کنفرانس مهندسی برق ایران

صفحه اصلی / سی امین کنفرانس بین المللی مهندسی برق

A New Unsupervised Feature Learning Method for Object Recognition using Prior-Knowledge Data

نویسندگان :

Ashkan Farrokhi¹ Hadi Seyedarabi²

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

طراحی و ساخت چرخاننده سه‌درگاهی صفحه E در موجبر باند X

زهرا عابدان - محمد حسین حسینی

Controllable UWB THz Absorber Using a New Single-layer Graphene-based Grating

Mahdieh Bozorgi - Mahmood Rafaei Booket - Mohammad Amin Zolghadr

Optimized ANFIS-based Control Design Using Genetic Algorithm to Obtain the Vaccination and Isolation Rates for the COVID-19

Zohreh Abbasi - Mohsen Shafieirad - Amir Hossein Amiri Mehra - Iman Zamani

Kickback noise reduction and offset cancellation technique for dynamic latch comparator

Mansoure Yousefirad - Mohammad Yavari

Super twisting sliding mode incorporated with USDE for tracking control of nonlinear robotic systems

Ahmadreza Fallahinezhad - Maryam Malekzadeh - Alireza Ariaei

The Use of Additive Decomposition and Deep Neural Network for Photovoltaic Power Forecasting

Fariba Dehghan - Mohsen Parsa Moghaddam - Maryam Imani

Improved Light-Load Efficiency of Resonant Switched-Capacitor Converter

Sajad AfsharZarandi - Reza Beiranvand

Stability Analysis of a New Switched SEIAR-Vac-Iso Epidemic Model for the COVID-19

Amir Hossein Amiri Mehra - Mohsen Shafieirad - Zohreh Abbasi - Iman Zamani

Effects of Derating Factor and Minimum Short Circuit Current on the BOP Cable Sizing of a Power Plant

Hossein Zamanpour abyaneh

Monte Carlo Analysis of Process Variations in Metal-Semiconductor-Metal Photodetectors for Nanophotonic Interconnects Application

Arash Qodratnama - Farshad Khunjush - Mohsen Raji

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4