Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo hóa học: " Attentional Mechanisms for Interactive Image Exploration Joseph Machrouh"
Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Attentional Mechanisms for Interactive Image Exploration Joseph Machrouh | EURASIP Journal on Applied Signal Processing 2005 14 2391-2396 2005 J. Machrouh and P. Tarroux Attentional Mechanisms for Interactive Image Exploration Joseph Machrouh Situated Perception Group Human-Machine Communication Department LIMSI-CNRS BP 133 91403 Orsay France Email joseph.machrouh@limsi.fr France Telecom Research Development 2 Pierre Marzin Avenue BP 50702 22307 Lannion Cedex France Email joseph.machrouh@rd.francetelecom.com Philippe Tarroux Situated Perception Group Human-Machine Communication Department LIMSI-CNRS BP 133 91403 Orsay France Ecole Normale Superieure 45 rue d Ulm 75230 Paris Cedex 05 France Email philippe.tarroux@limsi.fr Received 31 December 2003 Revised 15 December 2004 A lot of work has been devoted to content-based image retrieval from large image databases. The traditional approaches are based on the analysis of the whole image content both in terms of low-level and semantic characteristics. We investigate in this paper an approach based on attentional mechanisms and active vision. We describe a visual architecture that combines bottom-up and topdown approaches for identifying regions of interest according to a given goal. We show that a coarse description of the searched target combined with a bottom-up saliency map provides an efficient way to find specified targets on images. The proposed system is a first step towards the development of software agents able to search for image content in image databases. Keywords and phrases exploratory vision bottom-up exploration top-down exploration attention situated vision. 1. INTRODUCTION Image analysis is confronted with the development of large image databases and new techniques have to be designed for image and content retrieving in this context. The agent paradigm has proved its efficiency for searching in unstructured databases. An agent exhibits interaction abilities with its environment and an autonomous behavior driven by its perceptions of the environment and its expectancies. This