Search Results (7)

With the rapid advancement of deep learning technologies, computer vision has shown immense potential in retail automation. This paper presents a novel self-checkout system for retail based on an improved YOLOv10 network, aimed at enhancing checkout efficiency and reducing labor costs. We propose targeted optimizations for the YOLOv10 model, incorporating the detection head structure from YOLOv8, which significantly improves product recognition accuracy. Additionally, we develop a post-processing algorithm tailored for self-checkout scenarios, to further enhance the application of the system. Experimental results demonstrate that our system outperforms existing methods in both product recognition accuracy and checkout speed. This research not only provides a new technical solution for retail automation but offers valuable insights into optimizing deep learning models for real-world applications. Full article

With the continuous improvement of people’s health awareness and the continuous progress of scientific research, consumers have higher requirements for the quality of drinking. Compared with high-sugar-concentrated juice, consumers are more willing to accept healthy and original Not From Concentrated (NFC) juice and packaged drinking water. At the same time, drinking category detection can be used for vending machine self-checkout. However, the current drinking category systems rely on special equipment, which require professional operation, and also rely on signals that are not widely used, such as radar. This paper introduces a novel drinking category detection method based on wireless signals and artificial neural network (ANN). Unlike past work, our design relies on WiFi signals that are widely used in life. The intuition is that when the wireless signals propagate through the detected target, the signals arrive at the receiver through multiple paths and different drinking categories will result in distinct multipath propagation, which can be leveraged to detect the drinking category. We capture the WiFi signals of detected drinking using wireless devices; then, we calculate channel state information (CSI), perform noise removal and feature extraction, and apply ANN for drinking category detection. Results demonstrate that our design has high accuracy in detecting drinking category. Full article

Human–computer interactions (HCIs) use computer technology to manage the interfaces between users and computers. Object detection systems that use convolutional neural networks (CNNs) have been repeatedly improved. Computer vision is also widely applied to multiple specialties. However, self-checkouts operating with a faster region-based convolutional neural network (faster R-CNN) image detection system still feature overlapping and cannot distinguish between the color of objects, so detection is inhibited. This study uses a mask R-CNN with data augmentation (DA) and a discrete wavelet transform (DWT) in lieu of a faster R-CNN to prevent trivial details in images from hindering feature extraction and detection for deep learning (DL). The experiment results show that the proposed algorithm allows more accurate and efficient detection of overlapping and similarly colored objects than a faster R-CNN with ResNet 101, but allows excellent resolution and real-time processing for smart retail stores. Full article

Through human development and technological expansion, it has become apparent that the potential lies within each individual to have an essential part in the transcendence of society and the community. People less privileged than others may need more strength and determination to surpass their current resources to overcome normal and natural obstacles in order to simulate an environment where productivity and creativity exist. This paper aims to study an approach that will assist the elderly and people of determination in one of the most essential activities practiced by individuals: shopping. The study focuses on facilitating the acquirement of items from shelves and skipping the cashier line. The proposed system is a service robot supported by a robotic arm and a linear actuator as a lifting mechanism, controlled by a remote joystick to help the elderly or disabled people reach items on high shelves. The scanning system is based on barcode detection, using transfer learning. The network was designed using YOLOv2 layers connected to TinyYOLO as feature extraction layers. This network has proven to be the most practical, with 86.4% accuracy and real-time operation with 27 FPS in comparison to using the YOLOv2 layers with DarkNet or VGG19 as feature extraction layers. An anti-theft system is integrated into the robot to improve the reliability of the self-checkout feature. The system uses computer vision GMM and Kalman filter for item detection inside the cart, and the item is validated to be the one that has been scanned, using SURF for structural features, HSV for color, and load-sensors mounted to the base of the cart to measure the item’s weight. Full article

