Open Access

ARTICLE

The Crime Scene Tools Identification Algorithm Based on GVF‐Harris‐SIFT and KNN

Nan Pan¹, Dilin Pan², Yi Liu²

1 Faculty of Civil Aviation and Aeronautical, Kunming University of Science & Technology, Kunming 650500, P.R. China
2 Kunming SNLab Tech Co., Ltd., Kunming 650228, P.R. China

* Corresponding Author: Nan Pan,

Intelligent Automation & Soft Computing 2019, 25(2), 413-419. https://doi.org/10.31209/2019.100000103

Abstract

In order to solve the cutting tools classification problem, a crime tool identification algorithm based on GVF-Harris-SIFT and KNN is put forward. The proposed algorithm uses a gradient vector to smooth the gradient field of the image, and then uses the Harris angle detection algorithm to detect the tool angle. After that, the descriptors of the eigenvectors in corresponding feature points were using SIFT to obtained. Finally, the KNN machine learning algorithms is employed to for classification and recognition. The experimental results of the comparison of the cutting tools show the accuracy and reliability of the algorithm.

---

Keywords

---