SkeletonNet: Shape Pixel to Skeleton Pixel

TL;DR

This paper presents SkeletonNet, a deep learning model based on U-net with HED-inspired decoder enhancements, for extracting skeleton pixels from object shapes, achieving an F1 score of 0.77.

Contribution

It introduces a novel U-net based architecture with a HED-inspired decoder for improved skeleton extraction from shape images.

Findings

Achieved an F1 score of 0.77 on test data.

Demonstrated improved skeleton extraction accuracy.

Proposed architecture effectively connects broken skeleton links.

Abstract

Deep Learning for Geometric Shape Understating has organized a challenge for extracting different kinds of skeletons from the images of different objects. This competition is organized in association with CVPR 2019. There are three different tracks of this competition. The present manuscript describes the method used to train the model for the dataset provided in the first track. The first track aims to extract skeleton pixels from the shape pixels of 89 different objects. For the purpose of extracting the skeleton, a U-net model which is comprised of an encoder-decoder structure has been used. In our proposed architecture, unlike the plain decoder in the traditional Unet, we have designed the decoder in the format of HED architecture, wherein we have introduced 4 side layers and fused them to one dilation convolutional layer to connect the broken links of the skeleton. Our proposed architecture achieved the F1 score of 0.77 on test data.