KMITL

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

Browse

Search Results

Now showing 1 - 10 of 17

Some of the metrics are blocked by your
consent settings
Deep learning-based object detection of restorative dental instruments with potential implications for workflow automation and infection control in dental supply units
(2026-12-01)
Poomrittigul, Suvit
;
Mittong, Sirawit
;
Thanathornwong, Bhornsawan
;
Suebnukarn, Siriwan
This study presents a proof-of-concept deep learning approach for automated detection and classification of restorative dental instruments on standardized trays, aiming to support workflow automation and infection control in dental supply units. A dataset comprising 1,000 images and 14,000 annotated instances of restorative dental instruments across 14 categories was developed. The YOLOv8 model was trained and evaluated on this dataset using standard object detection metrics, including precision, recall, and mean average precision at IoU thresholds 0.5 (mAP@0.5) and 0.5:0.95 (mAP@[0.5:0.95]). To assess model advancement, YOLOv8 performance was compared against its predecessors, YOLOv5, YOLOv6, and YOLOv7, under identical experimental settings. A session-level data split was implemented as the primary evaluation to minimize data leakage and provide a realistic estimate of generalization across unseen tray configurations. The YOLOv8 model achieved highest mean average precision mAP@0.5 of 95.9% and mAP@[0.5:0.95] of 80.9%, demonstrating robust detection capability under both standard and stringent evaluation thresholds. Across instrument categories, YOLOv8 demonstrated precision ranging from 90.3% to 100% and recall from 80.6 to 98.5%. The findings demonstrate the feasibility of using YOLOv8 for automated restorative dental instrument detection as an early-stage tool for improving supply unit efficiency. While results indicate high detection accuracy and robustness, further validation in diverse clinical environments is needed. Future deployment should incorporate human-in-the-loop verification, audit trails, and error escalation mechanisms to ensure safe and accountable AI-assisted workflows.
Some of the metrics are blocked by your
consent settings
Performance of deep learning models for the classification and object detection of different oral white lesions using photographic images
(2025-12-01)
Khovidhunkit, Siribang on Piboonniyom
;
Phosri, Kunchidsong
;
Thanathornwong, Bhornsawan
;
Rungraungrayabkul, Dulyapong
;
Poomrittigul, Suvit
Computer vision adjunctive technology for oral lesion diagnoses has been developed to detect and identify Oral Potentially Malignant Disorders (OPMDs) and non-OPMDs. The early detection of OPMDs can reduce the risk of oral cancer development, improving the survival rate of the patients. This study aims to evaluate the computer vision technique in the white oral lesion domain within the scope of photographic images. Deep learning techniques for the classification of Convolution Neural Networks (CNNs) and transformer neural networks, and one-stage models of YOLOv7 and YOLOv8 were utilized to classify and detect five classes of OPMDs and non-OPMDs oral white lesions including oral leukoplakia, oral lichen planus, pseudomembranous candidiasis, oral ulcers covered with pseudomembrane and other white benign oral lesions. From the evaluation results of classification, the IFormerBase model achieves overperformance compared to CNN models with accuracy, precision, and F1 score of more than 80% on the test set. The best model for object detection is YOLOv7 with 84.5% mean Average Precision (mAP) at Intersection over Union (IoU) threshold of 0.3 and 74.5% at IoU of 0.5 on the test set. Object detection results reveal promising automatic oral lesion identification, which can be further developed to enhance the lesion screening system.
Some of the metrics are blocked by your
consent settings
Growth stage detection for food consumption management in smart cricket farming using a deep learning technique
(2025-11-01)
Nutnoi, Nitipoom
;
Yindeesuk, Witoon
;
Kamoldilok, Surachart
;
Srinuanjan, Keerayoot
;
Limsuwan, Pichet
This research proposed a novel method for tracking and predicting the growth stages of two-spotted crickets, reared in a temperature-controlled box at different growth stages using the YOLOv5s model. The images of crickets feeding inside the rearing box were taken with an infrared camera above the feeding point every hour. Images of the cricket were used to train a YOLOv5s model to detect crickets for each growth stage in the rearing box. The experimental results showed that the trained deep learning had an average accuracy of 95.7%. The relationship between the ratio of crickets at each growth stage throughout the 45-day rearing period was plotted and discussed. The results also showed a clear relationship between the amount of food consumed by crickets per day and their growth stage, which could be useful for appropriately managing food consumption according to the growth stage of crickets.
Some of the metrics are blocked by your
consent settings
A Comparative Study of Video Segmentation Techniques for Graduate Detection in Thai Graduation Ceremonies
(2025-01-01)
Chungmarisakul, Chanasorn
;
Chawuthai, Rathachai
Graduation ceremonies are significant occasions usually documented on lengthy, difficult-to-navigate videos. To make more satisfaction of the video needs to remove other participants and restore clear areas into short segments focused on particular graduates. By using YOLOv8 for efficient participant segmentation and the Segment Anything Model (SAM2) for accurate tracking, this study expands on earlier research by preparing videos for inpainting. The results establish the foundation for a complete system that combines inpainting, segmentation, and detection to produce polished, customized graduation video clips.
Some of the metrics are blocked by your
consent settings
Deep Learning-Based Heritage Building Assessment with Spatial Context
(2025-01-01)
Rattanapitak, Wirat
;
Khwansuwan, Poon
;
Wangsiripitak, Somkiat
;
Sirikitsathian, Phatthanan
