KMITL

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

Browse

Search Results

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
Interpretable ANN-Based Computer Vision System for Mangosteen Ripeness Detection for Export Markets
(2026-01-21)
Lapcharoensuk, Ravipat
;
Tosribunjerd, Naphon
;
Poonpakdee, Pasu
Mangosteen is a high-value tropical fruit widely consumed and exported from Thailand. Mangosteen ripeness classification is crucial for export quality control, but manual grading leads to inconsistency and inefficiency. This study presents a computer vision system using an Artificial neural network to classify mangosteen into ripe, semi-ripe, and unripe stages based on peel color. A dataset of 378 images was collected and processed to extract 40 color-based features across multiple color spaces. Principal Component Analysis demonstrated non-linear separability among the ripeness classes. SMOTE and Gaussian noise augmentation were used to tackle data imbalance and enhance generalizability. The model reached a 95% accuracy rate and displayed flawless precision and recall for the ripe class. Integrated Gradients analysis highlighted the importance of the red-green color component (CIELAB a*) in the classification process. The proposed method demonstrates a low-cost, interpretable, and efficient solution suitable for real-world application in the mangosteen export industry.
Some of the metrics are blocked by your
consent settings
Portable Signboard Size Measurement for Tax Collection
(2026-01-01)
Viriyakul, Vachara
;
Noisundod, Siwakorn
;
Chayawattana, Faikaew
;
Chokkhun, Pacharapol
;
Tienngam, Krittipoom
Challenges in the collection of signboard taxes largely emanate from access-related problems and human errors, which contribute to inefficiencies in the tax valuation processes. However, a question of concern, which is normally overlooked, is how to provide a systematic and portable solution which combines precision and convenience for the field officers. This paper addresses this gap by developing a portable device based on computer vision and machine learning approaches to automate signboard measurement. Through the integration of state-of-the-art technologies, this device not only increases accuracy but also brings a level of operational simplicity that has not been explored before in this area. The results showed that the device was able to identify and calculate the area of the signboards correctly.
Some of the metrics are blocked by your
consent settings
YOLO-augment strategy with diffusion-based inpainting for enhanced traffic sign detection
(2026-01-01)
Sub-r-pa, Chayanon
;
Pavarangkoon, Praphan
;
Huang, Su Wen
;
Fan, Ming Zhong
;
Chen, Rung Ching
Traffic sign datasets often suffer from data scarcity and class imbalance, which challenge the development of robust autonomous driving systems. This article proposes a novel dataset augmentation method that leverages Stable Diffusion inpainting to generate realistic synthetic traffic signs. The method fine-tunes a Stable Diffusion model and introduces an object-size-based crop (OSB-crop) technique with mask adjustments to ensure high-quality augmentations that maintain contextual consistency. Evaluations using the Fréchet Inception Distance (FID) show average scores of 195.85 for the DFG-T10 subset and 247.077 for the DFG-B10 subset, demonstrating the ability to produce realistic inpainted signs, particularly for more represented minority classes. Qualitative analyses further highlight seamless integration into real-world scenes, although challenges remain for extremely underrepresented classes and ensuring perfect visual fidelity. The benefits of this approach include its potential to enhance traffic sign datasets, address class imbalances, and improve the potential for training more reliable autonomous driving systems by providing more diverse and realistic training data. This study focuses on evaluating the quality of the generated data itself as a foundational step toward enhancing downstream detection models. However, limitations include the computational cost of fine-tuning and the difficulty in achieving high-quality inpainting for all underrepresented classes, especially those with poor initial data quality. This work lays a strong foundation for advancing dataset augmentation techniques for real-world applications.
Some of the metrics are blocked by your
consent settings
Quality Classification of Sunglasses Lens by Deep Learning
(2025-01-01)
Theskham, Charin
;
Jearanaitanakij, Kietikul
Sunglasses lens are medical devices designed to correct human vision while also providing protection against ultraviolet (UV) radiation. Sunglasses lenses come in various colors, each offering different light-filtering properties. Currently, the quality classification of sunglasses lenses during the production process still relies on human vision. Therefore, this research aims to study the design and quality classification of sunglasses lens with both evenness and unevenness colors using machine vision and deep learning techniques. However, from the review of existing studies on sunglasses lens quality inspection, informal research has been conducted in this area. This work is considered a new contribution with potential for practical application in the industry. In this study, a Convolutional Neural Network (CNN) will be used. To save research time, the researchers employed transfer learning techniques using models such as VGG16, VGG19, InceptionV3, Xception, DenseNet121, ResNet50, EfficientNetB0, EfficientNet -B7, and EfficientNetV2L. The classification results are divided into 2 categories for evenness colors lens and unevenness colors lens. The dataset used real photos of sunglasses lens from Hoya Lens Thailand as the data source. A dataset of 1,250 real images of sunglasses lens was used, comprising 625 images of evenness colors lens and 625 images of unevenness colors lens. Data augmentation was performed by rotating the images 90, 180, and 270 degrees, as well as vertically flipping the sunglasses lens images. This process yielded a total of 10,000 images, with 5,000 images each for lenses with evenness and unevenness colors. The results of applying Transfer Learning of each model for classifying the quality of sunglasses lens that the DenseNet121 model achieved the highest performance, with an accuracy of 82.23 % and precision of 82.32 %
Some of the metrics are blocked by your
consent settings
Comparative analysis of Tesseract and Google Cloud Vision for Thai vehicle registration certificate
(2022-04-01)
Thammarak, Karanrat
;
Kongkla, Prateep
;
Sirisathitkul, Yaowarat
;
Intakosum, Sarun
Optical character recognition (OCR) is a technology to digitize a paper-based document to digital form. This research studies the extraction of the characters from a Thai vehicle registration certificate via a Google Cloud Vision API and a Tesseract OCR. The recognition performance of both OCR APIs is also examined. The 84 color image files comprised three image sizes/resolutions and five image characteristics. For suitable image type comparison, the greyscale and binary image are converted from color images. Furthermore, the three pre-processing techniques, sharpening, contrast adjustment, and brightness adjustment, are also applied to enhance the quality of image before applying the two OCR APIs. The recognition performance was evaluated in terms of accuracy and readability. The results showed that the Google Cloud Vision API works well for the Thai vehicle registration certificate with an accuracy of 84.43%, whereas the Tesseract OCR showed an accuracy of 47.02%. The highest accuracy came from the color image with 1024×768 px, 300dpi, and using sharpening and brightness adjustment as pre-processing techniques. In terms of readability, the Google Cloud Vision API has more readability than the Tesseract. The proposed conditions facilitate the possibility of the implementation for Thai vehicle registration certificate recognition system.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results