Few-Shot learning for frame-Wise phoneme recognition: Adaptation of matching networks

Banerjee, Tirthankar; Thurlapati, Narasimha Rao; Pavithra, V.; Mahalakshmi, S.; Eledath, Dhanya; Ramasubramanian, V.

doi:10.23919/eusipco54536.2021.9616234

Cited by 4 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the first hiding technique developed for the suggested model, LSB sequentially embedded information bits into the cover image. Tampering LSB does not reflect a notable difference, as the change occurs on a small scale following its capacity [26]. The hackers would check secret bits from the cover least successively, a common flaw in steganography techniques.…”

Section: Least Significant Bit Steganography Technique Lsbmentioning

confidence: 99%

See 1 more Smart Citation

Jaccard-based Random Distribution with Least and Most Significant Bit Hiding Methods for Highly Patients MRI Protected Privacy

Tayh Albderi,

Al-Shammary,

Said

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

In this study, the main goal is to improve patient care by making it easier for patient data and pictures to be sent between medical centers without problems. Still, one of the biggest problems with telemedicine is keeping patient information private and ensuring data is safe. This is especially important because even small changes to patient information could have serious consequences, such as wrong evaluations and lower-quality care. This study develops a new model that uses the unique Jaccard distribution of the least significant bit (LSB) and the most significant bit (MSB) to solve this complex problem. The goal of this model is to hide much information about a patient in the background of an MRI cover picture. The careful creation of this model is a crucial part of the current study, as it will ensure a solid way to hide information securely. A more advanced method is also suggested, which involves randomly putting private text in different places on the cover picture. This plan is meant to strengthen security steps and keep private patient information secret. The peak signal-to-noise ratio (PSNR), the structural similarity index measure (SSIM), and the mean square error (MSE) all improved significantly when this method was tested in the real world. With these convincing results, the study shows telemedicine is more effective than traditional methods for keeping patient data safe. This proves that the model and method shown have the potential to greatly improve patient privacy and data accuracy in telemedicine systems, which would improve the general quality of health care.

show abstract

Section: Least Significant Bit Steganography Technique Lsbmentioning

confidence: 99%

“…This approach must conceal a secret bit in the high significant bit, with the resulting distortion equivalent to LSB. The same technique hid and extracted secret information [27]. The MRI host was then shifted with the following formula: =…”

Section: E Most Significant Bit Steganography Technique Msbmentioning

confidence: 99%

Jaccard-based Random Distribution with Least and Most Significant Bit Hiding Methods for Highly Patients MRI Protected Privacy

Tayh Albderi,

Al-Shammary,

Said

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…The common types of FSL are N-Shot Learning (NSL), Few-Shot Learning (FSL), One-Shot Learning (OSL), and Less than one or Zero-Shot Learning (ZSL) Fig. 1 The Embedding Network of Few-Shot Learning [27] All the few-shot learning perspectives use advanced science of several forms (e.g., data, model, and algorithm) to bring down 'sample difficulty' described as the number of training samples required to ensure the loss of reduced empirical risk [28], [29]. Several studies have been carried out in research related to our work.…”

Section: A Few-shot Learningmentioning

confidence: 99%

Closer Look at Image Classification for Indonesian Sign Language with Few-Shot Learning Using Matching Network Approach

Sari

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Huge datasets are important to build powerful pipelines and ground well to new images. In Computer Vision, the most basic problem is image classification. The classification of images may be a tedious job, especially when there are a lot of amounts. But CNN is known to be data-hungry while gathering. How can we build some models without much data? For example, in the case of Sign Language Recognition (SLR). One type of Sign Language Recognition system is vision-based. In Indonesian Sign Language dataset has a relatively small sample image. This research aims to classify sign language images using Computer Vision for Sign Language Recognition systems. We used a small dataset, Indonesian Sign Language. Our dataset is listed in 26 classes of alphabet, A-Z. It has loaded 12 images for each class. The methodology in this research is few-shot learning. Based on our experiment, the best accuracy for few-shot learning is Mnasnet1_0 (85.75%) convolutional network model for Matching Networks, and loss estimation is about 0,43. And the experiment indicates that the accuracy will be increased by increasing the number of shots. We can inform you that this model's matching network framework is unsuitable for the Inception V3 model because the kernel size cannot be greater than the actual input size. We can choose the best algorithm based on this research for the Indonesian Sign Language application we will develop further.

show abstract

Few shot learning for cross-lingual isolated word recognition

Banerjee

Eledath

Ramasubramanian

2021

The First International Conference on AI-ML-Systems

View full text Add to dashboard Cite

Few-Shot learning for frame-Wise phoneme recognition: Adaptation of matching networks

Cited by 4 publications

References 4 publications

Jaccard-based Random Distribution with Least and Most Significant Bit Hiding Methods for Highly Patients MRI Protected Privacy

Jaccard-based Random Distribution with Least and Most Significant Bit Hiding Methods for Highly Patients MRI Protected Privacy

Closer Look at Image Classification for Indonesian Sign Language with Few-Shot Learning Using Matching Network Approach

Few shot learning for cross-lingual isolated word recognition

Contact Info

Product

Resources

About