Acta Entomologica Sinica ›› 2021, Vol. 64 ›› Issue (5): 611-617.doi: 10.16380/j.kcxb.2021.05.008

• RESEARCH PAPERS • Previous Articles     Next Articles

F3Net based salient object detection for automatic foreground-background segmentation of butterfly images

HUANG Shi-Guo1,2, HONG Ming-Lin2, ZHANG Fei-Ping1, HE Hai-Yang2, CHEN Yi-Qiang2, LI Xiao-Lin2,*   

  1.  (1. Key Laboratory of Integrated Pest Management in Ecological Forests, Fujian Province University, Fujian Agriculture and Forestry University, Fuzhou 350002, China; 2. Key Laboratory of Smart Agriculture and Forestry, Fujian Province University, Fujian Agriculture and Forestry University, Fuzhou 350002, China)
  • Online:2021-05-20 Published:2021-05-31

Abstract: 【Aim】 It is difficult to segment the foreground-background of butterfly images with complex backgrounds. This study aims to explore an automatic foreground-background segmentation method using deep learning based salient object detection method. 【Methods】 The F3Net salient object detection algorithm was trained by using the DUTS-TR dataset to obtain the foreground-background prediction model. Then the model was applied to the dataset of butterfly images with complex background to implement automatic foreground-background segmentation of images. To further improve the accuracy of automatic segmentation, transfer learning was utilized by keeping ResNet backbone unchanged and retraining network through cross feature module, cascade decoders and pixel sensitive loss module to optimize model parameters, and then the better automatic segmentation model was obtained. Meanwhile, other five salient object detection algorithms based on deep learning were also applied to automatic segmentation and compared with F3Net on performance. 【Results】 With all the algorithms good butterfly foreground-background segmentation results were obtained. Among these algorithms, F3Net was the better algorithm, and the algorithm got the values of 0.940, 0.945, 0.938, 0.024, 0.929, 0.978 and 0.909 for the seven indexes S-measure, E-measure, F-measure, mean absolute error (MAE), precision, recall and average IoU, respectively. Transfer learning further improved the values of the above indexes of F3Net, which were 0.961, 0.964, 0.963, 0.013, 0.965, 0.967 and 0.938, respectively. 【Conclusion】 The experimental results showed that F3Net with transfer learning is the best segmentation algorithm. The method developed in this study can be applied to automatic segmentation of insect images taken in field investigations and extends the application range of salient object detection methods.

Key words: Butterfly, salient object detection, deep learning, image segmentation, automatic segmentation, F3Net