Yazar "Saygili, Ahmet" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    A Novel Approach for Tomato Leaf Disease Classification with Deep Convolutional Neural Networks
    (Ankara Univ, Fac Agriculture, 2024) Irmak, Gizem; Saygili, Ahmet
    Computer -aided automation systems for the detection of plant diseases represent a challenging and highly impactful research domain in the field of agriculture. Tomatoes, a major and globally significant agricultural commodity, are cultivated in large quantities. This study introduces a novel approach for the automated detection of diseases on tomato leaves, leveraging both classical machine learning methods and deep neural networks for image classification. Specifically, classical learning methods employed the local binary pattern (LBP) technique for feature extraction, while classification tasks were carried out using extreme learning machines, k -nearest neighborhood (kNN), and support vector machines (SVM). In contrast, a novel convolutional neural network (CNN) framework, complete with unique parameters and layers, was utilized for deep learning. The results of this study demonstrate that the proposed approach outperforms state-of-the-art studies in terms of accuracy. The classification process covered various scenarios, including binary classification (healthy vs. unhealthy), 6 -class classification, and 10 -class classification for distinguishing different types of diseases. The findings indicate that the CNN model consistently outperformed classical learning methods, achieving accuracy rates of 99.5%, 98.50%, and 97.0% for 2 -class, 6 -class, and 10 -class classifications, respectively. Future research may explore the use of computer -aided automated systems to detect diseases in diverse plant species.
  • Küçük Resim Yok
    Öğe
    AI-aided cardiovascular disease diagnosis in cattle from retinal images: Machine learning vs. deep learning models
    (Elsevier Sci Ltd, 2024) Cihan, Pinar; Saygili, Ahmet; Ermutlu, Celal Sallin; Aydin, Ugur; Aksoy, Ozgur
    Cardiovascular diseases (CVD) in animals can severely impact the heart and circulatory systems, like those in humans. Early diagnosis and treatment are crucial for improving animal welfare and lifespan. Traditional diagnostic methods face challenges such as insufficient anamnesis information, high costs of biochemical and hematological tests, and increasing data complexity. This study aims to address these issues by developing AIbased diagnostic systems for fast and accurate CVD diagnosis in cattle using retinal images. A total of 1118 retinal images from 100 cattle were collected, with 52 diagnosed with CVD and 48 as non-CVD. The dataset is publicly available on Kaggle. We evaluated three machine learning methods (Extreme Learning Machine, KNearest Neighbors, and Support Vector Machine) and four deep learning models (DenseNet201, ResNet101, SqueezeNet, and InceptionV3) for their diagnostic capabilities. ResNet101 emerged as the most effective model, achieving an accuracy of 96.1 f 3.15 %, sensitivity of 97.3 f 2.96 %, specificity of 94.9 f 4.07 %, and an F1score of 96.4 f 0.03. This study demonstrates that AI-based systems, particularly deep learning models, can significantly improve the accuracy of CVD diagnosis in animals, marking a critical advancement in veterinary healthcare.
  • Küçük Resim Yok
    Öğe
    CattNIS: Novel identification system of cattle with retinal images based on feature matching method
    (Elsevier Sci Ltd, 2024) Saygili, Ahmet; Cihan, Pinar; Ermutlu, Celal Sahin; Aydin, Ugur; Aksoy, Ozgur
    Small and large farm animals are frequently identified using techniques like microchipping or tagging. However, these techniques may have a detrimental impact on animal welfare and may result in theft and fraud. Modern and sophisticated identification procedures using biometrics, including retina, face, and iris recognition, are available and have less of a detrimental effect on animal welfare. Because biometric markers are unchangeable and unaffected, it is feasible to stop situations of theft and fraud. This study uses retina images to identify animals based on each animal ' s different and specific retinal patterns. To the best of our knowledge, there isn ' t a publicly accessible dataset for images of animal retinas. The three main goals of this study are to: 1) produce a novel dataset of Cattle retinal images and make it publicly available; 2) create a successful image processing -based system for retinal identification and recognition; and 3) create a graphical user interface (GUI) that enables querying the database to ascertain whether a specific Cattle retina is present. To accomplish these goals, a dataset comprising 2430 images from the left and right eyes of 300 cattle was produced. After the dataset was created, the animal retinal images were segmented using image processing methods such as scaling, color transformations, image sharpening, contrast enhancements, noise filtering, and histogram equalization. By using the segmented images with the SURF, FAST, BRISK, and HARRIS techniques, distinctive retinal features were found. During the identification phase, the animal whose retinal characteristic matched the sought animal ' s retina the closest was recognized. Within the developed CattNIS system, the SURF approach has the highest accuracy rate of 92.25 percent. The results of this study show that the identification of cattle using retinal vascular patterns is highly successful. The availability of the collected cattle retinal images from this study is expected to significantly contribute to the advancement of future research in this field, both in terms of quantity and quality.
  • Küçük Resim Yok
    Öğe
    Identification and Recognition of Animals from Biometric Markers Using Computer Vision Approaches: A Review
    (Kafkas Univ, Veteriner Fakultesi Dergisi, 2023) Cihan, Pinar; Saygili, Ahmet; Ozmen, Nihat Eren; Akyuzlu, Muhammed
    Although classic methods (such as ear tagging, marking, etc.) are generally used for animal identification and recognition, biometric methods have gained popularity in recent years due to the advantages they offer. Systems utilizing biometric markers have been developed for various purposes in animal management, including more effective and accurate tracking of animals, vaccination, disease management, and prevention of theft and fraud. Animals' irises, retinas, faces, muzzle, and body patterns contain unique biometric markers. The use of these markers in computer vision approaches for animal identification and tracking systems has become a highly effective and promising research area in recent years. This review aims to provide a general overview of the latest developments in image processing approaches for animal identification and recognition applications. In this review, we examined in detail all relevant studies we could access from different electronic databases for each biometric method. Afterward, the opportunities and challenges of classical and biometric methods were compared. We anticipate that this study, which conducts a literature review on animal identification and recognition based on computer vision approaches, will shed light on future research towards developing automated systems with biometric methods.