Rapid tool wear is a major concern of the machining operation, affecting the tooling cost and dimensional tolerance of the components. In line with Industry 4.0, rapid tool failure can be avoided by applying cyber-physical tool condition monitoring (TCM), which detects in-process tool wear evolution using sensors or machine vision systems, determining the actual time for tool replacement. Although sensor-based TCM is quick and adaptive in monitoring tool wear progression online, it cannot detect the failure modes to show the extent of wear severity on the tool’s cutting edge. On the other hand, machine vision systems effectively detect wear mechanisms that accelerate tool failure during machining. Therefore, this paper presents the practical application of machine vision systems in TCM and tool performance optimization (TPO). The findings in this research show that digital microscopes are used to monitor wear mechanisms, complementing TPO techniques in selecting the best cutting parameters that optimize tool performance. However, such techniques are time intensive and inefficient for real-time applications. With recent advances in imaging technology and artificial intelligence, an in-process machine vision-based TCM (MV-TCM) system is receiving more attention in intelligent manufacturing due to its efficient predictive capability. However, it is still in its infancy stage, relying on classical machine learning models, which are ineffective to extract high-level features on the tool wear images for in-process failure modes detection. Therefore, this paper highlights the significance of applying artificial intelligence to enhance MV-TCM capability for online failure modes detection and classification.