Hossein Pourghassem
Islamic Azad University
115 Papers
589 Citations
Hossein Pourghassem is an academic researcher from Islamic Azad University. The author has contributed to research in topics: Feature extraction & Image segmentation. The author has an hindex of 16, co-authored 115 publications. Previous affiliations of Hossein Pourghassem include Islamic Azad University, Isfahan & Tarbiat Modares University.
Chat about Author
Papers
Computer vision-based apple grading for golden delicious apples based on surface features
TL;DR: A computer vision-based algorithm for golden delicious apple grading is proposed which works in six steps and the accuracy of the proposed segmentation algorithms including stem end detection and calyx detection are evaluated for two different apple image databases.
183
Content-based medical image classification using a new hierarchical merging scheme
TL;DR: A hierarchical medical image classification method including two levels using a perfect set of various shape and texture features, including a tessellation-based spectral feature as well as a directional histogram has been proposed.
98
Breast cancer detection using MRF-based probable texture feature and decision-level fusion-based classification using HMM on thermography images
TL;DR: A breast cancer detection algorithm based on asymmetric analysis as primitive decision and decision-level fusion by using Hidden Markov Model (HMM) and a novel texture feature based on Markov Random Field model is proposed.
76
Seizure Detection Algorithms Based on Analysis of EEG and ECG Signals: a Survey
TL;DR: This paper attempts to provide a comprehensive survey of different types of seizure detection algorithms and their potential role in diagnostic and therapeutic applications.
49
Patient-Specific Epileptic Seizure Onset Detection Algorithm Based on Spectral Features and IPSONN Classifier
Saadat Nasehi,Hossein Pourghassem +1 more
- 06 Apr 2013
TL;DR: The proposed algorithm can be used as a seizure onset detector to initiate the just-in time therapy methods and obtain a higher sensitivity and smaller latency than other common algorithms.