An Efficient MLP-based Point-guided Segmentation Network for Ore Images with Ambiguous Boundary
This work addresses a domain-specific challenge in mineral processing by improving segmentation accuracy and efficiency for ore images, though it appears incremental as it builds on existing MLP and feature pyramid methods.
The paper tackles the problem of segmenting ore images with ambiguous boundaries by proposing a lightweight MLP-based network, achieving a processing speed of over 27 FPS with a model size of 73 MB and accuracy scores of 60.4 in AP50^box and 48.9 in AP50^mask.
The precise segmentation of ore images is critical to the successful execution of the beneficiation process. Due to the homogeneous appearance of the ores, which leads to low contrast and unclear boundaries, accurate segmentation becomes challenging, and recognition becomes problematic. This paper proposes a lightweight framework based on Multi-Layer Perceptron (MLP), which focuses on solving the problem of edge burring. Specifically, we introduce a lightweight backbone better suited for efficiently extracting low-level features. Besides, we design a feature pyramid network consisting of two MLP structures that balance local and global information thus enhancing detection accuracy. Furthermore, we propose a novel loss function that guides the prediction points to match the instance edge points to achieve clear object boundaries. We have conducted extensive experiments to validate the efficacy of our proposed method. Our approach achieves a remarkable processing speed of over 27 frames per second (FPS) with a model size of only 73 MB. Moreover, our method delivers a consistently high level of accuracy, with impressive performance scores of 60.4 and 48.9 in~$AP_{50}^{box}$ and~$AP_{50}^{mask}$ respectively, as compared to the currently available state-of-the-art techniques, when tested on the ore image dataset. The source code will be released at \url{https://github.com/MVME-HBUT/ORENEXT}.