0% Complete
صفحه اصلی
/
سی امین کنفرانس بین المللی مهندسی برق
A New Unsupervised Feature Learning Method for Object Recognition using Prior-Knowledge Data
نویسندگان :
Ashkan Farrokhi
1
Hadi Seyedarabi
2
1- دانشگاه تبریز
2- دانشگاه تبریز
کلمات کلیدی :
Unsupervised Clustering, Feature learning, Pyramid matching, Gaussian mixture Model
چکیده :
In this paper we first propose a Self-Organized Incremental Gaussian mixture based clustering mechanism (we named it as SOIGmm). The recognition system runs this clustering mechanism on some local features, which have been extracted, from some prior unlabeled data to create a strong visual codebook. In addition, a wavelet transform is applied for extracting color-based features. The second objective is considering the spatial importance of the different parts of each image into the representation. The saliency map is extracted and used which has a high role in the representation of each image. Furthermore, in the classifier, we used pyramid matching to find similarity between images and used averaging to combine the kernels on the classifier. The experimental results show that the proposed method could achieve excellent performance on object recognition both for one shot and multi-shot training data sets.
لیست مقالات
لیست مقالات بایگانی شده
Performance Evaluation of a DC-DC Dual-Input Single-Output Topology for Renewable Energy Applications
Saed Mahmood alilou - Mohammad mohsen Hayati - Mohammad Maalandish - Mehdi Abapour - Kazem Zare - Seyed hossein Hosseini
Proposed Small Signal Dynamic Model for a Grid-Connected Battery Storage System
Zahra Moradi- Shahrbabak
Low-Cost Clock Distribution Network in Highly Compact Integrated Circuits Against Single Event Transients
Ehsan Borhani nia - Amir Mohammad Hoseini
Inexpensive fabrication of stretchable dry EEG electrodes using well known dry film photoresists
Mohammad Sadegh Rasekh - Amir Jahanshahi - Hassan Ghafoorifard
True Random Number Generator Relying on Multiple Entropy Source and Triple Oscillator for Cryptography Purposes
Somayeh Gholam Mehraban - Mohsen Jalali - Mostafa Azadbakht
Applying Parameter-Oriented Learning to Identify Statistical EEG Features Associated with Depression
Sara Bargi Barkouk - Melika Changizi - Mahdi Zolfagharzadeh Kermani - Ali Asadi Zeidabadi
Speech Emotion Recognition Using Transfer Learning and Self-Supervised Speech Representation Learning
Marziye Azad - Babak Nasersharif
A Framework for Plant Topology Extraction Using Process Mining and Alarm Data
Amir Neshastegaran - Ali Norouzifar - ایمان ایزدی
کنترل فرآیند سیستم های حرارتی بر اساس مدل دو بعدیFMM و رویکرد یادگیری تکرارشونده تطبیقی
سهیلا عابدی - طاهره بینازاده
Source Seeking Via Circular Formation of n-Nonholonomic Agents in a 2-D Environment
Milad Ghane - Mohsen Mojiri - Mohammad Ali Ghadiri-Modarres - Elaheh Zadhoosh
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 43.6.0
