Support Vector Machines for automated classification of plastic bottles

Many recycling activities adopt manual sorting for plastic recycling that relies on plant personnel who visually identify and pick plastic bottles as they travel along the conveyor belt. These bottles are then sorted into the respective containers. Manual sorting may not be a suitable option for recycling facilities of high throughput. It has also been noted that the high turnover among sorting line workers had caused difficulties in achieving consistency in the plastic separation process. As a result, an intelligent system for automated sorting is greatly needed to replace manual sorting system. The core components of machine vision for this intelligent sorting system is the image recognition and classification.[3]Therefore, in this work, an automated classification of plastic bottles based on the extraction of best feature vectors to represent the type of plastic bottles is performed using the morphological based approach. Morphological operations are used to describe the structure or form of an image. By using the two-dimensional description of plastic bottle silhouettes, edge detection of the object silhouette is performed followed by the erosion process. This procedure can be considered as two stages; a) a feature vector is extracted from the analysis of morphological operation and structure element used and b) a classification technique is applied to that input vector in order to provide a meaningful categorization of the data content. In this study, Support Vector Machines (SVM) was employed merely to classify the image of two groups of plastic bottles namely polyethylene-terephthalate (PET) and non-PET. Additionally, for detailed classification task, the pattern of decision boundary for classification of extracted feature vectors based on morphological approach is also illustrated. Furthermore, the optimal features for input to SVM classifier is identified. The initial results indicate that the performance of the SVM in terms of classification accuracy is more than 90%.