Score Prediction Network and Graph-based Selection for Semantic Line Detection

Dongkwon Jin, Chang-Su Kim

Abstract: In this paper, we propose a novel semantic line detection algorithm. For an input image, we first detect semantic lines using a semantic line detector by classifying candidate lines. Then, we predict scores indicating whether they are harmonized or not between the detected lines. To this end, we develop a score prediction network (SPNet). Finally, we construct a graph consisting of the detected lines and the predicted scores between them and iteratively select the reliable semantic lines. Experimental results demonstrate that the proposed algorithm detects semantic lines accurately.