Welcome to Journal of Graphics share: 

Journal of Graphics ›› 2023, Vol. 44 ›› Issue (1): 41-49.DOI: 10.11996/JG.j.2095-302X.2023010041

• Image Processing and Computer Vision • Previous Articles     Next Articles

Cell counting method based on multi-scale feature fusion

ZHANG Qian(), WANG Xia-li(), WANG Wei-hao, WU Li-zhan, LI Chao   

  1. School of Information Engineering, Chang?an University, Xi?an Shaanxi 710064, China
  • Received:2022-04-09 Revised:2022-06-15 Online:2023-10-31 Published:2023-02-16
  • Contact: WANG Xia-li
  • About author:ZHANG Qian (1996-), master student. Her main research interests cover graphic image processing and computer vision. E-mail:975573734@qq.com
  • Supported by:
    National Natural Science Foundation of China(51678061)

Abstract:

To address the problem of low cell counting accuracy caused by factors such as cell size variation in cell counting work, the highly crowded target recognition network CSRNet was introduced and improved, and a cell counting method based on multi-scale feature fusion was constructed. First, the first 10 layers of VGG16 were employed to extract cell features, avoiding the loss of small target information due to the deep network. Then, the spatial pyramid pooling structure was introduced to extract the multi-scale features of cells and perform feature fusion, reducing the counting errors caused by different cell shapes, sizes, and cell occlusion. Then the feature map was decoded using the hybrid dilated convolution to obtain the density map, solving the problem of missing pixels in the decoding process of CSRNet. Finally, the density map was regressed pixel by pixel to obtain the total number of cells. In addition, a new combined loss function was introduced in the training process to replace the Euclidean loss function, which not only considered the relationship between the ground truth density map and the single pixel point of the predicted density map, but also considered the global and local density levels. Experiments show that the optimized CSRNet could yield better results on VGG cells and MBM cells datasets, effectively improving the low cell counting accuracy caused by factors such as cell size variation.

Key words: cell counting, multi-scale feature fusion, density estimation, spatial pyramid pooling, hybrid dilated convolution

CLC Number: