Abstract
Content Based Image Retrieval (CBIR) is an important field of research targeting different applications. The one presented in this work results from an identified need for a wine anti-counterfeiting scheme based on photos of cork stoppers already proposed in previous work. A photo of each cork stopper is used to register a wine bottle during the bottling process. To verify the genuineness of the product a user captures a photo of the stopper; that photo is then compared with the entirety of the database and all the relevant information is retrieved to the user. This approach can be a very slow process, becoming more time consuming with each increase of the database. Aiming to solve this problem, a CBIR system for wine anti-counterfeiting purposes based on cork stopper photos is presented. The feature extraction is achieved using Oriented FAST and Rotated BRIEF (ORB), selecting the "best" keypoints (according to the Harris corner measure) per region. The regions are delimited by concentric circumferences calculated using the radius of the identified cork. The number of regions (N-R), along with the number of selected keypoints (N-p) per region, define the number of ORB descriptors needed for indexing the image in the database. To measure the similarity between the query image and the database a score is calculated based on N-R and N-P Finally, the best N images according to the calculated score are retrieved. To evaluate the proposed approach 2 datasets (natural cork and agglomerate cork dataset) were created, totaling 1500 photos, and 4 different smartphone rear cameras were used. The recall results range from 75.0% to 99.5% in the natural dataset and from 86.0% to 99.0% in the agglomerate dataset. The average time for the retrieval process is about 9.74ms in a database populated with 100 photos. Critical analysis on the recall rate and its time tradeoff is also discussed. The results show that the proposed CBIR is adequate for its application - wine anti- counterfeiting.

Abstract

Abstract

Abstract

Abstract
This paper describes the development of SMORA (Servo Motor Optimised for Robotic Applications), which consists of custom hardware and firmware that includes a microcontroller and a series of sensors, allowing for the motor current, temperature and voltage to be measured in real-time as well as precise position feedback thanks to the integrated hall-effect magnetic position encoder. It also incorporates an accelerometer and a gyroscope to measure the servo body relative position and rotation. © 2018 by World Scientific Publishing Co. Pte. Ltd.

Abstract
Some industries have critical areas (dangerous or hazardous) where the presence of a human must be reduced or avoided. In some cases, there are areas where humans should be replaced by robots. The present work uses a robot with differential drive to scan an environment with known and unknown obstacles, defined in 3D simulation. It is important that the robot be able to make the right decisions about its way without the need of an operator. A solution to this challenge will be presented in this paper. The control application and its communication module with a simulator or a real robot are proposed. The robot can perform the scan, passing through all the waypoints arranged in a grid. The results are presented, showcasing the robot’s capacity to perform a viable trajectory without human intervention. © Springer International Publishing AG 2018.