0% Complete
فارسی
Home
/
دوازدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
A perceptual loss for screen content image super-resolution
Authors :
Hossein Sekhavaty-Moghadam
1
Marzieh Hosseinkhani
2
Azadeh Mansouri
3
1- خوارزمی تهران
2- خوارزمی تهران
3- خوارزمی تهران
Keywords :
single image super-resolution, deep learning, neural networks, loss function, screen content images
Abstract :
The acceptable results of deep learning led to the use of the deep neural network on a wide range of models, including image super-resolution. The performance of the deep neural network is directly affected by its loss function. Most methods use intensity loss, such as MSE, which computes the difference between the predicted image and the ground truth. Since the human visual system is more sensitive to the structural information of the scene, it is desired that the loss function could measure the impact of the structural error. The use of screen content images has become widespread because of many applications such as desktop-sharing and remote computing. As a result, super-resolution of screen content images becomes a crucial technique to enhance the quality of low-resolution images. In the presented loss function, the structural error is weighted employing DCT components. The model is trained and tested using the screen content images, and the experimental subjective and objective results illustrate the effectiveness of the presented loss for screen content images.
Papers List
List of archived papers
An efficient hybrid approach for performance-based alternative design evaluation in systems engineering
Abbas Chaman Para - Maryam Nooraei Abadeh - Sondos Bahadori
Business Process Improvement Challenges: A Systematic Literature Review
Hanieh Kashfi - Fereidoon Shams Aliee
A Framework for Systematic Stability Assessment of Post-hoc Explanations in Text Classification
Parman Mohammadalizadeh - Parham Mohammadalizadeh - Ayda Mahmoudian
Application of Artificial Intelligence and Remote Sensing for Oil Spill Detection
َAmir Reza Ziaee - Masomeh Azimzadeh - Parvin Ahmadi
From Faces to Words: An Efficient Persian Visual Lip Reading
Mana Amini - Sajjad Aemmi - Azadeh Ashouri - Reza Akhoundzadeh - Kourosh Hassanzadeh - Mohammad Reza Mohammadi
DART-Net یک معماری ترنسفورمر دو مسیره و مقاوم در برابر حملات تخاصمی برای تشخیص کارآمد و انعطافپذیر هرزنامه
امین هادی - مهدی مصلح - کیوان محبی
پیشبینی بستری مجدد بیماران با استفاده از استخراج مفاهیم زیستپزشکی از متون بالینی
فهیمه شاهرخ شهرکی - رسول سامانی - دکتر ناصر قدیری فهیمه شاهرخ شهرکی - رسول سامانی - ناصر قدیری -
A Comparative Evaluation of Machine Learning Models for Anomaly-Based IDS in IoT Networks
Seyed Amir Mousavi - Mostafa Sadeghi - Mohammad Sadeq Sirjani
Challenges of Specification Mining-based Test Oracle for Cyber-Physical Systems
Maryam Raiyat Aliabadi - Dr Mojtaba Vahidi - Dr Ramak Ghavamizadeh
Heart Sound Classification based on Group-based Sparse Features of PCG Signal
Zahra Hossein-Nejad - Mehdi Nasri
more
Samin Hamayesh - Version 42.5.2