scholarly journals A Novel Framework for Extracting Visual Feature-Based Keyword Relationships from an Image Database

2012 ◽  
Vol E95.A (5) ◽  
pp. 927-937
Author(s):  
Marie KATSURAI ◽  
Takahiro OGAWA ◽  
Miki HASEYAMA
Keyword(s):  
Image Database ◽  
Visual Feature ◽  
Feature Based

scholarly journals Configuration and Registration of Multi-Camera Spectral Image Database of Icon Paintings

Computation ◽  
2019 ◽  
Vol 7 (3) ◽  
pp. 47
Author(s):  
Arash Mirhashemi
Keyword(s):  
Dynamic Range ◽  
Specular Reflection ◽  
Signal To Noise Ratio ◽  
Simulated Data ◽  
Image Database ◽  
High Dynamic Range ◽  
Registration Method ◽  
Spatial Registration ◽  
Feature Based ◽  
The Cost

At the cost of added complexity and time, hyperspectral imaging provides a more accurate measure of the scene’s irradiance compared to an RGB camera. Several camera designs with more than three channels have been proposed to improve the accuracy. The accuracy is often evaluated based on the estimation quality of the spectral data. Currently, such evaluations are carried out with either simulated data or color charts to relax the spatial registration requirement between the images. To overcome this limitation, this article presents an accurately registered image database of six icon paintings captured with five cameras with different number of channels, ranging from three (RGB) to more than a hundred (hyperspectral camera). Icons are challenging topics because they have complex surfaces that reflect light specularly with a high dynamic range. Two contributions are proposed to tackle this challenge. First, an imaging configuration is carefully arranged to control the specular reflection, confine the dynamic range, and provide a consistent signal-to-noise ratio for all the camera channels. Second, a multi-camera, feature-based registration method is proposed with an iterative outlier removal phase that improves the convergence and the accuracy of the process. The method was tested against three other approaches with different features or registration models.

An Efficient Algorithm for Improved Shape Context Feature's Cost Matrix Computation

2012 ◽  
Vol 532-533 ◽  
pp. 1631-1635
Author(s):  
Shan Shan Li ◽  
Ying Hai Zhao ◽  
Jiang An Wang
Keyword(s):  
Efficient Method ◽  
Fourier Transformation ◽  
Time Complexity ◽  
Visual Feature ◽  
Shape Context ◽  
Rotation Invariant ◽  
Matrix Computation ◽  
Cost Matrix ◽  
Feature Based ◽  
The Cost

Shape context is not rotation invariant as a local visual feature. To solve this problem, 2-D and 1-D Fourier Transformation has been performed on the feature. Based on the property of Fourier Transformation, a fast and efficient method is presented in the cost matrix computation of these improved shape context feature. The analysis shows the time complexity is much lower and the experiments show effective and efficiency of this new algorithm.

scholarly journals EMAN: The Human Visual Feature Based No-Reference Subjective Quality Metric

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 46152-46164
Author(s):  
Pallab Kanti Podder ◽  
Manoranjan Paul ◽  
Manzur Murshed
Keyword(s):  
Subjective Quality ◽  
Visual Feature ◽  
Quality Metric ◽  
Feature Based

scholarly journals A Visual Object Tracking Algorithm Based on Dynamics Pattern and Convolutional Feature

2019 ◽  
Vol 37 (6) ◽  
pp. 1310-1319
Author(s):  
Boyan Zhang ◽  
Yong Zhong ◽  
Zhendong Li
Keyword(s):  
Short Term Memory ◽  
Motion Blur ◽  
Feature Representation ◽  
Visual Object ◽  
Visual Feature ◽  
Illumination Variation ◽  
Time Step ◽  
Bounding Box ◽  
Feature Based ◽  
Lstm Network

Deep visual feature-based method has demonstrated impressive performance in visual tracking attributing to its powerful capability of visual feature representation. However, in some complex environments such as dramatic change of appearance, illumination variation and rotation, the extracted deep visual feature is insufficient for accurately characterizing the target. To solve this problem, we present an integrated tracking framework which combines a Long Short-Term Memory (LSTM) network and a Convolutional Neural Network (CNN). Firstly, the LSTM extracted dynamics feature of target on time sequence, resulting the state of target at present time step. With that state, the accurate preprocessed bounding box was obtained. Then, deep convolutional feature of the target was extracted using a CNN, based on the processed bounding box. Finally, the position of the target was determined based on the score of the feature. During tracking stage, in order to improve the adaptation of the network, the parameters of the network were updated using samples of the target captured while successful tracking. The experiment shows that the proposed method achieves outstanding tracking performance and robustness in cases of partial occlusion, out-of-view, motion blur and fast motion.

Study of Face Feature Extraction and Recognition Techniques Based on Wavelet Analysis

2014 ◽  
Vol 1030-1032 ◽  
pp. 1810-1813
Author(s):  
Xin Wang ◽  
He Pan
Keyword(s):  
Face Recognition ◽  
Wavelet Decomposition ◽  
Feature Vector ◽  
Recognition Performance ◽  
Image Database ◽  
Face Image ◽  
Support Vector ◽  
Svm Model ◽  
Feature Based ◽  
Vector Dimension

Face recognition is a research hotspot of pattern recognition and artificial intelligence. This paper presents a method of extract face feature based on Wavelet. First, reduce vector dimension by wavelet decomposition of the image, second, train the multi class support vector machine (SVM) model by face feature vector extracted and make face recognition finally. The experiments on ORL face image database of the algorithm shows the superiority of the proposed algorithm in terms of recognition performance.

Sign in / Sign up

Export Citation Format

Share Document