A Study on Lung Image Retrieval Based on the Vocabulary Tree

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10361)

Abstract

Nowadays, the image retrieval technology has aroused the wide concern and achieved the significant effect in the area of medical image retrieval. However, the traditional image retrieval method based on the image bottom-layer features is inefficient. With the increase in the volume of retrieval data, its shortcoming has become obvious. To promote the accuracy of retrieval, Scale-invariant feature transform (SIFT) lung feature extraction algorithm was chosen as the descriptor in this study. For such case, the method of vocabulary tree was introduced to extract the recognition features of lung image, as well as the medical retrieval of lung images using the obtained features. In the development environment of MATLAB, the reading, storage and retrieval of medical images were performed to create a full set of algorithmic retrieval system finally. The vocabulary tree-based retrieval method and the medical image processing were employed to denoise the images, SIFT extraction to extract the image features, K-means clustering that mapped to the feature space to turn the extracted features into the vocabulary tree. According to the experimental results, the algorithm proposed in this study is able to achieve good results.

Keywords

Image processing Vocabulary tree SIFT extraction K-means clustering Lung image retrieval 

References

  1. 1.
    Jian, Z., Yu, X., Chen, X., et al.: Research of image retrieval based on vocabulary tree in virtual university. In: International Conference on E-Business and E-Government, pp. 4313–4316 (2010)Google Scholar
  2. 2.
    Seo, H., Lee, J.: Object recognition algorithm using a vocabulary tree and a pre-matching array. Artif. Life Robot. 15(1), 93–96 (2010)CrossRefGoogle Scholar
  3. 3.
    Wu, Z., Yang, Z., Sun, H., et al.: Hybrid radar emitter recognition based on rough k -means classifier and SVM. EURASIP J. Adv. Sig. Process. 2012(1), 198 (2012)CrossRefGoogle Scholar
  4. 4.
    Masami, A., Jitendra, A.: Decision tree-based acoustic models for speech recognition. EURASIP J. Audio Speech Music Process. 2012(1), 10 (2012)CrossRefGoogle Scholar
  5. 5.
    Jason, K.: Content-based image retrieval using deep belief networks. University of Kansas (2010)Google Scholar
  6. 6.
    Carlos, M., Travieso, M., Jesús, B.: Fused intra-bimodal face verification approach based on scale-invariant feature transform and a vocabulary tree. J. Pattern Recogn. Lett. 36, 254–260 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Shandong Provincial Key Laboratory of Network Based Intelligent ComputingUniversity of JinanJinanPeople’s Republic of China
  2. 2.School of Information Science and EngineeringUniversity of JinanJinanPeople’s Republic of China

Personalised recommendations