Rapid standardization of rock color determination is a crucial aspect of geological research. Current methods primarily rely on expert visual description, Munsell color chart comparison, and spectral analysis, which fall short of meeting the demands for rapid and accurate rock color identification and digital standardization during extensive indoor and outdoor core observations. This paper proposes a computer vision-based intelligent rock color recognition method. Based on the Codes for names and colors of rocks in the petroleum geology (SY/T 5751—2012), a standard database containing 112 rock colors is constructed. Three algorithms—color thresholding, edge detection, and GrabCut—are designed to accurately segment target rock regions. Digital analysis, including color feature extraction, is performed on coordinate-based and gridded images to calculate the color vector of the rock image. Addressing the challenge of accurately identifying similar color systems, a weighted multi-feature fusion color matching algorithm is designed, incorporating evaluation indicators such as cosine similarity, Euclidean distance, RGB component differences, and brightness factor, significantly improving the system's ability to identify similar hues. A visualized intelligent rock color recognition system is developed using Python programming language and the PyQT6 framework, achieving digital quantitative identification of rock colors and improving recognition accuracy and efficiency. The results show that the system's identification results for 35 rock samples are highly consistent with the Munsell color chart interpretation results, with the consistency of hue (H), value (V), and chroma (C) reaching 91.43%, 85.71%, and 71.43%, respectively. The system also shows complete consistency in the identification of independent test samples, verifying the correctness of the core algorithm logic, and the average identification time can reach the millisecond level.