One important aspect of assessing the quality in pulp and papermaking is dirt particle counting and classification. Knowing the number and types of dirt particles present in pulp is useful for detecting problems in the production process as early as possible and for fixing them. Since manual quality control is a time-consuming and laborious task, the problem calls for an automated solution using machine vision techniques. However, the ground truth required to train an automated system is difficult to ascertain, since all of the dirt particles should be manually segmented and classified based on image information. This paper proposes a framework for developing and tuning dirt particle detection and classification systems. To avoid manual annotation, dry pulp sheets with a single dirt type in each were exploited to generate semisynthetic images with the ground truth information. To classify the dirt particles, a set of features were computed for each image segment. Sequential feature selection was employed to determine a close-to-optimal set of features to be used in classification. The framework was tested both with semisynthetically generated images based on real pulp sheets and with independent original real pulp sheets without any generation. The results of the experiments show that the semisynthetic procedure does not significantly change the properties of images and has little effect on the particle segmentation. The feature selection proved to be important when the number of dirt classes changes since it allows to improve the classification results. Using the standard classification methods, it is possible to obtain satisfactory results, although the methods modeling the data, such as the Bayesian classifier using the Gaussian Mixture Model, show better performance.