CRIST900: A Fully-Labeled Natural Image Dataset for Multi-Operator Content Aware Image Retargeting

Abstract

A fully-labeled image dataset provides an exclusive resource for reproducible analysis, investigation inquiries and data analyses in different research computational fields like machine learning, computer vision and deep learning machine intelligence. This research paper present a large scale fully-labeled natural image dataset for Multi-Operator content aware image retargeting techniques. The image dataset is feely available for image processing research field. The current research natural image dataset entitled CRIST900, it include 900 natural images and uses for content aware image retargeting. The proposed CRIST is an image retargeting Multi-Operator method called Content Retargeting Image reSizing Technique. The proposed image resizing method has three phases, image object boundary identification, the image objects feature importance visual saliency map generation and Multi-Operator techniques for efficient retargeting of image objects. The Multi-Operator retargeted image quality assessment was done by different subjective and objective image quality assessment matrices. The experimental result shows that the proposed approach can attain better result than the traditional methods and content aware state-of-the-art image retargeting techniques. The research dataset is publicly available at https://sites.google.com/view/abhayadevmalayil/home.