Topic
Edge detection
About: Edge detection is a research topic. Over the lifetime, 25525 publications have been published within this topic receiving 486443 citations. The topic is also known as: edgel.
Papers published on a yearly basis
Papers
More filters
••
28 Mar 1993TL;DR: A two-stage neural network is proposed for segmentation of range images with emphasis on a neural network (NN) based system that integrates edge and surface information to generate robust surface maps in the range data.
Abstract: A two-stage neural network is proposed for segmentation of range images. Emphasis is placed on a neural network (NN) based system that integrates edge and surface information to generate robust surface maps in the range data. The proposed architecture has two stages. The first stage extracts the surface information through self-learning least-squares surface fitting along a set of nonorthogonal basis functions. Daugman's projection NN stage locally computes the surface normals in the image. In the second stage, the surface and edge information complete with each other to perform region growing. The edge information is obtained using a set of Zernike moment-based operators. Kohonen's self-organizing NN is used to implement the competitive region-growing. Experimental results with real images demonstrate the effectiveness of the proposed NN architecture. >
6 citations
••
TL;DR: In this article, a multiple model image estimation technique with its required steps of model design, edge detection, filtering, and model tuning is presented and compared with a moving window continuously adaptive technique.
6 citations
••
24 Sep 1990TL;DR: The authors present the dedicated hardware features of an image processing system based on a modular architecture where all modules are independent of each other and the algorithm used to generate the output data is programmable and uses separate dedicated image processing modules.
Abstract: The authors present the dedicated hardware features of an image processing system. The system is based on a modular architecture where all modules are independent of each other. A convolver implementation is given as an example of this approach. The hardware oriented image processing system is designed around a graphics processor. The system consists of a number of processing modules to enhance the performance of typical image processing applications in real-time and uses video RAM and dual-port RAM to enhance the system speed. The proposed design is a real-time image processing system. The novel feature of this architecture is that the algorithm used to generate the output data is programmable and uses separate dedicated image processing modules. These are combined to form a dedicated processing element (PE) which performs a range of tasks, eg, averaging, filtering, edge detection, scaling, point enhancement and thresholding. >
6 citations
•
10 Dec 2010
TL;DR: This study investigated the main role of horizontal cells for the retina's network toward building a retina-like robot's vision technique and Experimental results show the validity of the proposed algorithm to provide accurate edges in real-time with less noise.
Abstract: Edge detection plays a significant role in assessing the capability level of the robot's vision. Accurate edge detection leads to better vision. The work in this paper was conducted by the inspiration of the biological concept of mammalian vision. That is, the retina enriches the edges in the view before passing it to the visual cortex in the brain for further processes. Although many works have been done to investigate surrounding this issue, these works are still limited in compare with that exists in retina. In this study, we investigated the main role of horizontal cells for the retina's network toward building a retina-like robot's vision technique. Experimental results show the validity of the proposed algorithm to provide accurate edges in real-time with less noise.
6 citations
••
TL;DR: A cost criterion to select the operator of the best approximating function class and the most appropriate template size so that the difference operator can be locally adapted to the digitized function is introduced.
6 citations