Partial discharge (PD) detection is critical for ensuring the stable operation of Gas Insulated Switchgear (GIS) equipment. This paper addresses the issue of partial discharge pattern recognition in GIS by collecting and analyzing Ultra High Frequency (UHF) signals from PD using UHF sensors. Firstly, four typical discharge models commonly found in GIS were constructed, the corresponding discharge signals were collected using UHF sensors. By transforming the acquired signals into Phase Resolved Partial Discharge (PRPD) patterns, multiple features are extracted, including traditional statistical features and Tamura texture features. Subsequently, a K-Nearest Neighbors (KNN) classifier is employed to classify and identify the extracted features. Experimental results demonstrate that the classification accuracy is significantly improved when using Tamura texture features compared to traditional statistical features.