AAICS: Aesthetics-Driven Automatic Image Cropping and Scaling
Proceeding: The International Conference on Data Mining, Multimedia, Image Processing and their Applications (ICDMMIPA2016)Publication Date: 2016-09-06
Authors : Md Baharul Islam; Chen Tet Khuan; Muhammad Ehsan Rana; Md Kabirul Islam;
Page : 8-17
Keywords : Aesthetics; Computational Photography; Composition Rules/guidelines; Image Cropping and Scaling; Image Recomposition;
Abstract
Due to the availability of digital camera and smart phones, everyone is a casual photographer. Anyway, the quality of captured photos is questionable due to the lack of photographic composition knowledge. Professional photographer utilizes this composition knowledge during their photography whereas casual photographer does not. In this paper, we propose aesthetics-driven automatic image cropping and scaling (AAICS) approach that enables to recompose our regular photographs based on the pre-defined composition rules/guidelines, e.g. rule of thirds and visual balance. Firstly, our method finds the significant map of the given image using saliency detection technique. Then, our system search a cropping window on the significant map based on selected photographic composition rules whose aspect ratio is identical to the given image. Finally, cropping window rescales to get the enhanced image. Our method helps the casual photographer to recompose their poorly captured photos to enhance its composition. Experimental results show the effectiveness of our proposed method.
Other Latest Articles
- Color Image Segmentation Features and Techniques: A Comparative Study
- Support and Improvement of the Educational Process in Regional Education in Slovakia Through Tablet Classrooms
- A Study of Data Acquisition and Analysis for Driver's Behaviour and Characteristics through Application of Smart Devices and Data Mining
- Monitoring of events in SOA architecture for Real Time Financial Decision System
- A Diagnosis and Prescription System to Automatically Diagnose Pests
Last modified: 2016-09-21 00:18:55