Journals / Bilgi Dünyası / 2008 / Cilt: 9 - Sayı: 1

Performance Evaluation of Image Search Engines Based on the Number of Query Words

Resim Arama Motorlarının Sorgu Sözcük Sayısına Göre Performans Değerlendirmeleri

Pages
126–139
Publication Date
2022-10-12
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Retrieval performance of image search engines needs to be improved.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this article, the impact of the number of query words on information retrieval effectiveness of image search engines was investigated.
📊
Key Findings & Data:Then, 40 queries were extracted from the list of Wordtrackerand categorized in four groups as one-, two-, three- and four-word queries.
💡
Conclusion & Impact:Retrieval performance of image search engines needs to be improved.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

In this article, the impact of the number of query words on information retrieval effectiveness of image search engines was investigated. First of all, three popular search engines, namely, Google, Yahoo and MSN, were selected. Then, 40 queries were extracted from the list of Wordtrackerand categorized in four groups as one-, two-, three- and four-word queries. After every query was run on the selected image search engines and binary human relevance judgments were done, the performance evaluation of image search engines was carried out on two cut-off points (first 10 and first 20 retrievals) in terms of precision and normalized recall. In general, the information retrieval effectiveness of image search engines decreases as the number of query words increases. Retrieval performance of image search engines needs to be improved.

Özet

Bu çalışmada, sorgu sözcük sayısının bilgi erişim etkinliği açısından resim arama motorları üzerindeki etkisi araştırılmıştır. Öncelikle, üç popüler resim arama motoru (Google, Yahoo ve MSN) seçilmiş ve Wordtracker’ın yayımlamış olduğu en sık aranan sorgular listesinden alınan 40 sorgu bir, iki, üç ve dört sözcüklü sorgu grupları şeklinde sınıflandırılmıştır. Seçilen sorgu sözcükleri resim arama motorlarında ayrı ayrı çalıştırılmış ve erişim çıktıları üzerinde ilgililik değerlendirmeleri yapılmıştır. Daha sonra arama motorlarının iki farklı kesme noktası (ilk 10 ve ilk 20) üzerinden farklı sorgu sözcük sayılarına göre erişim performansları duyarlılık ve normalize sıralama ölçütleri kullanılarak değerlendirilmiş ve genelde sorgu sözcük sayısı arttıkça resim arama motorlarının bilgi erişim etkinliklerinde düşüş gözlenmiştir. Resim arama motorlarının geliştirilmesine ihtiyaç vardır.

🔖

Cite This Article

EMİRZADE, E., BİTİRİM, Y. (2022). Performance Evaluation of Image Search Engines Based on the Number of Query Words. Bilgi Dünyası, Cilt: 9 - Sayı: 1, 126–139. https://ajindex.com/articles/464561

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (10)

  1. Bitirim, Y., Tonta, Y. ve Sever, H. (2002). Information retrieval effectiveness of Turkish search engines. T. Yakhno (Ed.), Advances in Information Systems: Second International Conference, ADVIS 2002,
  2. İzmir,
  3. Turkey, October 23-25, 2002, Proceedings içinde (s. 93-103). Berlin: Springer-Verlag. Brilakis, I., ve Soibelman, L. (2005). Content-based search engines for construction image databases. Automation in Construction, 14, 537-550.
  4. Fukumoto, T. (2006). An analysis of image retrieval behavior for metadata type image database. Information Processing & Management, 42, 723-728.
  5. Jansen, B.J. ve Spink, A. (2003). An analysis of web information retrieved and viewed. H.R. Arabnia ve Y. Mun (Ed.), Proceedings of the International Conference on Internet Computing, IC ’03, Las Vegas, Nevada, June 23-26, 2003 (2 vols.) içinde (s. 65-69). Las Vegas: CSREA. 21 Temmuz 2007 tarihinde http://www.viktoria.se/~dixi/BISON/resources/ jansenspink- 2003.pdf adresinden erişildi. Kuwabara, A. ve Tanaka, K. (2005). RelaxImage: A cross-media metasearch engine for searching images from web based on query relaxation. Proceedings of the 21st International Conference on Data Engineering, ICDE 2005, April 5-8, 2005,
  6. Tokyo, Japan içinde (s. 1102-1103). Tokyo: IEEE Computer Society. Stevenson, K. ve Leung, C. (2005). Comparative evaluation of web image search engines for multimedia applications. H.Ip.A. Smeaton, J. Smith ve A.W.M. Smeulders (Ed.), Proceedings of the International Conference on Multimedia and Expo, July 6-8, 2005,
  7. Amsterdam, The Netherlands içinde (s. 4). Amsterdam: IEEE Press.
  8. Van Rijsbergen, C.J. (1979). Information retrieval (2nd ed.). London: Butterworths. Vaughan, L. (2004). New measurements for search engine evaluation proposed and tested. Information Processing & Management, 40, 677–691.
  9. Yao, Y.Y. (1995). Measuring retrieval effectiveness based on user preference of documents. Journal of the American Society for Information Science, 46, 133-145.
  10. Zhang, J. ve Mostafa, J. (2002). Examining the relationships among user involvement, profile quality, and information filtering performance. Proceedings of the American Society for Information Science and Technology Annual Meeting, 39, 298-306.