Pictures at an Exhibition: EE368 Project
نویسنده
چکیده
This report presents an algorithm which matches photographs of paintings to a small database. The algorithm uses a modified SIFT approach to match keypoints between paintings. The algorithm is somewhat invariant to size and rotation, highly invariant to perspective change and noise, and can tolerate multiple images in the field of view. Significant optimization was performed, leading to a typical identification time of 900 ms on an Intel Core Duo 1.67 GHz computer.
منابع مشابه
Pictures at an Exhibition: Design of a Hybrid Puppetry Performance Piece
Pictures at an Exhibition is a physical/digital puppetry piece that uses tangible interface puppets to modify a virtual scene projected at the back of the stage in real-time. The piece merges traditional puppeteering practices with tangible interaction technologies and virtual environments to create a novel performance for the live stage. This paper describes the design and development of piece...
متن کاملThe Detection of Faces in Color Images: EE368 Project Report
A face detection system is presented. The system has been optimized to detect faces in images created for the purpose of the EE368 class. The system uses a neural network trained to detect face-colored pixels to create regions of interest. Then, a combination of low-pass filters and clustering techniques is used to further refine these regions.
متن کاملJIKUKAN-POEMER: Geographic Information System Using Camera Phone Equipped with GPS, and Its Exhibition on a Street
In this paper, we introduce a geographic information system using camera phone equipped with GPS and its exhibitions. We have proposed a new kind of interface to see lost of pictures which have location information, and in the exhibition, we projected our system onto a shopping street in Japan and held it as a photography exhibition. We studied 700 pictures sent for the exhibition and three pec...
متن کاملThe Flux: Creating a Large Annotated Image Database
From image retrieval to image classification, all research shares one common requirement: a good image database to test or train the algorithms. In order to create a large database of images, we set up a project that allowed gathering a collection of more than 33000 photographs with keywords and tags from all over the world. This project was part of the “We Are All Photographers Now!” exhibitio...
متن کاملPictures at an Exhibition
This project is to recognize an input image through the database which are learned from a set of training images. The first thing we have done is to extract only the main image. This step requires an adaptive threshold to decide whether the selected region is a painting we want or not. The morphological operation follows the filtering process. The edges of the painting extracted in the source i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007