لطفا منتظر بمانید ...
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
Microwave Dielectric Characterization of Liquids Using Double Split Elliptical Resonator Integrated With a PDMS-Based Sample Holder
Zeynab Alipour - Soheil Moradi - Mehdi Fardmanesh
Modeling and control of two PPR cooperative manipulations with a passive joint
Hassan Khosravi - Farhad Fani Saberi - Rasul Fesharakifard
Non-Isolated Step-Up Converter Employing Switched-LC Cell Stages for High Voltage Gain and Low Semiconductor Stress
Reza Arabkhazaeli - Hani Vahedi - Mohsen Arabkhazaeli
Highly Sensitive PCF-Based SPR Sensor for Cancer Cells Detection and Temperature Sensing
Mohammad Reza Hosseini - Mohammad Ghanavati - Shahram Mohammadnejad - Mohammad Azim Karami
Data Association and Multi-Target Localization Using Particle Swarm Optimization
Seyed Mohammad B. Seyedin - Fereidoon Behnia
A New Atrial Fibrillation Detection System with Noise Cancellation and Signal Annotation
Amirali Banaei Kashani - Bardia Baraeinejad - Mohammad Fakharzadeh
Enhanced Reliability Optimization in TMR Series Systems through Shared Spares and Hybrid Redundancy Strategies
Mohammad Amin Khayyamirad - Siavash Es'haghi - Mehdi Khatir - Mahdi Karbasian
Using Convolutional Neural Networks for Sudden Cardiac Death prediction
Sara Tavazo - Farideh Ebrahimi
نحوه کنترل سطوح هوشمند با قابلیت تنظیم مجدد در راستای مقابله با استراق سمع کننده ها
محمد کاظم ناطقی - زلفا زینل پور یزدی
A Low-Temperature-Coefficient Sub-1V BGR Using Dual-PTAT Subtraction
Mohammad Rashtian - Mahdi Shahpasandi - Seyed Parsa Mirasadi - Sajjad Shojaei Baghini
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2
