Peer-reviewed Articles - Computer sci

119 downloads
476 views

A learning algorithm is proposed for the task of Arabic Handwritten Character and Digit recognition. The architecture consists on an ensemble of different Convolutional Neural Networks. The proposed training algorithm uses a combination of adaptive gradient descent...

["Algorithms and Analysis of Algorithms","Artificial Intelligence","Computer Vision","Data Mining and Machine Learning"]
doi:10.7717/peerj-cs.167
2 citations
430 downloads
1,745 views

We propose a multi-scale image fusion scheme based on guided filtering. Guided filtering can effectively reduce noise while preserving detail boundaries. When applied in an iterative mode, guided filtering selectively eliminates small scale details while restoring...

["Computer Vision"]
doi:10.7717/peerj-cs.80
2 citations
350 downloads
1,623 views

Our aim was to determine the possibility of detecting cognitive emotion information (neutral, disgust, shameful, “sensory pleasure”) by using a remote eye tracker within an approximate range of 1 meter. Our implementation was based on a self-learning ANN used for...

["Human-Computer Interaction","Artificial Intelligence","Computer Vision"]
doi:10.7717/peerj-cs.75
2 citations
1,012 downloads
3,024 views

Edge preserving filters aim to simplify the representation of images (e.g., by reducing noise or eliminating irrelevant detail) while preserving their most significant edges. These filters are typically nonlinear and locally smooth the image structure while minimizing...

["Algorithms and Analysis of Algorithms","Computer Vision"]
doi:10.7717/peerj-cs.72
3 citations
898 downloads
3,162 views

Three-dimensional (3D) data of many kinds is produced at an increasing rate throughout all scientific disciplines. The Portable Document Format (PDF) is the de-facto standard for the exchange of electronic documents and allows for embedding three-dimensional models....

["Computer Vision","Data Science","Digital Libraries","Emerging Technologies","Scientific Computing and Simulation"]
doi:10.7717/peerj-cs.64
1 citation
486 downloads
1,642 views

An object-oriented computational framework for the transformation of colour data and colour metric tensors is presented. The main idea of the design is to represent the transforms between spaces as compositions of objects from a class hierarchy providing the methods...

["Computer Vision","Graphics","Optimization Theory and Computation","Scientific Computing and Simulation","Software Engineering"]
doi:10.7717/peerj-cs.48
208 downloads
1,669 views

Common tasks in document analysis, such as binarization, line extraction etc., are still considered difficult for highly degraded text documents. Having reliable fundamental information regarding the characters of the document, such as the distribution of character...

["Computer Vision","Digital Libraries"]
doi:10.7717/peerj-cs.39

Refine by manuscript type

Top subject areas - Articles

Top subject areas - People

View all subject areas