Relevance Feedback: A Power Tool for Interactive Content-Based Image Retrieval Export

@misc{citeulike:5778901, abstract = {Content-Based Image Retrieval \#CBIR\# has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these research e\#orts establish the basis of CBIR, the usefulness of the proposed approaches is limited. Speci\#cally, these e\#orts have relatively ignored two distinct characteristics of CBIR systems: \#1\# the gap between high level concepts and low level features; \#2\# subjectivityofhuman perception of visual content. This paper proposes a relevance feedback based interactive retrieval approach, which e\#ectively takes into account the abovetwocharacteristics in CBIR. During the retrieval process, the user\&\#039;s high level query and perception subjectivity are captured by dynamically updated weights based on the user\&\#039;s feedback. The experimental results over more than 70,000 images show that the proposed approach greatly reduces the user\&\#039;s e\#ort of composing a query and captures the user\&\#039;s information...}, author = {Rui, Yong and Huang, Thomas S. and Ortega, Michael and Mehrotra, Sharad}, citeulike-article-id = {5778901}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.4695}, keywords = {cbir, images, relevance-feedback}, posted-at = {2009-09-13 07:00:15}, priority = {2}, title = {Relevance Feedback: A Power Tool for Interactive Content-Based Image Retrieval}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.4695}, year = {1998} }

TY - ELEC ID - citeulike:5778901 L3 - citeulike-article-id:5778901 N2 - Content-Based Image Retrieval #CBIR# has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these research e#orts establish the basis of CBIR, the usefulness of the proposed approaches is limited. Speci#cally, these e#orts have relatively ignored two distinct characteristics of CBIR systems: #1# the gap between high level concepts and low level features; #2# subjectivityofhuman perception of visual content. This paper proposes a relevance feedback based interactive retrieval approach, which e#ectively takes into account the abovetwocharacteristics in CBIR. During the retrieval process, the user's high level query and perception subjectivity are captured by dynamically updated weights based on the user's feedback. The experimental results over more than 70,000 images show that the proposed approach greatly reduces the user's e#ort of composing a query and captures the user's information... TI - Relevance Feedback: A Power Tool for Interactive Content-Based Image Retrieval KW - cbir KW - images KW - relevance-feedback AU - Rui, Yong AU - Huang, Thomas AU - Ortega, Michael AU - Mehrotra, Sharad PY - 1998/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.4695 ER -