Hand Gesture Recognition from 2D Images by Using Convolutional Capsule Neural Networks

Güler, Osman; Yücedağ, İ̇brahim

doi:10.1007/s13369-021-05867-2

Cited by 13 publications

(11 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…We can answer RQ3 as follows. When uncontrolled overfitting and memorization can occur, which is undesirable [46], the network response may differ when an image not contained in the training set is used for testing. To prevent a model from memorizing data and obtain more realistic and reliable results, we conducted a two‐tier cross‐test, increasing the robustness of the proposed model.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer‐learning‐based classification of pathological brain magnetic resonance images

Savaş,

Damar

2023

ETRI Journal

View full text Add to dashboard Cite

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state‐of‐art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet‐B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross‐validation and a two‐tier cross‐test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Transfer‐learning‐based classification of pathological brain magnetic resonance images

Savaş,

Damar

2023

ETRI Journal

View full text Add to dashboard Cite

show abstract

“…Both models are trained and tested from the American Sign Language public database. Güler et al [40] proposed a method for HGR using a capsule network with CNN. They used three different datasets, i.e., Cifar-10, HG14, and FashionMnist datasets, and four different CNN models, i.e., Reset50, Vgg16, DenseNet, and CapsNet.…”

Section: Deep Learning-based Hgr Systemsmentioning

confidence: 99%

An Efficient and Robust Hand Gesture Recognition System of Sign Language Employing Finetuned Inception-V3 and Efficientnet-B0 Network

Hussain¹,

Amin²,

Fayaz³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Hand Gesture Recognition (HGR) is a promising research area with an extensive range of applications, such as surgery, video game techniques, and sign language translation, where sign language is a complicated structured form of hand gestures. The fundamental building blocks of structured expressions in sign language are the arrangement of the fingers, the orientation of the hand, and the hand's position concerning the body. The importance of HGR has increased due to the increasing number of touchless applications and the rapid growth of the hearing-impaired population. Therefore, real-time HGR is one of the most effective interaction methods between computers and humans. Developing a user-free interface with good recognition performance should be the goal of real-time HGR systems. Nowadays, Convolutional Neural Network (CNN) shows great recognition rates for different image-level classification tasks. It is challenging to train deep CNN networks like VGG-16, VGG-19, Inception-v3, and Efficientnet-B0 from scratch because only some significant labeled image datasets are available for static hand gesture images. However, an efficient and robust hand gesture recognition system of sign language employing finetuned Inception-v3 and Efficientnet-Bo network is proposed to identify hand gestures using a comparative small HGR dataset. Experiments show that Inception-v3 achieved 90% accuracy and 0.93% precision, 0.91% recall, and 0.90% f1-score, respectively, while EfficientNet-B0 achieved 99% accuracy and 0.98%, 0.97%, 0.98%, precision, recall, and f1-score respectively.

show abstract

“…Many researchers have focused on DL architectures because of the success of CNN structures in object recognition [6]. Today, DL algorithms are also used in medicine to solving a wide range of ML problems.…”

Section: Introductionmentioning

confidence: 99%

Karotis Arter Intima-Medya Kalınlığı Ultrason Görüntülerinde Derin Öğrenme Modellerinin Karşılaştırılması: CAIMTUSNet

Topaloğlu

Kazci

Koşar

2022

Bilişim Teknolojileri Dergisi

View full text Add to dashboard Cite

Deep learning is a machine learning technique that uses deep neural networks, which are multilayer neural networks that contain two or more hidden layers. In recent years, deep learning algorithms are also used to solve machine learning problems in medicine. Carotid artery disease is a type of cardiovascular disease that can result in a stroke. If a stroke is not diagnosed early, it is in the first place among the disabling diseases and the third place for the most common cause of death after cancer and heart disease. In this study, the classification performances of deep learning architectures in the biomedical field are compared, and Carotid Artery (CA) Intima-Media Thickness (IMT) Ultrasound (US) images were used. For an early diagnosis, AlexNet, ZFNet, VGGNet (16-19), which had successful results in the ImageNet competition, and authors' original CNNcc models were used for comparison. An image database of CA-IMT-US which contains 501 ultrasound images from 153 patients was used to test the models' classification performances. It is seen that AlexNet, ZFNet, VGG16, VGG19, and CNNcc models achieved rates of 91%, 89.1%, 93%, 90%, and 89.1% respectively. The CNNcc model was found to produce successful classification results on CAIMTUS images when different performance indicators are also taken into account. In addition, different performance indicators including confusion matrices were investigated and the results were announced. The results showed that deep architectures are promising in the biomedical field and can provide proper classification on biomedical images so; this can help clinics to diagnose the disease early.

show abstract

Hand Gesture Recognition from 2D Images by Using Convolutional Capsule Neural Networks

Cited by 13 publications

References 42 publications

Transfer‐learning‐based classification of pathological brain magnetic resonance images

Transfer‐learning‐based classification of pathological brain magnetic resonance images

An Efficient and Robust Hand Gesture Recognition System of Sign Language Employing Finetuned Inception-V3 and Efficientnet-B0 Network

Karotis Arter Intima-Medya Kalınlığı Ultrason Görüntülerinde Derin Öğrenme Modellerinin Karşılaştırılması: CAIMTUSNet

Contact Info

Product

Resources

About