Method, system, and medium for retrieving photo using multimodal information
First Claim
1. A photo retrieval method implemented by a computing device which comprises a category assignor, an expansion retriever, a ranking determiner and a photo arranger, the method comprising:
- using the category assignor, assigning an object category based on a query;
using the expansion retriever, retrieving photos associated with an expanded query term extracted from the query;
using the ranking determiner, identifying a category with respect to each retrieved photo by referring to content of each retrieved photo;
using the ranking determiner, measuring a level of consistency between the assigned object category and the identified category for each retrieved photo and determining an Image_Score corresponding to each measured level of consistency;
using the ranking determiner, assigning a score to each retrieved photo by applying the determined Image_Score and a previously provided weight;
using the ranking determiner, determining a ranking of the retrieved photos based on the assigned score; and
using the photo arranger, arranging and displaying the photos in response to the determined ranking,wherein, in assigning the score to each retrieved photo, each score si given to the photo is calculated by satisfying an equation as
si=w×
TF_IDF_Score+(1−
w)×
Image_Scorein which w is a weight for TF_IDF_Score, wherein;
each TF_IDF_Score is a value of modeling a probability that the expanded query term is included in the memo information of the corresponding photo, andImage_Score is a probability that the category exists.
1 Assignment
0 Petitions
Accused Products
Abstract
A photo retrieval method, system, and medium using multimodal information which prevents a photo of an irrelevant category to be retrieved having a high ranking due to an unfavorable side effect from a query expansion, by reflecting a level of consistency between an object category of a query and a category of a photo retrieved by expansion retrieval using ontology, to a photo retrieval result ranking is provided. The photo retrieval method using the multimodal information includes: assigning an object category with respect to a query; retrieving photos associated with an expanded query term extracted from the query; determining a ranking of the retrieved photo by reflecting the assigned object category; and arranging and displaying the photos in response to the determined ranking.
49 Citations
18 Claims
-
1. A photo retrieval method implemented by a computing device which comprises a category assignor, an expansion retriever, a ranking determiner and a photo arranger, the method comprising:
-
using the category assignor, assigning an object category based on a query; using the expansion retriever, retrieving photos associated with an expanded query term extracted from the query; using the ranking determiner, identifying a category with respect to each retrieved photo by referring to content of each retrieved photo; using the ranking determiner, measuring a level of consistency between the assigned object category and the identified category for each retrieved photo and determining an Image_Score corresponding to each measured level of consistency; using the ranking determiner, assigning a score to each retrieved photo by applying the determined Image_Score and a previously provided weight; using the ranking determiner, determining a ranking of the retrieved photos based on the assigned score; and using the photo arranger, arranging and displaying the photos in response to the determined ranking, wherein, in assigning the score to each retrieved photo, each score si given to the photo is calculated by satisfying an equation as
si=w×
TF_IDF_Score+(1−
w)×
Image_Scorein which w is a weight for TF_IDF_Score, wherein; each TF_IDF_Score is a value of modeling a probability that the expanded query term is included in the memo information of the corresponding photo, and Image_Score is a probability that the category exists. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. At least one computer readable medium storing instructions that control at least one processor for executing a photo retrieval method implemented by a computing device which comprises of a category assignor, an expansion retriever, a ranking determiner and a photo arranger, the method comprising:
-
using the category assignor, assigning an object category based on a query; using the expansion retriever, retrieving photos associated with an expanded query term extracted from the query; using the ranking determiner, identifying a category with respect to each retrieved photo by referring to content of each retrieved photo; using the ranking determiner, measuring a level of consistency between the assigned object category and the identified category for each retrieved photo and determining an Image_Score corresponding to each measured level of consistency; using the ranking determiner, assigning a score to each retrieved photo by applying the determined Image_Score and a previously provided weight; using the ranking determiner, determining a ranking of the retrieved photos based on the assigned score; and using the photo arranger, arranging and displaying the photos in response to the determined ranking, wherein, in assigning the score to each retrieved photo, each score si given to the photo is calculated by satisfying an equation as
si=w×
TF_IDF_Score+(1−
w)×
Image_Scorein which w is a weight for TF_IDF_Score, wherein; each TF_IDF_Score is a value of modeling a probability that the expanded query term is included in the memo information of the corresponding photo, and Image Score is a probability that the category exists.
-
-
11. A photo retrieval system to retrieve photos using computing device which comprises a category assignor, an expansion retriever, a ranking determiner and a photo arranger, the system comprising:
-
a memory coupled to the computing device; the category assignor to assign an object category based on a query; the expansion retriever to retrieve photos associated with an expanded query term extracted from the query; the ranking determiner to identify a category with respect to each retrieved photo by referring to content of each retrieved photo, to measure a level of consistency between the assigned object category and the identified category for each retrieved photo and to determine an Image_Score corresponding to the measured level of consistency, to assign a score to each retrieved photo by applying the determined Image—
Score and a previously provided weight, and to determine a ranking of the retrieved photos based on the assigned score; andthe photo arranger to arrange and display the photos in response to the determined ranking, wherein the ranking determiner calculates a score si given to each photo, by satisfying an equation as
si=w×
TF_IDF_Score+(1−
w)×
Image_Scorein which w is a weight for TF_IDF_Score, wherein; each TF_IDF_Score is a value of modeling a probability that the expanded query term is included in the memo information of the corresponding photo, and Image_Score is a probability that the category exists. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18)
-
Specification