Yazar "Sonmez, E.B." seçeneğine göre listele
Listeleniyor 1 - 7 / 7
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Comparative Study of Deep Learning Methods on Food Classification Problem(Institute of Electrical and Electronics Engineers Inc., 2020) Memis, S.; Arslan, B.; Batur, O.Z.; Sonmez, E.B.This paper gives a comparative study on the performances of several deep learning methods for the food images recognition challenge. The experiments were conducted on the UEC Food-100 dataset using ResNet-18, Inception-V3, Resnet-50, Densenet-121, Wide Resnet-50 and ResNext-50 with images of size 320x320 and 299x299. The limited size of the database required the transfer learning approach; that is, all models were trained with pretrained ImageNet weights. The best classification result was obtained using ResNext-50 with 87.7 % accuracy. © 2020 IEEE.Öğe Diagnosing The Breathing Sounds as COPD or Asthma(Institute of Electrical and Electronics Engineers Inc., 2022) Turkan, B.; Ates, A.G.; Ozdemir, O.; Sonmez, E.B.The aim of this research is to classify recorded chest sounds to distinguish among Asthma, Bronchiolitis, Bronchiectasis, COPD, Pneumonia and URTI diseases versus Healthy sound. That is, this paper introduces and challenges a seven- class problem using one of the few publicly available collection of sounds, the Respiratory Sound database from Kaggle. The performance of several deep learning algorithms has been compared and the Convolutional Neural Network architecture resulted in the most successful model. Unlike previous papers which worked on a subset of this database, this work proposes a more comprehensive seven-class challenge to distinguish among all diseases sampled in the database. The performance of several deep-learning algorithms has been compared and the best model is described in detail. © 2022 IEEE.Öğe Facial Expression Recognition on Wild and Multi-Label Faces with Deep Learning(Institute of Electrical and Electronics Engineers Inc., 2023) Han, H.; Sonmez, E.B.The analysis of facial expressions is a powerful tool to decode nonverbal behavior in humans. Due to its importance, several studies have already been done in the past. However, facial expression recognition on wild and multi-label faces is under-investigated also due to the limited number of available databases. This paper fills in the current lack by challenging the RAF-ML dataset and fixing the state-of-the-art performance of 50.5% on the "single label experiment". The proposed method is also tested in a second experiment, suggested by this work, which considers only wild faces having a dominant expression. The benchmark performance for the second trial is 56.1%. The deep-learning algorithms presented in this work are described in detail to facilitate their reproduction. © 2023 IEEE.Öğe Fine-Grained Food Classification Methods on the UEC FOOD-100 Database(Institute of Electrical and Electronics Engineers Inc., 2022) Arslan, B.; Memis, S.; Sonmez, E.B.; Batur, O.Z.The development of an automatic food recognition system has severalinteresting applications ranging from waste food management, to advertisement, to calorie estimation, and daily diet monitoring. Despite the importance of this subject, the number of related studies is still limited. Moreover, the comparison in the literature was currently done over the best-shot performance without considering the most common method of averaging over several trials. This article surveys the most common deep learning methods used for food classification, it presents the publicly available databases of food, it releases benchmark results for the food classification experiment averaged over five-trials, and it beats the current best-shot performance experiment reaching the state-of-the-art accuracy of 90.02% on the UEC Food-100 database. The best results have been achieved by the ensemble method averaging the predictions of ResNeXt and DenseNet models. All the experiments are run on the UEC Food-100 database because it is one of the most used databases, and it is challenging due to the presence of multifood images, which need to be cropped before processing. This article aims to contribute to automatic food recognition by presenting the most common algorithms used for food classification, introducing the main databases of food items currently available, and reaching the state-of-the-art performance in the best-shot classification experiment of the UEC Food-100 database. That is, this article improves the current best-shot performance by 0.44 percentage points, and fixes it to 90.02%. Furthermore, with the best of our knowledge, this is the first article to introduce to the research community comparison of performances of the classification experiment on the UEC Food-100 database averaged over five-trails. As expected, performance averaged is slightly lower thanthe best-shot one. © 2020 IEEE.Öğe A survey of product recognition in shelf images(Institute of Electrical and Electronics Engineers Inc., 2017) Melek, C.G.; Sonmez, E.B.; Albayrak, S.Nowadays, merchandising is one of the significant method which allows to increase the sales. Therefore, activities such as monitoring the number of products on the shelves, completing the missing products and matching the planogram continuously have become important. An autonomous system is needed to automate operations such as product or brand recognition, stock tracking and planogram matching. In the literature, it is seen that many studies have been carried out in order to address this issue. This survey classifies and compares all existing works with the aim to guide researchers working on merchandising. © 2017 IEEE.Öğe Video-based turkish sign language recognition systems(CRC Press/Balkema, 2016) Aktaş, M.; Sonmez, E.B.Automatic recognition of sign language will be extremely beneficial for hearing impaired people, by allowing them to easily communicate with the outside world. Sign language is a non-verbal and visual language, which evolved detached from the spoken language and it is based on the simultaneous contribution of both temporal and spatial configurations. Even if it is spread all over the world, sign language is not a universal language and every country needs to build its own automatic system. This paper challenges the issue of the development of automatic video-based Turkish Sign Language (TSL) recognition systems; it presents two computer vision-based automatic systems for TSL recognition and compares their performances. Since we are using a newly released TSL database, this paper has also the side-effect to divulge the database to the research community. © 2016 Taylor & Francis Group, London.Öğe Weighted Cross-Entropy for Unbalanced Data with Application on COVID X-ray images(Institute of Electrical and Electronics Engineers Inc., 2020) Ozdemir, O.; Sonmez, E.B.Since December 2019 the world is infected by COVID-19 or Coronavirus disease, which spreads very quickly, out of control. The high number of precautions for laboratory access, which need to be taken to contain the virus, together with the difficulties in running the gold standard test for COVID-19, result in a practical incapability to make early diagnosis. Recent advances in deep learning algorithms allow efficient implementation of computer-aided diagnosis. This paper investigates on the performance of a very well known residual network, ResNet50, and a lightweight Atrous CNN (ACNN) network using a Weighted Cross-entropy (WCE) loss function, to alleviate imbalance on COVID datasets. As a result, ResNet50 model initialized with pre-trained weights fine-tuned by ImageNet dataset and exploiting WCE achieved the state-of-the-art performance on COVIDXRay-5K test set, with a top balanced accuracy of 99.87%. © 2020 IEEE.