Improved kernel density peaks clustering for plant image segmentation applications

Jiaze Bi, Pingzhe Zhang, Yujia Gao, Menglong Dong, Yongzhi Zhuang, Ao Liu, Wei Zhang, Yiqiong ChenJournal of Intelligent Systems 2023 · DOI

Abstract

Precision agriculture relies heavily on accurate plant segmentation to monitor growth and health. However, traditional clustering methods like $k$-means and Density Peaks Clustering (DPC) often struggle with the non-convex shapes of plants and the "chain reaction" errors caused by misclassified boundary points. This paper proposes an improved DPC method that utilizes Gaussian kernel mapping and a novel two-stage point assignment strategy. By projecting data into a high-dimensional feature space and employing a "temporary boundary point" to halt initial assignments, the method achieves superior segmentation accuracy on complex agricultural images and standard benchmarks.

Introduction

In agricultural image processing, segmenting early-stage crops from soil is challenging due to two primary factors. First, the color profiles of young plants and surrounding soil are often highly similar, rendering simple thresholding ineffective. Second, traditional DPC algorithms suffer from a "chain reaction" error: because points are assigned to the same cluster as their nearest neighbor of higher density, a single misclassification at a cluster boundary can trigger a cascade of errors, pulling unrelated data points into the wrong group.

Methodology

The proposed method addresses these limitations through a three-phase workflow: centroid selection, high-dimensional mapping, and a two-stage allocation strategy.

The proposed workflow for plant image segmentation using kernel density peaks clustering.

1. Centroid Selection and Kernel Mapping

Following the DPC paradigm, cluster centers are identified using a decision graph that plots local density ($\rho$) against the distance from points of higher density ($\delta$). To handle non-linearly separable data, the algorithm projects the input features into a high-dimensional space using a Radial Basis Function (RBF) Gaussian kernel. This transformation allows complex, interlocking shapes to be separated more effectively than in the original Euclidean space.

2. Two-Stage Allocation Strategy

To prevent the "chain reaction" error, the authors introduce a two-stage assignment process:

  • First Stage: Starting from the identified centroids, the algorithm performs a similarity search in the high-dimensional space. This process continues until it reaches a temporary boundary point, defined by a similarity threshold ($d_q$). This ensures that only points with high confidence are clustered initially.
  • Second Stage: Once the core of the clusters is established, the remaining unassigned points are allocated to the cluster with which they share the highest overall similarity, rather than just following a single nearest neighbor.
Illustration of the temporary boundary point mechanism (a) and cluster distribution (b).

Experimental Results

The algorithm was validated against $k$-means, DPC, and Fuzzy c-means across synthetic, UCI, and agricultural datasets.

  • Synthetic Datasets: The method achieved perfect scores (1.0) for Accuracy (ACC) and Normalized Mutual Information (NMI) on complex shapes like Spiral and Two Moons, where $k$-means failed due to its assumption of spherical clusters.
  • UCI Benchmarks: On the Robot Navigation dataset, the proposed method reached an ACC of 0.7428, a significant improvement over the 0.3616 achieved by traditional DPC.
  • Plant Segmentation: In practical applications using the Leaf Counting Dataset, the method demonstrated high robustness. It successfully outlined plant structures even when soil brightness varied significantly, avoiding the "muddy" edges and misclassifications common in other clustering approaches.

Conclusion

By combining high-dimensional kernel mapping with a robust two-stage allocation strategy, this improved DPC method effectively mitigates the cascading errors inherent in traditional density-based clustering. While the current implementation requires some manual parameter tuning for the decision graph, future work will focus on automating centroid selection to create a fully autonomous segmentation pipeline for precision agriculture.

Summary updated

Abstract

Abstract In order to better solve the shortcomings of the k -means clustering method and density peaks clustering (DPC) method in agricultural image segmentation, this work proposes a method to divide points in a high-dimensional space, and a clustering method is obtained to divide crops and soil. In the process of assigning points in the DPC method, if a point is divided incorrectly, a series of points may be assigned to a cluster that is not related to it. In response to this problem, this study uses the decision graph to select the centroids, and uses Gaussian kernel to map the data to the high-dimensional space, each centroid searches for the most relevant points in the high-dimensional space until a temporary boundary point is found to stop the first assignment strategy, and then the points that are not clustered are assigned to the correct cluster to complete the clustering. The experimental results show that the proposed method has a better clustering effect through experiments on multiple artificial datasets and UCI datasets, compared with other clustering methods, and finally applied to plant image segmentation.
BibTeX
@article{bi2023improved,
  author = {Jiaze Bi and Pingzhe Zhang and Yujia Gao and Menglong Dong and Yongzhi Zhuang and Ao Liu and Wei Zhang and Yiqiong Chen},
  title = {{Improved kernel density peaks clustering for plant image segmentation applications}},
  journal = {Journal of Intelligent Systems},
  year = {2023},
  doi = {10.1515/jisys-2022-0151},
}
Figure