Querying Salient Objects

Let us express the query Q: ``find images with 2 people next to each other without any building, or images with buildings without people, or images with animals'' in VisualMOQL. This query is in fact a combination of three queries:

• Qa: images with 2 people next to each other without any building
• Qb: images with buildings without people
• Qc: images with animals

The final expression of the query is given in Figure . Qa is expressed in MOQL by (Query1 AND NOT Query2) where Query1 is a sub-query expressing images with two people one to the west of the other (see the working canvas of Figure ) and Query2 expresses images with buildings. Qb is expressed in MOQL by (Query3 AND NOT Query4) where Query3 expresses images with buildings and Query4 expresses images with people. Qc is expressed by the sub-query Query5 and expresses images with animals. The final expression is obtained by combining the sub-queries using the OR connective.

The VisualMOQL expression is translated into MOQL (Figure ) before being submitted to the query processor. Part of the query result can be seen in Figure . An image in a query result can be an input of a similarity query. This is done by clicking on the check box above the image thumbnail.