FARKLI BOYUTLARDA GÖRÜNTÜLERDE UYARLAMALI YEREL PENCERE İLE BENZERLİK ÖLÇÜMÜ

İçerik tabanlı görüntü erişim yöntemleri, renk, desen ve şekil bilgileri gibi farklı özelliklere ihtiyaç duymaktadır. Araştırmacılar, görüntü histogramından elde edilen verileri de bu bağlamda kullanmaktadır. Histogram bilgileri, yerel veya global olarak hesaplanır. Ancak, aynı içeriğe sahip olsalar da, farklı en / boy oranlarına sahip görüntülerde yerel yaklaşımlar kullanılamamakta ve tüm pikselleri işleyen yöntemler ile de her zaman istenilen sonuca varılamamaktadır. Bu çalışmada, farklı boyutlarda iki görüntüden, eşit sayıda pencere alınarak, görüntülerin benzerlik ölçümünde kullanılan ve yerel histograma dayanan yeni bir yöntem geliştirilmiştir. Geliştirilen yöntem, Weizmann tekli nesne görüntü bölütleme veritabanındaki 100 görüntü üzerinde test edilmiş ve yöntemin başarısı global histogram yaklaşımlarıyla karşılaştırılmıştır.

SIMILARITY MEASURE WITH ADAPTIVE LOCAL WINDOW IN DIFFERENT SIZE IMAGES

Content based image retrieval methods require different features such as color, pattern and shape information. The researchers also use the data obtained from the image histogram in this context. The histogram information is calculated locally or globally. However, even though they have the same content, local approaches cannot be used in images with different aspect ratios, and methods that process over the entire pixels cannot always give the desired results. In this study, a new method based on the local histogram, which is used for the similarity measurement of images, has been developed by providing equal number of windows from two images of different sizes. The developed method is tested on 100 images on Weizmann single object image segmentation database and the success of the method is compared with global histogram approaches.

___

  • Alpert, S., Galun, M., Brandt, A., & Basri, R., 2012. Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration. IEEE transactions on pattern analysis and machine intelligence, 34(2), 315-327.
  • Chitkara, V., 2001. Color-Based Image Retrieval Using Compact Binary Signatures, Tech. Report TR 01-08, University of Alberta Edmonton, Alberta, Canada.
  • Ioka, M., 1989. A Method of Defining the Similarity of Images on the Basis of Color Information, Tech. ReportRT-0030, IBM Tokyo Research Lab.
  • Niblack, C.W., Barber, R., Equitz, V., Flickner, M.D., Glasman, E.H., Petkovic, D., … & Taubin, G., 1993. The QBIC Project: Querying Images by Content Using Color, Texture and Shape, Proc. of IS & T/SPIE Int. Symp. on Electronic Imaging: Science & Technology, 1908: Storage and Retrieval for Image and Video Databases, 173-187.
  • Stricker, M., Dimai, A., 1997. Spectral Covariance and Fuzzy Regions for Image Indexing, Machine Vision Applications, 10(2), 66–73.
  • Stricker, M., Orengo, M., 1995. Similarity of Color Images, Proc. of the SPIE Conf., 2420, 381–392.
  • Swain, M.J., Ballard, D.H., 1991. Color Indexing, Int. J. Computer Vision, 7(1), 11–32.
  • Tanyeri, U., İncetaş, M.O., Aydemir, Z., 2017. Gürültülü Görüntü Üzerinde İnterpolasyon Etkisinin Filtre Yöntemleri ile İncelenmesi, 25. IEEE Sinyal İsleme ve İletişim Uygulamaları Kurultayı.
  • TinEye. (n.d.). Retrieved December 29, 2016, from http://www.tineye.com/faq#similar.
  • Vassilieva, N.S., 2009. Content-based Image Retrieval Methods. Programming and Computer Software, 35(3), 158-180.
  • Vassilieva, N., Novikov, B., 2005. Construction of Correspondences between Low-level Characteristics and Semantics of Static Images, Proc. of the 7th All-Russian Scientific Conf. “Electronic Libraries: Perspective Methods and Technologies, Electronic Collections”, RCDL’2005, Yaroslavl’, Russia.
  • Wang, Z., Lu, L., Bovik, A.C., 2004. Video Quality Assessment Based on Structural Distortion Measurement. Signal processing: Image communication, 19(2), 121-132.
  • What is the Algorithm Used by Google's Reverse Image Search (i.e. search by image)? (n.d.). Retrieved December 29, 2016, from https://www.quora.com/What-is-the-algorithm-used-by-Googles-reverse-image-search-i-e-search-by-image?redirected_qid=828413.
  • Who were They? (n.d.). Retrieved May 24, 2017, from https://www.myheritage.com.tr/
  • Xu, S., Li, C., Jiang, S., Liu, X.P., 2012. Similarity Measures for Content-Based Image Retrieval Based on Intuitionistic Fuzzy Set Theory. JCP, 7(7), 1733-1742.
  • Zhang, J., Deng, Y., Guo, Z., Chen, Y., 2016. Face Recognition Using Part-Based Dense Sampling Local Features. Neurocomputing, 184, 176-187.