In recent years, with the development of science and technology, the emerging competitive markets in various industries, and the need for quality control, quantitative and qualitative measurements of products' properties have become significantly important. Quality production is the most vital part of a production line in a way that a few factories exist, with some of their sectors not being controlled by intelligent Computer Vision (CV) and image processing systems. Accordingly, Real-time quality management can increase production efficiency. Moreover, quality management focuses on customer experience with agents and products. In this regard, Sentiment Analysis (SA) can also determine the success rate of services and products, identify customers' thoughts, and mirror their true voice. This paper aims to conduct a comparative analysis of feature extraction approaches used by CV and Natural Language Processing (NLP) for quality control of products and SA in the industry. These approaches and trends can further be integrated into Web-based quality control systems in industry. Therefore, this paper also investigates how such technologies can enhance quality control through large-scale textual and image data analytics.