In previous studies, the retrieval accuracy of large image databases has been improved as a result of reducing the semantic gap by combining the input sketch with relevance feedback. A further improvement of retrieval accuracy is expected by combining each stroke, and its order, of the input sketch with the relevance feedback. However, this leaves as a problem the fact that the effect of the relevance feedback substantially depends on the stroke order in the input sketch. Although it is theoretically possible to consider all the possible stroke orders, that would cause a realistic problem of creating an enormous amount of data. Consequently, the technique introduced in this paper intends to improve retrieval efficiency by effectively using the relevance feedback by means of conducting data mining of the sketch considering the similarity in the order of strokes. To ascertain the effectiveness of this technique, a retrieval experiment was conducted using 20,000 images of a collection, the Corel Photo Gallery, and the experiment was able to confirm an improvement in the retrieval efficiency.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Takashi HISAMORI, Toru ARIKAWA, Gosuke OHASHI, "Query-by-Sketch Image Retrieval Using Similarity in Stroke Order" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 6, pp. 1459-1469, June 2010, doi: 10.1587/transinf.E93.D.1459.
Abstract: In previous studies, the retrieval accuracy of large image databases has been improved as a result of reducing the semantic gap by combining the input sketch with relevance feedback. A further improvement of retrieval accuracy is expected by combining each stroke, and its order, of the input sketch with the relevance feedback. However, this leaves as a problem the fact that the effect of the relevance feedback substantially depends on the stroke order in the input sketch. Although it is theoretically possible to consider all the possible stroke orders, that would cause a realistic problem of creating an enormous amount of data. Consequently, the technique introduced in this paper intends to improve retrieval efficiency by effectively using the relevance feedback by means of conducting data mining of the sketch considering the similarity in the order of strokes. To ascertain the effectiveness of this technique, a retrieval experiment was conducted using 20,000 images of a collection, the Corel Photo Gallery, and the experiment was able to confirm an improvement in the retrieval efficiency.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.1459/_p
Copy
@ARTICLE{e93-d_6_1459,
author={Takashi HISAMORI, Toru ARIKAWA, Gosuke OHASHI, },
journal={IEICE TRANSACTIONS on Information},
title={Query-by-Sketch Image Retrieval Using Similarity in Stroke Order},
year={2010},
volume={E93-D},
number={6},
pages={1459-1469},
abstract={In previous studies, the retrieval accuracy of large image databases has been improved as a result of reducing the semantic gap by combining the input sketch with relevance feedback. A further improvement of retrieval accuracy is expected by combining each stroke, and its order, of the input sketch with the relevance feedback. However, this leaves as a problem the fact that the effect of the relevance feedback substantially depends on the stroke order in the input sketch. Although it is theoretically possible to consider all the possible stroke orders, that would cause a realistic problem of creating an enormous amount of data. Consequently, the technique introduced in this paper intends to improve retrieval efficiency by effectively using the relevance feedback by means of conducting data mining of the sketch considering the similarity in the order of strokes. To ascertain the effectiveness of this technique, a retrieval experiment was conducted using 20,000 images of a collection, the Corel Photo Gallery, and the experiment was able to confirm an improvement in the retrieval efficiency.},
keywords={},
doi={10.1587/transinf.E93.D.1459},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Query-by-Sketch Image Retrieval Using Similarity in Stroke Order
T2 - IEICE TRANSACTIONS on Information
SP - 1459
EP - 1469
AU - Takashi HISAMORI
AU - Toru ARIKAWA
AU - Gosuke OHASHI
PY - 2010
DO - 10.1587/transinf.E93.D.1459
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2010
AB - In previous studies, the retrieval accuracy of large image databases has been improved as a result of reducing the semantic gap by combining the input sketch with relevance feedback. A further improvement of retrieval accuracy is expected by combining each stroke, and its order, of the input sketch with the relevance feedback. However, this leaves as a problem the fact that the effect of the relevance feedback substantially depends on the stroke order in the input sketch. Although it is theoretically possible to consider all the possible stroke orders, that would cause a realistic problem of creating an enormous amount of data. Consequently, the technique introduced in this paper intends to improve retrieval efficiency by effectively using the relevance feedback by means of conducting data mining of the sketch considering the similarity in the order of strokes. To ascertain the effectiveness of this technique, a retrieval experiment was conducted using 20,000 images of a collection, the Corel Photo Gallery, and the experiment was able to confirm an improvement in the retrieval efficiency.
ER -