KMITL

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

Browse

Search Results

Now showing 1 - 10 of 24

Some of the metrics are blocked by your
consent settings
Micro-nanoscale metrology for reference material size from speckle pattern images
(2026-03-05)
Sirikarntayuprakit, Pakkhanan
;
Plaipichit, Suwan
;
Ngansalung, Benjarat
;
Buranasiri, Prathan
Recently, the fabrication of micro- and nanoscale materials has become necessary in daily life. The sizes and compositions of those materials need to be explored, as the products will be used in other industries. Therefore, micro-nanoscale metrology is necessary for quality control, as some processes require the use of reference materials for comparing the size of industrial micro-nano-sized products. This study investigates the feasibility of using laser speckle imaging. Since the laser speckle setup is relatively inexpensive, the system is a good choice for installation in small factories. Combined with the Gray-level Co-occurrence Matrix (GLCM) analysis method, this technique has been used to compare the size of reference materials that are fabricated by the National Institute of Metrology of Thailand. Two sizes of reference materials, 100 nm and 1,000 nm, were of interest. The particles are composed of polystyrene, and their certified mean diameter and size distribution were determined using transmission electron microscopy (TEM), validated through international comparison, and served as the basis for testing the technique. Clear differences in GLCM contrast, dissimilarity, energy, and correlation were observed between the two particle sizes, reflecting their distinct scattering characteristics. The results demonstrate that speckle-based texture analysis provides a sensitive response to particle size variation, offering a promising pathway toward low-cost, non-invasive micro-nano metrology.
Some of the metrics are blocked by your
consent settings
Bacterial Colony Counting and Classification System Based on Deep Learning Model
(2026-02-01)
Pintavirooj, Chuchart
;
Bunkum, Manao
;
Vongmanee, Naphatsawan
;
Nampeng, Jindapa
;
Visitsattapongse, Sarinporn
Microbiological analysis is crucial for identifying species, assessing infections, and diagnosing infectious diseases, thereby supporting both research studies and medical diagnosis. In response to these needs, accurate and efficient identification of bacterial colonies is essential. Conventionally, this process is performed through manual counting and visual inspection of colonies on agar plates. However, this approach is prone to several limitations arising from human error and external factors such as lighting conditions, surface reflections, and image resolution. To overcome these limitations, an automated bacterial colony counting and classification system was developed by integrating a custom-designed imaging device with advanced deep learning models. The imaging device incorporates controlled illumination, matte-coated surfaces, and a high-resolution camera to minimize reflections and external noise, thereby ensuring consistent and reliable image acquisition. Image-processing algorithms implemented in MATLAB were employed to detect bacterial colonies, remove background artifacts, and generate cropped colony images for subsequent classification. A dataset comprising nine bacterial species was compiled and systematically evaluated using five deep learning architectures: ResNet-18, ResNet-50, Inception V3, GoogLeNet, and the state-of-the-art EfficientNet-B0. Experimental results demonstrated high colony-counting accuracy, with a mean accuracy of 90.79% ± 5.25% compared to manual counting. The coefficient of determination (R<sup>2</sup> = 0.9083) indicated a strong correlation between automated and manual counting results. For colony classification, EfficientNet-B0 achieved the best performance, with an accuracy of 99.78% and a macro-F1 score of 0.99, demonstrating strong capability in distinguishing morphologically distinct colonies such as Serratia marcescens. Compared with previous studies, this research provides a time-efficient and scalable solution that balances high accuracy with computational efficiency. Overall, the findings highlight the potential of combining optimized imaging systems with modern lightweight deep learning models to advance microbiological diagnostics and improve routine laboratory workflows.
Some of the metrics are blocked by your
consent settings
Hybrid Deep Learning Framework for Accurate Surface Defect Detection Using Autoencoder and CNNs
(2026-01-01)
Craypo, Niphat
;
Banjongkan, Anupong
;
Hanskunatai, Anantaporn
Surface defect detection is paramount in industrial quality control. Conventional methods, which often rely on human inspection or manually engineered statistical models, frequently fail to accurately detect and classify defects, particularly on complex surfaces or those with intricate features. Human inspection is inherently inconsistent and prone to errors due to fatigue, while traditional machine vision systems often lack the sensitivity to clearly identify small or low-contrast defects. This paper proposes a hybrid deep learning framework, termed Autoencoders-Convolutional Neural Networks (AE-CNNs), DefectNet, for surface defect classification, AE, and CNNs to enhance both accuracy and efficiency. The AE is employed to extract and compress reliable features from surface images into latent representations, which are subsequently classified by a CNN enhanced through transfer learning using InceptionV3. The CNN is fine-tuned from a pretrained model with customized fully connected layers to adapt to specific defect characteristics, while the AE is trained exclusively on non-defective images. The encoded features produced by the AE serve as the input to the CNN. The proposed model is evaluated on standard benchmark datasets comprising diverse surface defect types and compared against Anomaly Detection with Autoencoder (ADA), Visual Geometry Group (VGG16), Inception-based Convolutional Neural Network Long Short-Term Memory (In-CNNLSTM), and DTL_Inception_v3. Experimental results demonstrate the superior performance of the proposed method, achieving classification accuracies ranging from 85.60% to 100% across five datasets, including a perfect 100% accuracy on the glass bottle neck dataset.
