In this paper a simple and accurate method is proposed to recognize Arabic (indian) numerals using Fourier descriptors as the main classifier feature set, and to improve the recognition accuracy a simple structure bas...
详细信息
ISBN:
(纸本)9781601321916
In this paper a simple and accurate method is proposed to recognize Arabic (indian) numerals using Fourier descriptors as the main classifier feature set, and to improve the recognition accuracy a simple structure based classifier is add as a supplementary classifier. The recognition system was tested on 450 samples collected from 5 students and the test results indicate that the recognition ratio is %89.6 when only 5 Fourier descriptors are used as discriminating features set, and the ratio is raised to %98 when 4 Fourier descriptors are used in addition to the simple structure based classifier.
Limited depth of focus of optical lenses results in blurred representation of some of the relevant objects in any image. Multi focus image fusion is used to solve this problem. Both curvelet based and wavelet based im...
详细信息
ISBN:
(纸本)9781601321916
Limited depth of focus of optical lenses results in blurred representation of some of the relevant objects in any image. Multi focus image fusion is used to solve this problem. Both curvelet based and wavelet based image fusion methods are implemented and compared in this paper. Comparison is done based on various parameters called "fusion performance index". Wavelet and curvelet coefficients are calculated and represented in the form of images. Experiments showed that curvelet decomposition based fusion increases the quality of obtained fused images.
The proceedings contain 181 papers. The topics discussed include: modifications in normalized cross correlation expression for template matching applications;a generic strategy for designing an efficient and robust 11...
ISBN:
(纸本)9781601321916
The proceedings contain 181 papers. The topics discussed include: modifications in normalized cross correlation expression for template matching applications;a generic strategy for designing an efficient and robust 11mm-based action recognizer;partial discharge pattern recognition using Hilbert-Huang transform in acoustic signal analysis;a fuzzy condition sensitive hierarchical algorithm for template matching in emotionally expressive facial images;a generic approach for recognition and structural modelling of drawers' sketching gestures;handwritten Arabic (indian) numerals recognition using Fourier descriptor and structure base classifier;recognition of soccer players after occlusions using temporal color signatures;biometric template protection for dynamic time warping-based user authentication;rating whole-body suspiciousness factors in automated surveillance of a public area;and categorizing global and local features of on-line signature verification using DTW and fuzzy logic.
The proceedings contain 181 papers. The topics discussed include: modifications in normalized cross correlation expression for template matching applications;a generic strategy for designing an efficient and robust 11...
ISBN:
(纸本)9781601321916
The proceedings contain 181 papers. The topics discussed include: modifications in normalized cross correlation expression for template matching applications;a generic strategy for designing an efficient and robust 11mm-based action recognizer;partial discharge pattern recognition using Hilbert-Huang transform in acoustic signal analysis;a fuzzy condition sensitive hierarchical algorithm for template matching in emotionally expressive facial images;a generic approach for recognition and structural modelling of drawers' sketching gestures;handwritten Arabic (indian) numerals recognition using Fourier descriptor and structure base classifier;recognition of soccer players after occlusions using temporal color signatures;biometric template protection for dynamic time warping-based user authentication;rating whole-body suspiciousness factors in automated surveillance of a public area;and categorizing global and local features of on-line signature verification using DTW and fuzzy logic.
An extra-classical receptive field (ECRF) based mid-level model of visual processing which we refer to as the neuro-visually inspired model of figure-ground segregation (NFGS) is proposed in this work. It is inspired ...
详细信息
A considerable amount of research is undergoing in the field of computervision is related to object tracking. However, object tracking, in general, is a challenging problem. The challenges in objects tracking arise d...
详细信息
A nonlinear weighted averaging filter called bilateral filter depends mainly on two parameters. The spatial distance indicates the size, and the intensity distance indicates the contrast of the features to be preserve...
详细信息
A nonlinear weighted averaging filter called bilateral filter depends mainly on two parameters. The spatial distance indicates the size, and the intensity distance indicates the contrast of the features to be preserved, with respect to a center pixel. Its simplicity in behavior and implementation makes it easily adaptable to many applications with minor variations. This paper brings out one such variation by using different scales of the image for computing the parametric functions of the filter. Experimental results demonstrate the efficacy of the proposed technique.
The proceedings contain 70 papers. The topics discussed include: the human action image and its application to motion recognition;human action recognition in video by 'meaningful' poses;human action recognitio...
ISBN:
(纸本)9781450300605
The proceedings contain 70 papers. The topics discussed include: the human action image and its application to motion recognition;human action recognition in video by 'meaningful' poses;human action recognition using a dynamic Bayesian action network with 2D part models;unsupervised discovery of activity correlations using latent topic models;optimal shot detection and recognition using Shiryaev-Roberts statistics;the human action image and its application to motion recognition;a novel technique for sketch to photo synthesis;implicit surface octrees for ray tracing point models;a multi-view extension of the ICP algorithm;a convex multi-view stereo formulation with robustness to occlusions and time-varying clutter;realtime motion segmentation based multibody visual slam;image based PTM synthesis for realistic rendering of low resolution 3D models;and reground-background separation on GPU using order based approaches.
We present a novel dance posture based annotation model by combining features using Multiple Kernel Learning (MKL). We have proposed a novel feature representation which represents the local texture properties of the ...
详细信息
We present a novel dance posture based annotation model by combining features using Multiple Kernel Learning (MKL). We have proposed a novel feature representation which represents the local texture properties of the image. The annotation model is defined in the direct a cyclic graph structure using the binary MKL algorithm. The bag-of-words model is applied for image representation. The experiments have been performed on the image collection belonging to two indian classical dances (Bharatnatyam and Odissi). The annotation model has been tested using SIFT and the proposed feature individually and by optimally combining both the features. The experiments have shown promising results.
In this paper, we present algorithms for resizing and transcoding of images in the transform domain. The approach is based on wavelet filtering (analysis/synthesis) along with downsampling/upsampling operation in the ...
详细信息
In this paper, we present algorithms for resizing and transcoding of images in the transform domain. The approach is based on wavelet filtering (analysis/synthesis) along with downsampling/upsampling operation in the block DCT space. We use linear filtering in the block DCT domain to perform convolution. To obtain results equivalent to linear convolution, filtering is performed on the three adjacent blocks. To reduce the complexity, we perform sampling rate change and filtering operations in a single combined step. The proposed approach achieves the best performance in terms of quality compared to the DCT domain technique.
暂无评论