Analyzing images in frequency domain to estimate the quality of wood particles in OSB production

Abstract

Abstract-The analysis of the quality of particulate materials is of great importance for a variety of research and industrial applications. Most image-based methods rely on the segmentation of the image to measure the particles and aggregate their characteristics. However, the segmentation of particulate materials can be severely affected when the setup is not controlled. For instance, when there are device errors, changes in the light conditions, or when the camera gets dirty because of the dust or a similar substance. All of these circumstances are common in industrial setups, like the one studied in this paper. This work presents a framework for quality estimation based on image processing algorithms that avoids segmentation. The considered application scenario is the online quality control of the production of Oriented Strand Boards (OSB), a type of wood panel frequently used in construction and manufacturing industries. The proposed method quantizes frequency domain into a histogram using a non-parametric method, which is later exploited using computational intelligence to classify the quality of superimposed wood particles deposed on a conveyor belt. The method has been tested using synthetic and real images with different noise conditions. The results illustrate the robustness of the approach and its capability to detect significant quality changes in the wood particles.

Computational intelligence for industrial and environmental applications

“…Moreover, Wireless Sensor Networks (WSNs) are being increasingly used for industrial monitoring due to their low cost, ease of installation, adaptivity, and selforganization [6], [25]. In industrial applications, CI techniques can be used to map the features extracted from the images or from the sensors to the observed quantities [20], [21], [23], [24], and they can be used as a general approach to monitor the quality of the industrial production process, by learning the relationship between the features of the raw materials and the quality of the obtained product [26]- [31], or to detect faults in the machinery by learning from the normal operating parameters [5], [6], [32]- [34].…”

“…Both feature extraction and selection steps have the purpose of reducing the dimensionality of the original data to limit the complexity of the problem while retaining its discriminative characteristics, allowing the use of simpler classifiers with a lower computational complexity and less prone to overtraining effects [59]. Examples of features extracted in industrial and environmental applications can be the anomalies in the frequency ranges of a signal to predict the quality of the production process [11], [26], the gray-level variations of the image used for estimating the granularity of a surface [60], and the shape of the moving area in a frame sequence to identify smoke [35].…”

“…CI techniques have been extensively applied to classification problems in industrial and environmental applications. Relevant examples include quality prediction in diverse production processes using neural networks [26], [27], evolutionary fuzzy systems [84] or SVMs [31], or fault detection using neuro-fuzzy systems [33], or SVMs [34]. Good examples of environmental applications include the use of neural networks to detect pollution problems [9], or natural disasters [35], [44].…”

Prediksi Kualitas Hasil Hutan Lahan Basah Menggunakan Backpropagation

“…Selama ini penentuan kualitas kayu dilakukan oleh manusia yang sudah telatih dan biasanya disebut grader. Grader mendeteksi kualitas kayu dengan cara memeriksa secara visual [3]. Akibat buruk dari proses ini diantaranya deteksi hanya bisa terlihat pada kayu yang memiliki perbedaan yang signifikan dari standart kayu yang bermutu, bersifat subjektif apalagi jika kayu dalam jumlah banyak maka bisa terjadi kebosanan pada grader sehingga menghasilkan deteksi yang akurasinya tidak standart.…”