Some of the metrics are blocked by your
consent settings
Using a Computer Vision System for Monitoring the Exterior Characteristics of Damaged Apples
(2025-10-01)
Al-Riyami, Zamzam
;
Al-Dairi, Mai
;
Pathare, Pankaj B.
;
Kramchote, Somsak
Mechanical damage like bruises produced during postharvest handling can lower market value, affect nutritional value, and pose food safety risks. The study evaluated bruises on apples using image processing. This research focuses on using computer vision for apple fruit damage detection. The fruits were subjected to three levels of impact using three ball weights (66, 98, and 110 g) dropped from 50 cm height and stored at 22 °C. The overall impact energies generated were 0.323 J (low), 0.480 J (medium), and 0.539 J (high). The bruise area and susceptibility of the damage, surface area of the fruit, and color were measured manually (colorimeter) and by image processing. The study found that the bruise area was significantly affected by impact force, where 110 g (0.539 J) damaged apples showed a bruise area of 4.24 cm<sup>2</sup> after 21 days of storage at 22 °C. The images showed a significant change in the RGB values (Red, Green, Blue) over 21 days of storage when impacted at 0.539 J. The study showed that the greater the impact energy effect, the higher the weight loss under constant conditions of storage. After 21 days of storage, the 110 g mechanically damaged apples recorded the highest percentage of weight loss (6.362%). The study found a significant decrease in the surface area of 110 g bruised apples, with a smaller decrease in surface area for 66 g bruised fruit. The use of computer vision to detect bruise damage and other quality attributes of Granny Smith apples can be highly recommended to detect their losses.
Some of the metrics are blocked by your
consent settings
A Bootstrapping Convolutional Neural Network Technique for Optimizing Automated Detection of Equatorial Plasma Bubbles by Optical All-Sky Imagers
(2025-06-01)
Okoh, Daniel
;
Cesaroni, Claudio
;
Rabiu, Babatunde
;
Shiokawa, Kazuo
;
Otsuka, Yuichi
Equatorial plasma bubbles (EPBs) disrupt satellite-based communication and navigation systems, particularly in equatorial regions. Reliable detection and classification of EPBs from all-sky imager (ASI) images are essential for accurate space weather monitoring and forecasting. This study presents a novel bootstrapping convolutional neural network (CNN) approach to optimize automated EPB detection on ASI images for operational space weather monitoring applications, and overcoming challenges related to image variability and imbalanced data sets. Data used for CNN training were obtained from the optical mesosphere thermosphere imagers ASI installed at the Space Environment Research Laboratory, National Space Research and Development Agency, Abuja during the period from 2015 to 2020. Our method involved training three sub-models, and aggregating their predictions. The CNN trainings were conducted on three sub-datasets of 3,000 images each, categorized as “EPB,” “Noisy/Cloudy” or “No EPB.” Three corresponding sub-models were developed from the CNN trainings. The three sub-model classifications independently gave prediction accuracies of 98.67%, 98.33%, and 95.83% on a reserved test data set of 600 images. Ensemble models further improved the model prediction accuracies to 99.17% and 99.33% for methods based on the mean of sub-model probabilities and the mode of sub-model classifications respectively. Our results indicate that the bootstrapping CNN technique enhanced the EPB detection accuracy, providing a powerful tool for real-time space weather monitoring applications, and implications for improving operational reliability of satellite-based navigation and communication in the equatorial region.
Some of the metrics are blocked by your
consent settings
Revolutionizing Egg Quality Control: Advanced Prompt-based Models for Automated Detection of Broken Eggs Without the Need for Training
(2025-02-01)
Soontornnapar, Tomorn
;
Praneenatthavee, Natdhanai
;
Ploysuwan, Tuchsanai