Rapid urbanization threatens architectural heritage in developing regions, where limited conservation experts cannot assess thousands of potentially valuable buildings before irreversible modifications occur. This paper presents an automated screening system for heritage building identification using deep learning and spatial analysis. The proposed framework employs a dual-stream architecture combining YOLOv8 object detectionwith SegFormer semantic segmentation to extract architectural features from building facade photographs. These visual features are integrated with Geographic Information System (GIS) data to incorporate spatial context, recognizing that heritage buildings often cluster in historically significant areas. A hybrid weighting mechanism balances data-driven feature importance (80%) with expert architectural knowledge (20%) to ensure cultural sensitivity. Experimental evaluation on 1,500 buildings in Roi Et Province, northeastern Thailand, demonstrates the system's effectiveness, achieving 87.6% classification accuracy while processing each building in approximately one second. In corporating spatial context improved performance by 6.4% over visual features alone. The transformer-based architecture proved particularly effective at identifying characteristic features such as paired windows and traditional wall patterns that distinguish heritage structures. This work provides a practical tool for large scale preliminary heritage assessment, enabling conservation authorities to efficiently allocate limited expert resources to high priority buildings while maintaining classification reliability suitable for initial screening purposes.
Some of the metrics are blocked by your
consent settings
The detection and classification of acute myeloid leukaemia blood cell images based on different YOLO approaches
(2024-04-01)
Naing, Kaung Myat
;
Kittichai, Veerayuth
;
Tongloy, Teerawat
;
Chuwongin, Santhad
;
Boonsang, Siridech
Medical image examination with a deep learning approach is greatly beneficial in the healthcare industry for faster diagnosis and disease monitoring. One of the popular deep learning algorithms such as you only look once (YOLO) developed for object detection is a successful state-of-the-art algorithm in real-time object detection systems. Although YOLO is continuously improving in the object detection area, there are still questions about how different YOLO versions compare in terms of performance. We utilize eight YOLO versions to classify acute myeloid leukaemia (AML) blood cells in image examinations. We also acquired the publicly available AML dataset from the cancer imaging archive (TCIA) which consists of expert-labeled single cell images. Data augmentation techniques are additionally applied to enhance and balance the training images in the dataset. The overall results indicated that eight types of YOLO approaches have outstanding performances of more than 90% in precision and sensitivity. In comparison, YOLOv4-tiny has a more reliable performance than the other seven approaches. Consistently, the YOLOv4-tiny also achieved the highest AUC score. Therefore, this work can potentially provide a beneficial digital rapid tool in the screening and evaluation of numerous haematological disorders.
Some of the metrics are blocked by your
consent settings
Deployment of Machine Vision Platform for Checking Spot Welds on Metal Strap Belts
(2023-01-01)
Wiangtong, Theerayod
;
Wongkharn, Siripong
;
Sirisuk, Phaophak
This paper presents a designed platform used to detect the perfection and number of spot welds on the strap belt of metal sheet coils. Three different approaches include image morphology, thresholding and Hough transform are compared. The results from real implementation show that using the adaptive threshold values in image thresholding approach instead of fixed value can increase the system accuracy from 69% to 88%. Also, to find the pad, the comparison of using Haar cascade machine learning and YOLO deep learning is described.
Some of the metrics are blocked by your
consent settings
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.
Some of the metrics are blocked by your
consent settings
Classification of Adulterated Particle Images in Coconut Oil Using Deep Learning Approaches
(2022-01-01)
Palananda, Attapon
;
Kimpan, Warangkhana
In the production of coconut oil for consumption, cleanliness and safety are the first priorities for meeting the standard in Thailand. The presence of color, sediment, or impurities is an important element that affects consumers’ or buyers’ decision to buy coconut oil. Coconut oil contains impurities that are revealed during the process of compressing the coconut pulp to extract the oil. Therefore, the oil must be filtered by centrifugation and passed through a fine filter. When the oil filtration process is finished, staff inspect the turbidity of coconut oil by examining the color with the naked eye and should detect only the color of the coconut oil. However, this method cannot detect small impurities, suspended particles that take time to settle and become sediment. Studies have shown that the turbidity of coconut oil can be measured by passing light through the oil and applying image processing techniques. This method makes it possible to detect impurities using a microscopic camera that photographs the coconut oil. This study proposes a method for detecting impurities that cause the turbidity in coconut oil using a deep learning approach called a convolutional neural network (CNN) to solve the problem of impurity identification and image analysis. In the experiments, this paper used two coconut oil impurity datasets, PiCO_V1 and PiCO_V2, containing 1000 and 6861 images, respectively. A total of 10 CNN architectures were tested on these two datasets to determine the accuracy of the best architecture. The experimental results indicated that the MobileNetV2 architecture had the best performance, with the highest training accuracy rate, 94.05%, and testing accuracy rate, 80.20%.
Some of the metrics are blocked by your
consent settings
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.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results