Jari Käyhkö

Framework for developing image-based dirt particle classifiers for dry pulp sheets

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.

Automated counting and characterization of dirt particles in pulp

Dirt count and dirt particle characterization have an important role in the quality control of the pulp and paper production. The precision of the existing image analysis systems is mostly limited by methods for only extracting the dirt particles from the images of pulp samples with non-uniform backgrounds. The goal of this study was to develop a more advanced automated method for the dirt counting and dirt particle classification. For the segmentation of dirt particles, the use of the developed Niblack thresholding method and the Kittler thresholding method was proposed. The methods and different image features for classification were experimentally studied by using a set of pulp sheets. Expert ground truth concerning the dirt count and dirt particle classes was collected to evaluate the performance of the methods. The evaluation results showed the potential of the selected methods for the purpose.

Estimation of Bubble Size Distribution Based on Power Spectrum

A bubble size distribution gives relevant insight into mixing processes where gas-liquid phases are present. The distribution estimation is challenging since accurate bubble detection from images captured from industrial processes is a complicated task due to varying lighting conditions which change the appearance of bubbles considerably. In this paper, we propose a new method for estimating the bubble size distribution based on the image power spectrum. The method works by calculating the power spectrum for a number of frequency bins and learning the linear relationship between the power spectrum and the bubble size distribution. Since the detection of individual bubbles is not needed, the proposed method is remarkably faster than the traditional approaches. The method was compared to a geometry-based bubble detection method with both synthetic and industrial image data. The proposed method outperformed the bubble detection based approach especially in the cases where bubbles were small and the number of bubbles high.

High-speed infrared imaging of flash mixing and streetview omnilens thermography

In-line mixing technologies used in paper and pulp manufacturing have been studied long and broadly by XAMK Fiberlaboratory in Savonlinna, Finland. Especially, wider introduction and diversification of technologies related to mixing of paper chemicals have created a need to determined research of the in-line mixing technologies. In Finnish research project FLASH, a ground was based for researching and developing the fast in-line mixing techniques together with companies operating in pulp and paper industry segment. Application potential, basic knowledge, measurement technologies, experiment techniques, and research facilities were surveyed for utilizing them later in practical processes. One of the tested measurement technologies was high-speed infrared imaging. The high-speed infrared imaging tests were carried out together by VTT, XAMK and the companies in Fiberlaboratory research facility in 2013-2015. The Fiberlaboratory research facility includes medium-consistency pulp (MC) chemical mixing equipment, which is almost equal to real life paper mill chemical mixing environment. The infrared imaging was done with the help of IR transmitting sapphire window attached to suitable point in mixing tube system. Temperature differences of main flow and mixing flow enabled analyzing and calculating mixing indexes for different mixing drive parameters successfully. VTT has also designed a new kind of infrared omnilens for example for panoramic streetview thermography. The VTT omnilens technology enables the streetview thermography with a single infrared camera. Horizontal 360 degree infrared image is achieved by novel lens solution and also vertical image portion is possible. The streetview thermography is useful when finding thermal leaks from buildings in wide area or it can be used to find thermal leaks inside buildings with wheeled small vehicles. Also, utilizing the omnilens in drones to prevent them to collide each other or other drone applications are possible in the future.