Results 291 to 300 of about 1,732,484 (345)
Some of the next articles are maybe not open access.
Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101), 2002
We present a new approach for accurate detection of two-dimensional shapes. We first derive an optimal smoothing filter, which minimizes both the noise power and the mean squared error between the input and the filter output. This operator is found to be a derivative of the double exponential (DODE) function.
H. Moon, R. Chellappa, A. Rosenfeld
openaire +1 more source
We present a new approach for accurate detection of two-dimensional shapes. We first derive an optimal smoothing filter, which minimizes both the noise power and the mean squared error between the input and the filter output. This operator is found to be a derivative of the double exponential (DODE) function.
H. Moon, R. Chellappa, A. Rosenfeld
openaire +1 more source
SHAPE-BASED ADULT IMAGE DETECTION
International Journal of Image and Graphics, 2005This paper investigates adult images detection based on the shape features of skin regions. In order to accurately detect skin regions, we propose a skin detection method using multi-Bayes classifiers in the paper. Based on skin color detection results, shape features are extracted and fed into a boosted classifier to decide whether or not the skin ...
null Qing-Fang Zheng +3 more
openaire +1 more source
Detection of contrast-defined shape
Journal of the Optical Society of America A, 2001We assessed the accuracy of contrast-defined shape detection of stimuli of constant aspect ratio, namely, circular bandpass stimuli whose radii were sinusoidally varied about a mean radius. Performance for these contrast-defined shapes, which we show is determined by the global rather than the local attributes of the stimulus, is 2-8 times worse than ...
R F, Hess, R L, Achtman, Y Z, Wang
openaire +2 more sources
Shape-Based Volumetric Collision Detection
2000 IEEE Symposium on Volume Visualization (VV 2000), 2000In this paper, we describe a method to detect collisions between volumetric objects. A hierarchy of bounding spheres is computed from a volumetric object based on the distance transform. Multiple levels of bounding approximations to the volumetric object are automatically computed. The computation of bounding spheres is based on the shape of the object.
Nikhil Gagvani, Deborah Silver
openaire +1 more source
Optimal edge-based shape detection
IEEE Transactions on Image Processing, 2002We propose an approach to accurately detecting two-dimensional (2-D) shapes. The cross section of the shape boundary is modeled as a step function. We first derive a one-dimensional (1-D) optimal step edge operator, which minimizes both the noise power and the mean squared error between the input and the filter output.
Hankyu, Moon +2 more
openaire +2 more sources
IEEE Transactions on Knowledge and Data Engineering, 2016
Given a set of activity points (e.g., crime, disease locations), Ring-Shaped Hotspot Detection (RHD) finds ring-shaped areas where the concentration of activities inside is significantly higher than that outside. RHD is societally important for applications such as environmental criminology, epidemiology, and biology to investigate evasive patterns ...
Emre Eftelioglu +3 more
openaire +1 more source
Given a set of activity points (e.g., crime, disease locations), Ring-Shaped Hotspot Detection (RHD) finds ring-shaped areas where the concentration of activities inside is significantly higher than that outside. RHD is societally important for applications such as environmental criminology, epidemiology, and biology to investigate evasive patterns ...
Emre Eftelioglu +3 more
openaire +1 more source
Shape Detection Using Air-Drawing
2023 11th International Symposium on Digital Forensics and Security (ISDFS), 2023Computer vision is a branch of AI that enables computers and systems to extract and process meaningful information from visual inputs such as digital images and videos. Computer vision endows computers with the ability to see, observe, and understand the visual world, while AI endows them with the ability to think and reason. Computer vision has a wide
Ali, S.H., Aygun, H.
openaire +1 more source
Parallel Simulated Annealing for Shape Detection
Computer Vision and Image Understanding, 1995Abstract In this paper, we describe two parallel implementations of the simulated annealing method applied to the shape detection problem. The first is a massively parallel implementation on an SIMD mesh-connected architecture; the second uses an MIMD model of computation.
BONGIOVANNI, Giancarlo +2 more
openaire +2 more sources

