Image Searching System

: cc. 161 - 168
Lviv Polytechnic National University
Національний університет «Львівська політехніка», кафедра електронних обчислювальних машин

Finding similar images on a visual sample is a difficult AI task, to solve which many works are devoted. The problem is to determine the essential properties of images of low and higher semantic level. Based on them, a vector of features is built, which will be used in the future to compare pairs of images. Each pair always includes an image from the collection and a sample image that the user is looking for. The result of the comparison is a quantity called the visual relativity of the images. Image properties are called features and are evaluated by calculation algorithms. Image features can be divided into low-level and high-level. Low-level features include basic colors, textures, shapes, significant elements of the whole image. These features are used as part of more complex recognition tasks. The main progress is in the definition of high-level features, which is associated with understanding the content of images.

In this paper, research of modern algorithms is done for finding similar images in large multimedia databases. The main problems of determining high-level image features, algorithms of overcoming them and application of effective algorithms are described. The algorithms used to quickly determine the semantic content and improve the search accuracy of similar images are presented.

The aim: The purpose of work is to conduct comparative analysis of modern image retrieval algorithms and retrieve its weakness and strength.

  1. Ibtihaal M. Hameed, Sadiq H. Abdulhussain & Basheera M. Mahmmod | D T Pham (Reviewing editor) (2021) Content- based image retrieval: A review of recent trends, Cogent Engineering, 8:1, DOI: 10.1080/23311916.2021.1927469.
  2. Narendra Kumar Rout, Mithilesh Atulkar and Mitul Kumar Ahirwal. A review on content-based image retrieval system: present trends and future challenges. Published Online:August 19, 2021pp., 461-485, Available at:, (Accessed: 18 November 2021).
  3. Alsmadi, M.K. Content-Based Image Retrieval Using Color, Shape and Texture Descriptors and Features. Arab J Sci Eng 45, 3317–3330 (2020),
  4. Zenggang, X., Zhiwen, T., Xiaowen, C. et al. Research on Image Retrieval Algorithm Based on Combination of Color and Shape Features. J Sign Process Syst 93, 139–146 (2021),
  5. Juan Luo, Oubong Gwun. "A comparison of sift, pca-sift and surf." International Journal of Image Processing (IJIP) (2009): 143-152, Available at: 01.7041&rep=rep1&type=pdf, (Accessed: 18 November 2021).
  6. Ghrabat, M.J.J., Ma, G., Maolood, I.Y. et al. An effective image retrieval based on  optimized genetic algorithm utilized a novel SVM-based convolutional neural network classifier. Hum. Cent. Comput. Inf. Sci. 9, 31 (2019),
  7. William La Cava, Sara Silva, Kourosh Danai, Lee Spector, Leonardo Vanneschi, Jason H. Moore. Multidimensional genetic programming for multiclass classification, Swarm and Evolutionary Computation, Volume 44, 2019, Pages 260-272, ISSN        2210-6502,
  8. Haseena Sikkandar , Revathi Thiyagarajan. Soft biometrics- based face image retrieval using improved grey wolf optimization ISSN 1751-9659 Received on 7th March 2019 Revised 11th September 2019 Accepted on 14th October 2019 E-First on 27th January 2020, doi: 10.1049/iet- ipr.2019.0271,
  9. Xushan Peng, Xiaoming  Zhang,  Yongping  Li,  Bangquan Liu, Research on image feature extraction and retrieval algorithms based on convolutional neural network, Journal of Visual Communication and Image Representation, Volume      69,      2020,      102705,      ISSN      1047- 203,
  10. F. Luo, L. Zhang, X. Zhou, T. Guo, Y. Cheng and T. Yin, "Sparse-Adaptive Hypergraph Discriminant Analysis for Hyperspectral Image  Classification," in  IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 6, pp. 1082-1086, June 2020, doi: 10.1109/LGRS.2019.2936652.