In modern industrial production, quantity statistics and quality inspection face problems of low accuracy and efficiency. This study proposes a method that combines principal component analysis (PCA) and normalized cross-correlation (NCC) to extract features from collected product image data using PCA, and reduces high-dimensional data to principal component space to form a feature template library. Then, for each product to be tested on the assembly line, the article calculates its feature vector and the NCC value of each template in the template library to determine the best matching template. By comparing the NCC values, the specific model of the product is identified and the quantity is counted. Finally, the article uses the NCC algorithm to perform quality inspection on product images, identifying possible defects or anomalies by analyzing the correlation between images. The experimental results show that the algorithm is significantly better than manual detection in terms of statistical time and accuracy. In terms of quality inspection, the accuracy of defect detection by algorithms is generally higher than that of manual detection, especially in multiple samples, with a difference of over 17%. Therefore, by combining PCA and NCC, this study not only improves the accuracy and efficiency of product quantity statistics and quality inspection but also provides the possibility of using automated inspection systems in a wider range of application scenarios in the future.