This paper proposes an end-to-end pipeline to detect broken eggs in a holder without extensive training, employing a two-step image segmentation and processing approach using saliency scores, all without relying on a large amount of labeled data. The process begins by inputting an egg image with text prompts into Grounding DINO, which returns an egg bounding box. This is followed by the segment anything model (SAM), which extracts the egg’s segmented region. The segmented region is then divided into two crucial components for detection: a binary mask image and a background-removed egg image. The innovation in our method lies in using the saliency score of the estimated anomaly region by employing image processing techniques to effectively distinguish between intact and broken eggs. To validate our approach, we compare it to well-known models such as SVM, XGBoost, and YOLOv8, and we also conduct zero-shot experiments with CLIPSeg, Florence-2, and SAA. In our experimental setup, we utilize 50 egg holder images, each containing both intact and broken eggs. We carefully cropped and processed 30 eggs (arranged in a 6×5 grid) from each holder, resulting in a comprehensive testing dataset totaling 1,500 images. Our results demonstrate the robustness of our method, achieving an impressive 99.56% accuracy in detecting both intact and broken eggs. This breakthrough promises significant advancements in the field of broken egg detection, with broad applications across diverse industries, including food safety, quality control, and automated packaging systems.
Some of the metrics are blocked by your
consent settings
Study on Damage to Flexible Pavement Road in Thailand: Identification Types of Crack on Roads Using Image Processing Takes
(2025-01-01)
Chutchavong, Vanvisa
;
Doungpan, Satawat
;
Kasettakarn, Witchapon
;
Thiabkhuang, Surapit
;
Phungtua-Eng, Thanapol
The detection and identification of flexible pavement road cracks pose a significant challenge for civil engineers when they start work at the beginning level, as it requires extensive work experience of engineers in classifying types of cracks for planning road maintenance. Inaccurate analysis and identification of cracks can negatively affect the quality of maintenance work and threaten the safety of road users in the future. This paper presents a case study of 60 asphalt roads managed by the Provincial Administrative Organization (PAO) in central of Thailand (case of two provinces, Uthai Thani and Nakhon Sawan), focusing on identification type road cracks. The study aims to address issues related to data preparation and classification across various domains Our data are fed model, which is photography to medium-resolution images of flexible pavement road cracks so that guidelines for engineers' inspection and identification of road cracks. We propose the development of a U-Net model specifically designed for image processing tasks. The results indicate that the U-Net model is effective in converting road cracks images into segmentation masks, and this effectiveness is evaluated using four well-defined key performance indicators.
Some of the metrics are blocked by your
consent settings
Comparative Analysis of Deep Learning Models for Building Extraction from High-resolution Satellite Imagery
(2025-01-01)
Chueprasert, Tachasit
;
Udomchaiporn, Akadej
;
Intagosum, Sarun
In this research, an approach to extract buildings from Google's satellite imagery was proposed. The performances of various deep learning models (U-Net, RIU-Net, U-Net++, Res-U-Net, and DeepLabV3+) on pre-processed datasets were compared. The models were trained using the similarity metrics of Intersection over Union (IoU) and Dice Similarity Coefficient (DSC). The best-performing models among the segmentation techniques were Res-U-Net and DeepLabV3+. Res-U-Net, an enhanced version of the traditional U-Net model that incorporates residual connections for improved feature propagation, achieved an F1 score of 85.43% when using the RGB dataset. Similarly, DeepLabV3+ also achieved high performance on the Enhanced RGB dataset, obtaining an F1 score of 85.18% after applying pre-processing techniques. This research highlights the significance of color as a dominant feature for accurate building extraction from satellite images. The findings contribute to improved methodologies for building identification, benefiting urban planning, and disaster management applications.
Some of the metrics are blocked by your
consent settings
Clamp Dot Image Classification Using Neural Network
(2024-01-01)
Srikam, Krittapak
;
Saenthon, Anakkapon
In this paper, we discuss the classification of images captured by a machine camera while assembling components. To crop out specific points of interest, we employ image processing. Additionally, we utilize deep learning techniques, specifically convolutional neural networks, to identify the type of equipment being assembled. This approach allows us to determine and record specific parts within a device. However, the main challenge of this project is to achieve both high accuracy and the shortest possible prediction time.
Some of the metrics are blocked by your
consent settings
Modern Manufacturing for Alloy Wheel Defect Detection using Image Processing and Application
(2024-01-01)
Archevapanich, Tuaniai
;
Krungseanmuang, Woranidtha
;
Chaowalittawin, Vasutorn
;
Sathaporn, Posathip
;
Chaowalittawin, Punyisa
This paper presents an innovative approach to identifying defects in alloy wheel production by integrating image processing techniques with a mobile application platform. The system receives X-ray alloy images from the factory via mobile phone, processes them using image processing techniques to enhance clarity and readiness for defect detection, and then transmits the processed images to a Django framework via a uniform resource locator (URL). Subsequently, the system detects defects in the images, encodes them in Base64 format, and sends them to the mobile application through an API (Application Program Interface) for display on the user interface. This well-designed system architecture offers manufacturers a comprehensive solution to ensure product quality, reduce costs, and enhance customer satisfaction.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results