Cobalt, as a rare metal, plays an important role in strategic resources due to its physical, chemical, and mechanical properties in applications. In order to achieve automatic control of the cobalt extraction process, it is necessary to conduct online detection of the color characteristics of the cobalt extraction solution. Unfortunately, due to the lack of online automatic detection methods for the color of cobalt extraction solution, the automatic control of the extraction process has not yet been achieved. Currently, the color of cobalt extraction solution needs to be observed and judged by operators based on experience. This will result in significant detection errors and time lag. To change this situation, an online detection method for color features of cobalt extraction solution based on machine vision is proposed in this article. Firstly, we establish a real-time image acquisition environment for detecting object colors, and then use the Gaussian filters and K-means algorithm to denoise and segment the image. In order to correct color distortion in images caused by ambient light, we measure the color feature values of a set of standard color cards using the machine vision system and a standard spectrophotometer. Based on this test data, we establish chromaticity correction models for the extraction solution using back propagation (BP) network and radial basis function (RBF) network, respectively. The models can correct the color characteristic values of the extraction solution, overcome environmental interference, and thus obtain more accurate color characteristic values of the extraction solution. The established model can be used for online automatic color detection of cobalt extraction solution. The modeling results indicate that in the established color measurement environment, the RBF network model outperforms the BP network model in color feature detection accuracy.