• International Journal of Contents
• /
• v.10 no.4
• /
• pp.1-10
• /
• 2014

In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area from the image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.

• International Journal of Contents
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2011

In this paper, we propose a method to segment the bottle label in images taken by mobile phones using multi-gradient approaches. In order to segment the label region of interest-object, the saliency map method and Hough Transformation method are first applied to the original images to obtain the candidate region. The saliency map is used to detect the most salient area based on three kinds of features (color, orientation and illumination features). The Hough Transformation is a technique to isolated features of a particular shape within an image. Therefore, we utilize it to find the left and right border of the bottle. Next, we segment the label based on the gradient information obtained from the structure tensor method and edge method. The experimental results have shown that the proposed method is able to accurately segment the labels as the first step of product label recognition system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.365-368
• /
• 2021

In this study, a plastic bottle recycling bin system that utilizes an infrared sensor was implemented. The proposed system consists of a recognition unit, a control unit, an alarm unit, and a driving unit. The recognition unit detects the plastic bottle, measures the distance between the plastic bottle and the infrared sensor, extracts the value of the bottle, compares the extracted value with a standard range, and then transmits the control value to the control unit if the extracted value of the bottle is outside the standard range. In this case, the result of the presence or absence of a brand label or bottle cap is transmitted to the controller. The control unit opens the entrance of the recycling bin or alerts the alarm unit according to the result value transmitted from the sensor unit. In order to implement the proposed system, the recognition unit was implemented with an infrared sensor, and the control unit was made with an Arduino IDE controller, based on the C programming language. Additionally, the recognition unit and the control unit are able to communicate using analog signals. The proposed system accurately judges the presence or absence of a brand label and bottle cap of plastic bottles according to a predetermined algorithm. It then blocks the entrance of the recycling bin when a brand label or bottle cap is still attached. As the amount of waste discharged per person is relatively high and the majority of such waste is incinerated rather than recycled, the system proposed in this study is expected to increase the recycling rate of plastic bottles.

• The monthly packaging world
• /
• s.335
• /
• pp.82-89
• /
• 2021

• The monthly packaging world
• /
• s.372
• /
• pp.86-90
• /
• 2024

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.11
• /
• pp.2155-2161
• /
• 2016

Since Korea is highly dependent on energy imports, it has been making efforts to save energy resources by enacting laws to promote resource saving and recycling. Recently, as a part of recycling of empty bottles, a bottle unattended collecting machine has been installed in the big shopping mall in the metropolitan area. However, there is no commercialization of the unattended collecting machine in Korea and the smart device application for providing information on empty bottle recycling is not yet provided. In this paper, we have designed and constructed a bottle recycling information management system to promote resource recycling. The manager has built a homepage that can manage the information of the empty bottle and the a bottle unattended collecting machine. Also, many people with smart devices can easily access bottle recycling information by using camera and barcode search and label search.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2005

Purpose: The morbidity of pesticides are largely related with accidental ingestion in human. The four principal ideals of clarity, completeness, conformity and consistency of label are important to make a correct usage and prevent unnecessary health risk. The aim of this study is to evaluate the appropriateness of pesticides labelling practice in Korea. Methods: The photographic label images of pesticide products were gathered through visiting thirteen manufacturers that produce pesticide products in Korea. We scored labelling practice by guidelines of Food and Agriculture Organization of the United Nations in 1995. Results: From August 2005 to November 2005, we gathered 1,296 label images of pesticide and $58.3{\%}$ (755/1,296) of images were scored by check lists for reviewing label content. The average score of four check list categories was $71.9{\pm}2.2$. Each categorical score were $91.7{\pm}0.9$ for the information appearing on the label, $31.3{\pm}0.0$ for safety precaution, $77.7{\pm}2.0$ for instructions for use, $87.0{\pm}8.7$ for general configurations. In safety precaution, the sentence of keeping locked up the product and two mandatory safety pictograms were missed in all label images. In general configurations category, there was score difference in product package types between bottle and bag container ($85.1{\pm}9.0$ vs. $90.3{\pm}7.2$, p < 0.01). Conclusion: Although there was no comparable previous data, the score of safety precaution was lowest than other categories because the two mandatory safety pictograms and locked up warning sentence were missed. In general configurations, the colour contrast was more inappropriate in the labels on bottle than bag container.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.226-231
• /
• 2013

In The matching algorithm for automatic packaging of drugs is essential to determine whether the canister can exactly refill the suitable medicine. In this paper, we propose a hierarchical neural network with the upper and lower layers which can perform real-time processing and classification of many types of medicine bottles to prevent accidental medicine disaster. A few number of low-dimensional feature vector are extracted from the label images presenting medicine-bottle information. By using the extracted feature vectors, the lower layer of MLP(Multi-layer Perceptron) neural networks is learned. Then, the output of the learned middle layer of the MLP is used as the input to the upper layer of the MLP learning. The proposed hierarchical neural network shows good classification performance and real- time operation in the test of up to 30 degrees rotated to the left and right images of 100 different medicine bottles.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.1
• /
• pp.77-85
• /
• 2014

Medicine-bottle classification algorithm to avoid medicine accidents must be robust to a geometric change such as rotation, size variation, location movement of the medicine bottles. In this paper, we propose an algorithm to classify the medicine bottles exactly in real-time by using SIFT(Scale Invariant Feature Transform) which is robust to the geometric change. In first, we classify medicine bottles by size using minimum boundary rectangle(MBR) of medicine bottles as a striking feature in order to classify the medicine bottles. We extract label region in the MBR and the region of interest(ROI) considering rotation. Then, we classify medicine bottles using SIFT for the extracted ROI. We also simplify the number of octave of SIFT in order to improve a process speed of SIFT. We confirm to classify all the medicine bottles exactly as a result of performance evaluation of the proposed algorithm about images of 250 medicine bottles. We also confirm to improve the process time more than twice the processing time by simplifying the number of octave of SIFT.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.27 no.2
• /
• pp.63-70
• /
• 2021

As the government strengthens its policy of separating and discharging packaging materials, consumers are increasingly dissatisfied. In order to increase consumer participation in separate discharge policy of packaging materials, it is necessary to increase the willingness to participate by reducing potential consumer problems such as removal of packaging labels. This study conducted a survey of 300 consumers aged 14 and over who recycle and discharge directly from their homes. Ninety-nine percent of consumers said PET bottles are released separately. However, only 65% of consumers removed labels (attachment labels, shrink labels) and other materials (caps, vinyl coatings, tapes, handles, bases, etc.) during separate discharge process. Nearly 52% of consumers cited 'difficulty of separation' as the main reason for not removing labels and other materials. One-way ANOVA analysis showed that 'strong adhesion', 'removal initiation problem' and 'material strength' had high mean regardless of age, which are major factors impedes label removal. Using shrink labels with perforated lines rather than adhesive labels would be more beneficial to encouraging participation in separate discharge. However, if the shrink labels do not have perforated lines or are difficult to remove, adhesive labels are often easier to remove than shrink labels because of the strong cohesiveness of shrink labels. As a result, how easy it is for consumers to remove the label is more important than technological differences. In order to increase consumer participation in packaging material and label separations, improvements in structural design are needed along with the selection of materials that are easy to separate. This study is meaningful in examining consumer perceptions, deriving problems and suggesting directions for policy improvement.