The traditional weighing and selling process of non-barcode items requires manual service, which not only consumes manpower and material resources but is also more prone to errors or omissions of data. This paper proposes an intelligent self-service vending system embedded with a single camera to detect multiple products in real-time performance without any labels, and the system realizes the integration of weighing, identification, and online settlement in the process of non-barcode items. The system includes a self-service vending device and a multi-device data management platform. The flexible configuration of the structure gives the system the possibility of identifying fruits from multiple angles. The height of the system can be adjusted to provide self-service for people of different heights; then, deep learning skill is applied implementing product detection, and real-time multi-object detection technology is utilized in the image-based checkout system. In addition, on the multi-device data management platform, the information docking between embedded devices, WeChat applets, Alipay, and the database platform can be implemented. We conducted experiments to verify the accuracy of the measurement. The experimental results demonstrate that the correlation coefficient $R^2$ between the measured value of the weight and the actual value is 0.99, and the accuracy of non-barcode item prediction is 93.73%. In Yangpu District, Shanghai, a comprehensive application scenario experiment was also conducted, proving that our system can effectively deal with the challenges of various sales situations. Full article

In recent years, the technology of artificial intelligence (AI) and robots is rapidly spreading to countries around the world. More and more scholars and industry experts have proposed AI deep learning models and methods to solve human life problems and improve work efficiency. Modern people’s lives are very busy, which led us to investigate whether the demand for Bento buffet cafeterias has gradually increased in Taiwan. However, when eating at a buffet in a cafeteria, people often encounter two problems. The first problem is that customers need to queue up to check out after they have selected and filled their dishes from the buffet. However, it always takes too much time waiting, especially at lunch or dinner time. The second problem is sometimes customers question the charges calculated by cafeteria staff, claiming they are too expensive at the checkout counter. Therefore, it is necessary to develop an AI-enabled checkout system. The AI-enabled self-checkout system will help the Bento buffet cafeterias reduce long lineups without the need to add additional workers. In this paper, we used computer vision and deep-learning technology to design and implement an AI-enabled checkout system for Bento buffet cafeterias. The prototype contains an angle steel shelf, a Kinect camera, a light source, and a desktop computer. Six baseline convolutional neural networks were applied for comparison on food recognition. In our experiments, there were 22 different food categories in a Bento buffet cafeteria employed. Experimental results show that the inception_v4 model can achieve the highest average validation accuracy of 99.11% on food recognition, but it requires the most training and recognition time. AlexNet model achieves a 94.5% accuracy and requires the least training time and recognition time. We propose a hierarchical approach with two stages to achieve good performance in both the recognition accuracy rate and the required training and recognition time. The approach is designed to perform the first step of identification and the second step of recognizing similar food images, respectively. Experimental results show that the proposed approach can achieve a 96.3% accuracy rate on our test dataset and required very little recognition time for input images. In addition, food volumes could be estimated using the depth images captured by the Kinect camera, and a framework of visual checkout system was successfully built. Full article

The physical features of fruit and vegetables make the task of vision-based classification of fruit and vegetables challenging. The classification of fruit and vegetables at a supermarket self-checkout poses even more challenges due to variable lighting conditions and human factors arising from customer interactions with the system along with the challenges associated with the colour, texture, shape, and size of a fruit or vegetable. Considering this complex application, we have proposed a progressive coarse to fine classification technique to classify fruit and vegetables at supermarket checkouts. The image and weight of fruit and vegetables have been obtained using a prototype designed to simulate the supermarket environment, including the lighting conditions. The weight information is used to change the coarse classification of 15 classes down to three, which are further used in AdaBoost-based Convolutional Neural Network (CNN) optimisation for fine classification. The training samples for each coarse class are weighted based on AdaBoost optimisation, which are updated on each iteration of a training phase. Multi-class likelihood distribution obtained by the fine classification stage is used to estimate a final classification with a softmax classifier. GoogleNet, MobileNet, and a custom CNN have been used for AdaBoost optimisation, with promising classification results. Full article