Recognition and classification of geometric shapes using neural networks

Spasojević, Sofija; Susic, Marko; Đurović, Željko

doi:10.1109/neurel.2012.6419966

Cited by 6 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Owing to their characteristics of learning, memory and generalization, neural networks are chosen as a suitable method for solving problems of recognition and classification of geometric shapes, image, etc. [1]. The recognition problem in a real industrial setting is significantly more challenging than character recognition in documents or natural scenes [7].…”

Section: Theoretical Foundamentals and Related Researchmentioning

confidence: 99%

See 1 more Smart Citation

Product Classification Using Neural Network at Industry Robotic Line

Halenár

Križanová

2019

Research Papers Faculty of Materials Science and Technology Slovak University of Technology

View full text Add to dashboard Cite

The article describes a possible way of implementing a neural network in recognizing the shape and position of the products in the production process. The neural network is designed as a multilayer perceptron (MLP), and the whole system is implemented in a form of attachment to robotic arm, where the primary task of neural network is to distinguish a position of product. The neural network is trained like a classifier and outputs are used to control the robot. The advantage of the solution is a high degree of reliability of product positioning under different lighting conditions.

show abstract

Section: Theoretical Foundamentals and Related Researchmentioning

confidence: 99%

“…The areas of recognition and classification of geometric shapes may be of interest for implementation of many robotic tasks, especially those related to gripping objects by a robotic arm or movement of a robot across a set of obstacles [1]. There are various methods devoted to this issue.…”

Section: Theoretical Foundamentals and Related Researchmentioning

confidence: 99%

Product Classification Using Neural Network at Industry Robotic Line

Halenár

Križanová

2019

Research Papers Faculty of Materials Science and Technology Slovak University of Technology

View full text Add to dashboard Cite

show abstract

“…Next the gradient magnitude and direction is computed by employing the same formula as in equations (4), (5), (6). The edge of the image is determined by refining the roof ridge of the gradient magnitude image.…”

Section: Canny Edge Detectionmentioning

confidence: 99%

“…Thus, the shape of the roof can be used as the main characteristic to recognize the traditional houses. Nonetheless, this recognition faces the same challenge as other building recognition issues, due to lighting conditions influenced by weather and time of day, complex background caused by the existence of trees and other objects that have similar shapes and scale changes [6].…”

Section: Introductionmentioning

confidence: 99%

Traditional house recognition

Sabri

İbrahim

Zulkifli

2015

2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE)

View full text Add to dashboard Cite

This research investigates the performance of edge and texture features, and Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers for traditional house recognition. Malaysia is well known for its wealthy segments of cultural heritage and one of it is the traditional Malay houses. Capturing images of houses from the natural scenes are affected by illumination changes, scale and rotation invariants that makes the recognition process very challenging. Feature and classifier selection plays an important role in this recognition process. Thus, two comparative studies have been conducted, that are, between edge and texture features and between ANN and SVM classifiers to determine which combination will produce better recognition performance. Experimental results show that edge features with ANN achieve good recognition result.

show abstract

“…A boa classificação da MLP também foi obtida em (Spasojevic et al, 2012), onde a rede foi usada para classificar cubos, piramedes e cilindros. As imagens eram segmentadas para limpar o fundo e, depois de feita a extração das bordas, eram classificadas pela rede neural.…”

Section: Redes Neuraisunclassified

Um sistema de reconhecimento de objetos incorporado a um robô humanoide aplicado na educação

Pinto¹

View full text Add to dashboard Cite

I ncreasingly there has been the introduction of new technologies in the classroom. With the help of public policies, computers connected to the internet has been used in the classes in the far reaches of our country. This has provided the knowledge reachs broader and unrestricted way to all children under development. In the last decade, besides computers, has been seen the presence in classrooms of Ipads, smart phones, owned by the students themselves and even electronic whiteboard in schools with higher purchasing power. Added to this, there is also the inclusion of robotic kits that has motivated much students in learning logical reasoning and programming, as they experience the concept: "learning through doing". The use of all these technologies aims to captivate the attention of students, encourage research and interactive learning, since the school, before exhibition, gives way to interactive teaching, that is, who has the most active student participation. In this direction, this Master's thesis brings an innovation in the sense that is being proposed a system that allows a robot humanoid is inserted into classrooms. It is a prototype that allows the robot to recognize planar geometric figures, which can be extended to other types of content. The goal is the integration of a computer vision system in a control a humanoid robot environment to make it able to recognize This has provided the knowledge gets broader and unrestricted way all children under development geometric figures, to be used as a teaching tool. This vision system is based on Visual Attention techniques and uses a neural network LEGION to target the salient objects image and a Multilayer (MLP) neural network, to perform the classification of these objects. Thanks to the vision system, the robot can distinguish independent of the actual environment in which overlapping figures is inserted. To evaluate the performance of the proposed system, some applications were developed that involved the participation of children interacting with the robot in the recognition of geometric figures. Although a larger number of experiments are needed, the results indicate that the proposed system is presented as an alternative tool, promising and interesting, and it was very well received by students and teachers. vii

show abstract

Recognition and classification of geometric shapes using neural networks

Cited by 6 publications

References 6 publications

Product Classification Using Neural Network at Industry Robotic Line

Product Classification Using Neural Network at Industry Robotic Line

Traditional house recognition

Um sistema de reconhecimento de objetos incorporado a um robô humanoide aplicado na educação

Contact Info

Product

Resources

About