JCSE, vol. 18, no. 2, pp.93-115, June, 2024

DOI: http://dx.doi.org/10.5626/JCSE.2024.18.2.93

TGMatting: Automatic Image Matting Based on Trimap Generation

Jianming Wang, Xiao Jiang, Yuhang Zhang, Jiting Yin, and Zizhong Yang
School of Mathematics and Computer, Dali University, Dali, China; Yunnan Provincial Key Laboratory of Entomological Biopharmaceutical R&D, Dali University, Dali, China/ School of Mathematics and Computer, Dali University, Dali, China/ Dali Forestry and Grassland Science Research Institute, Dali, China/ Yunnan Provincial Key Laboratory of Entomological Biopharmaceutical R&D, Dali University, Dali, China

Abstract: At present, automatic image matting methods primarily focus on portraits and hard edge targets, which gives them a limited ability to deal with low-resolution, complex, and blurred non-portrait targets. To address these issues, the current paper proposes an automatic image matting method called TGMatting. This method automatically optimizes Trimap generation through three modules: the U2S-Net pre-segmentation module, which is based on the U2-Net network, enhances segmentation by removing null convolutions and reducing oversampling interference; the BGTrimap module, which is also based on U2-Net, refines edge regions using optimized dilation-erosion methods and Manhattan distance for seed point sparsification, thus ensuring accurate region growth and background information removal; and in the last module, edges are transformed into mixed-pixel regions using Sobel operator and non-local-means denoising binarization, and a Trimap map is automatically generated by combining OTSU segmentation with pre-segmentation results, thus achieving fully automated processing. Finally, a transparency mask is obtained via FBAMatting, which enables interaction-free automatic matting. The experimental results demonstrate that the improved U2S-Net network reduces MAE by 0.003 on the SOD-Spider test set, enhances accurate detection of significant regions in low-resolution images compared to U2S-Net, and reduces BGTrimap's sum of absolute difference value by about 10% compared to other Trimap generation methods in IFMatting and KNN Matting.

Keyword: Image matting; Trimap generation; Deep learning; Saliency object detection (SOD)

Full Paper:   329 Downloads, 365 View