Sarukhanyan Hakob ; Саруханян Акоп
Nowadays, the task of similar content retrieval is one of the central topics of interest in academic and industrial worlds. There are numerous techniques that are both dealing good with structured data and unstructured such as texts, respectively. However, in this paper we present a technique for retrieval of similar image content. We embed images to N dimensional feature space using convolutional neural networks and perform the nearest neighbor search afterwards. At the end, several distance metrics and their influence on the outcome are discussed. We are rather interested in the proportion of related content than in the additional ranking. Thus, the evaluation of results is based on precision and recall. We have selected 6 major categories from ImageNet dataset to assess the performance.
;
В данной работе представлено исследование системы поиска визуально похожих изображений, основанной на свойствах высшего уровня конволюционных нейронных сетей. Показано, что выбор функции расстояния для свойств высшего уровня Соод1еЫе1 имеет большое влияние на точность поисковой системы. Для получения лучших результатов из просмотренных функций выделяется функция корреляции.
Mathematical Problems of Computer Science
oai:noad.sci.am:136047
agasy18@gmail.com ; hakop@ipia.sci.am
Institute for Informatics and Automation Problems of NAS RA
May 3, 2021
Jul 30, 2020
19
https://noad.sci.am/publication/149686
Edition name | Date |
---|---|
Aghasi Poghosyan, Image Visual Similarity Based on High Level Featuresof Convolutional Neural Networks | May 3, 2021 |
Poghosyan Aghasi Sarukhanyan Hakob
Poghosyan Aghasi
Poghosyan Aghasi Hakob Sarukhanyan