China 
Africa 
Explore chapters and articles related to this topic
The RIMcomb research project: Towards the application of building information modeling in Railway Equipment Engineering
Published in Jan Karlshøj, Raimar Scherer, eWork and eBusiness in Architecture, Engineering and Construction, 2018
S. Vilgertshofer, D. Stoitchkov, S. Esser, A. Borrmann, S. Muhič, T. Winkelbauer
This technique compares objects with their contours. A contour lies on the border between the black and white spaces. A contour tree contains the hierarchy between the contours or how they relate to one another. Contours can be compared with the help of image moments. An image moment is a characteristic of a given contour calculated by summing over the pixels of that contour. The Hu invariant moments (Hu, 1962) were used in our work to compare contours. The Hu moments are combinations of different normalized central moments and are scale, rotation and translation invariant. However, this method works only if the symbol is not connected to other lines or objects in the image, because then the contour around the symbol can’t be defined properly.
Model-based Visual Servoing of a 7 DOF Manipulator
Published in Laxmidhar Behera, Swagat Kumar, Prem Kumar Patchaikani, Ranjith Ravindranathan Nair, Samrat Dutta, Intelligent Control of Robotic Systems, 2020
Laxmidhar Behera, Swagat Kumar, Prem Kumar Patchaikani, Ranjith Ravindranathan Nair, Samrat Dutta
One of the basic problems in the design of an imagery pattern recognition system relates to the selection of a set of appropriate numerical attributes of features to be extracted from the object of interest for the purpose of classification. The recognition of objects from imagery may be achieved with many methods by identifying an unknown object as a member of a set of known objects. Efficient object recognition techniques abstracting characterizations uniquely from objects for representation and comparison are crucially important for a given pattern recognition system. One of the popular techniques to characterise an object in the image space is to use image moments.
An efficient stacked ensemble model for the detection of COVID-19 and skin cancer using fused feature of transfer learning and handcrafted methods
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
Geometric moments: In computer vision, object recognition, pattern recognition and related fields, the intensity values of the image pixels are represented by the specific weighted average (moment), which is usually chosen to have some appealing interpretation. Image moments are helpful in describing objects in image data (Chadha et al. 2012). Hu (1962) develops a geometric moment invariant feature extraction method that focuses on shape detection tasks from image data. The method extracts features via the Rotation Scale Translation (RST) invariant. This means that the features obtained through this method are not altered for the variation of translation, rotation and scaling. To represent the image by using geometric moments, Hu derives seven invariants. They are invariant for similarity, translation, rotation and reflection. The formulas from Equations (1) to (7) are the seven invariants:
Comparative study of feature extraction and classification methods for recognition of characters taken from vehicle registration plates
Published in The Imaging Science Journal, 2020
Ladislav Karrach, Elena Pivarčiová
The image moments describe an image in terms of its spatial (or pixel) distribution. The image can be reconstructed from the set of its moments [9]. An example of image moments are geometric (normalized central) moments, Hu moments or orthogonal moments (e.g. Zernike, Legendre, Chebyshev moments) [10–12].