Agricultural pest image segmentation based on neighborhood algorithm

Liying Cao, Wenxuan Guo, Guifen Chen, Helong Yu

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Image segmentation is a key technology in image processing and computer vision systems. The effect of the image segmentation effect directly affects the analysis of subsequent images and the accuracy of the understanding. Therefore, for the agricultural pest image cannot distinguish the adjacent gray value when segmentation, this paper proposes a neighborhood algorithm. The algorithm of neighborhood segmentation determines the neighborhood of the pixel. In order to verify the effectiveness of the algorithm, this paper compares with K-means algorithm, DBSCAN algorithm, SNC algorithm, DMHAC algorithm and STING algorithm. Objective analysis indicators were measured by normalized correlation coefficient, segmentation time and segmentation accuracy. The verification results show that this method has achieved good results under these three indicators. The normalized correlation coefficient is close to 1, the time of segmentation consumption is the smallest and the accuracy is the highest among all methods. The effectiveness of the proposed algorithm is verified by experiments.

Original languageEnglish
Pages (from-to)1554-1565
Number of pages12
JournalRevista de la Facultad de Agronomia
Issue number5
StatePublished - 2019


  • Agricultural pest
  • Clustering method
  • Image segmentation
  • Neighborhood algorithm

Fingerprint Dive into the research topics of 'Agricultural pest image segmentation based on neighborhood algorithm'. Together they form a unique fingerprint.

Cite this