Deep-learned Models for Photography Idea Retrieval

Integrating Deep-learned Models and Photography Idea Retrieval

2 Replies

Intelligent Portrait Composition Assistance (IPCA) – Integrating Deep-learned Models and Photography Idea Retrieval, Farshid Farhat, Mohammad Kamani, Sahil Mishra, James Wang, ACM Multimedia 2017, Mountain View, CA, USA.

ABSTRACT: Retrieving photography ideas corresponding to a given location facilitates the usage of smart cameras, where there is a high interest among amateurs and enthusiasts to take astonishing photos at anytime and in any location. Existing research captures some aesthetic techniques such as the rule of thirds, triangle, and perspectiveness, and retrieves useful feedbacks based on one technique. However, they are restricted to a particular technique and the retrieved results have room to improve as they can be limited to the quality of the query. There is a lack of a holistic framework to capture important aspects of a given scene and give a novice photographer informative feedback to take a better shot in his/her photography adventure. This work proposes an intelligent framework of portrait composition using our deep-learned models and image retrieval methods. A highly-rated web-crawled portrait dataset is exploited for retrieval purposes. Our framework detects and extracts ingredients of a given scene representing as a correlated hierarchical model. It then matches extracted semantics with the dataset of aesthetically composed photos to investigate a ranked list of photography ideas, and gradually optimizes the human pose and other artistic aspects of the composed scene supposed to be captured. The conducted user study demonstrates that our approach is more helpful than the other constructed feedback retrieval systems.

Updated goal > Step-by-Step-Guide for Portrait Photography

[FullText] [Dataset] [Code]

This entry was posted in Art, Computer Vision, Conference Paper, Deep Learning, Image Processing, Machine Learning, Pattern Recognition, Photography, Research, Thesis and tagged ACM Multimedia, ACMM, Aesthetics, AI, Art Theory, Artificial Intelligence, CBIR, Computer Vision, Content-based Image Retrieval, DEEP LEARNING, Deep-Learned Model Transfer, Human Pose, Human Pose Estimation, Image Aesthetics, Image Processing, Image Retrieval, Intelligent Portrait Composition Assistance, IPCA, Machine Learning, Object Detection, Pattern Recognition, Penn State Deep Learning, Photography, Photography Idea, Portrait, Portrait Composition, Portrait Dataset, Portrait Photography, Pose Estimation, Pose Recommendation, Scene Parsing, Step-by-Step-Guide on July 2, 2017.