LEARNING-BASED FEATURE SUPER-RESOLUTION FOR LOW-RESOLUTION IMAGE CLASSIFICATION
Asaad Musaed Ahmed Anam;
Abstract
Key Words:
Image resolution; feature learning; partial least-square regression; coupled dictionary learning; material classification.
Summary:
The classification of images from their visual texture has many applications ranging from medical diagnosis applications to image retrieval and object recognition. As image resolution determines the amount of details an image holds, it plays an important role when using digitalimages for classification tasks. The problem we address in this thesis is one of automatically classifying textural images with low resolution conditions since high resolution images are not always available. In this work, we propose learning-based approaches to infer high-resolution features from low-resolution features extracted from low-resolution images. Applying these learned maps is equivalent to super-resolution (SR) in the feature domain. Two different applications are studied in this work. Experimental and statistical evaluations show significant improvement in classification performance due to applying theproposed techniques in comparison with direct classification in the low-resolution space.
Image resolution; feature learning; partial least-square regression; coupled dictionary learning; material classification.
Summary:
The classification of images from their visual texture has many applications ranging from medical diagnosis applications to image retrieval and object recognition. As image resolution determines the amount of details an image holds, it plays an important role when using digitalimages for classification tasks. The problem we address in this thesis is one of automatically classifying textural images with low resolution conditions since high resolution images are not always available. In this work, we propose learning-based approaches to infer high-resolution features from low-resolution features extracted from low-resolution images. Applying these learned maps is equivalent to super-resolution (SR) in the feature domain. Two different applications are studied in this work. Experimental and statistical evaluations show significant improvement in classification performance due to applying theproposed techniques in comparison with direct classification in the low-resolution space.
Other data
| Title | LEARNING-BASED FEATURE SUPER-RESOLUTION FOR LOW-RESOLUTION IMAGE CLASSIFICATION | Other Titles | تصنيف الصور الرقمية منخفضة التمايز باستخدام طرائق تعلم فرط تمييز معالم الصور | Authors | Asaad Musaed Ahmed Anam | Issue Date | 2017 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.