In this technical demonstration, we showcase theMindFinder
system − a novel image search engine. Different from ex-
isting interactive image search engines, most of which only
provide image-level relevance feedback, MindFinder enables
users to sketch and tag query images at object level. By con-
sidering the image database as a huge repository, MindFinder
is able to help users present and refine their initial thoughts
in their mind, and finally turn thoughts to a beautiful im-
age(s). Multiple actions are enabled for users to flexibly de-
sign their queries in a bilateral interactive manner by lever-
aging the whole image database, including tagging, refining
query by dragging and dropping objects from search results,
as well as editing objects. After each action, the search re-
sults will be updated in real time to provide users up-to-date
materials to further formulate the query. By the deliberate
but easy design of the query, MindFinder not only tries to
enable users to present on the query panel whatever they
are imagining, but also returns to users the most similar
images to the picture in users’ mind. By scaling up the im-
age database to 10 million, MindFinder has the potential
to reveal whatever in users’ mind, that is where the name
MindFinder comes from.
In this technical demonstration, we showcase theMindFindersystem − a novel image search engine. Different from ex-isting interactive image search engines, most of which onlyprovide image-level relevance feedback, MindFinder enablesusers to sketch and tag query images at object level. By con-sidering the image database as a huge repository, MindFinderis able to help users present and refine their initial thoughtsin their mind, and finally turn thoughts to a beautiful im-age(s). Multiple actions are enabled for users to flexibly de-sign their queries in a bilateral interactive manner by lever-aging the whole image database, including tagging, refiningquery by dragging and dropping objects from search results,as well as editing objects. After each action, the search re-sults will be updated in real time to provide users up-to-datematerials to further formulate the query. By the deliberatebut easy design of the query, MindFinder not only tries toenable users to present on the query panel whatever theyare imagining, but also returns to users the most similarimages to the picture in users’ mind. By scaling up the im-age database to 10 million, MindFinder has the potentialto reveal whatever in users’ mind, that is where the nameMindFinder comes from.
การแปล กรุณารอสักครู่..