;
    Tongloy, Teerawat
    ;
    Chuwongin, Santhad
    ;
    Boonsang, Siridech
    The previous two-stage deep learning model for detecting and classifying misidentified serial numbers on the defect hard disk drive (HDD) slider was proposed by authors. We found that the threshold level adjusted during preprocessing process could limit the robustness of the two-stage model in large-scale manufacturing. Thus, we proposed a three-stage deep learning model comprised of 1) region of interest (ROI) detection and cropping, 2) character detection and cropping, and 3) character classification. Object detection algorithm and classification network used in this model are based on YOLO v.4 and EfficientNet-B0. The 1000 images captured by the digital camera were used for training (600 images) and validation (400 images) of the ROI detection model. The other 1000 captured images were used for testing the performance of the proposed three-stage model, then we compared them with those obtained from the previous two-stage model. The proposed three-stage model reaches F1 score = 0.997 and recovery rate up to 95.9%, while the two-stage model yields only 0.948 and 73%, respectively.