Name
Title | ||
|---|---|---|
Landing page component classification with convolutional neural networks for online advertising. |
Abstract | ||
|---|---|---|
Pages on digital platforms used for online advertising in order to attract customer attention for a target product are called landing pages. The aim of landing pages is to increase advertisement conversion rates using metrics like clicks, views or subscriptions. In this study, a method is presented to automatically detect the most commonly used components on landing pages; buttons, texts and checkboxes. Landing page images given as inputs, are segmented by morphological and thresholding-based image analysis methods, and each segment is classified using Convolutional Neural Networks (CNN). The proposed method is anticipated to be an important step in the process of automatically designing landing pages with high advertisement conversion rates by segmenting pages into components that have higher performance metrics. In preliminary experiments, high accuracy is achieved in the test data set. |
Year | Venue | Keywords |
|---|---|---|
2018 | Signal Processing and Communications Applications Conference | Online advertising,Landing page,Image segmentation,Convolutional neural networks (CNN) |
Field | DocType | ISSN |
Computer vision,Landing page,Market segmentation,Pattern recognition,Computer science,Convolutional neural network,Online advertising,Image segmentation,Artificial intelligence,Test data | Conference | 2165-0608 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gulsah Ayhan | 1 | 0 | 0.34 |
| Cagla Senel | 2 | 0 | 0.34 |
| Zeynep Eda Uran | 3 | 0 | 0.34 |
| Behcet Ugur Töreyin | 4 | 1 | 1.72 |