Affiliation:
1. Ankara Yıldırım Beyazıt University
Abstract
Abstract
Content-based image retrieval involves searching for the desired image from an image database. It is realized through the feature vectors obtained from the architectural image in question. Therefore, feature extraction is a crucial step. In this study, a new feature vector representation is proposed. In the proposed study, a composite feature vector is obtained by using color, edge, and gradient features. In particular, the method applied for edge detection offers a non-linear approach that simulates the human visual system well. In addition, there is no need for any parameter or user intervention in edge detection. In the study, experiments were carried out in Corel 1K and Corel 10K databases, which are frequently used in image retrieval. The proposed study was compared with 13 different methods. When the results are examined, the superiority of the method draws attention.
Publisher
Research Square Platform LLC
Reference42 articles.
1. Manjunath, B. S., Salembier, P., Sikora, T. (Eds.). Introduction to MPEG-7: multimedia content description interface. John Wiley & Sons (2002)
2. Texture features for browsing and retrieval of image data;Manjunath BS;IEEE Transactions on pattern analysis and machine intelligence,1996
3. Color texture description with novel local binary patterns for effective image retrieval;Singh C;Pattern recognition,2018
4. Image retrieval based on the texton co-occurrence matrix;Liu GH;Pattern Recognition,2008
5. Liu, G. H. Content-based image retrieval based on cauchy density function histogram. In 2016 12th international conference on natural computation, fuzzy systems and knowledge discovery (ICNC-FSKD) (pp. 506–510). IEEE. (2016). https://doi.org/10.1109/FSKD.2016.7603225