scholarly journals DETECTING AND DISCARDING OF SHADOWS IN IMAGE USING GEOMETRIC CONTOURS AND REGION BASED SEGMENTATION USING THRESHOLDING APPROACH

2015 ◽  
Vol 3 (2) ◽  
pp. 13-19
Author(s):  
Shanthi S ◽  
Vinothini K. R ◽  
Manikandan
Keyword(s):  
Image Matching ◽  
Feature Vector ◽  
Active Contours ◽  
Feature Representation ◽  
Shadow Detection ◽  
Image Feature ◽  
Traditional Model ◽  
Image Feature Extraction ◽  
Segmentation Methods ◽  
Geometric Active Contours

Shadow detection and removal is an important task when dealing with color outdoor images. Shadows are generated by a local and relative absence of light. Most shadow detection and segmentation methods are based on image analysis. However, some factors will affect the detection result due to the complexity of the circumstances.In this paper, a new algorithm for shadow detection and isolation of buildings in high-resolution panchromatic satellite imagery is proposed. This algorithm is based on tailoring the traditional model of the geometric active contours such that the new model of the contours is systematically biased toward segmenting the shadow and the dark regions in the image. Feature extraction a type of dimensionality reduction that efficiently represents interesting parts of an image as a compact feature vector. This approach is useful when image sizes are large and a reduced feature representation is required to quickly complete tasks such as image matching and retrieval.

scholarly journals ROBUST MULTIMODAL IMAGE MATCHING BASED ON MAIN STRUCTURE FEATURE REPRESENTATION

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 583-589
Author(s):  
Y. Fu ◽  
Y. Ye ◽  
G. Liu ◽  
B. Zhang ◽  
R. Zhang
Keyword(s):  
Image Matching ◽  
Template Matching ◽  
Feature Representation ◽  
Image Feature ◽  
Feature Descriptor ◽  
Phase Congruency ◽  
Main Structure ◽  
Structure Information ◽  
Remote Sensing Image Processing ◽  
Multimodal Images

Abstract. Image matching is a crucial procedure for multimodal remote sensing image processing. However, the performance of conventional methods is often degraded in matching multimodal images due to significant nonlinear intensity differences. To address this problem, this letter proposes a novel image feature representation named Main Structure with Histogram of Orientated Phase Congruency (M-HOPC). M-HOPC is able to precisely capture similar structure properties between multimodal images by reinforcing the main structure information for the construction of the phase congruency feature description. Specifically, each pixel of an image is assigned an independent weight for feature descriptor according to the main structure such as large contours and edges. Then M-HOPC is integrated as the similarity measure for correspondence detection by a template matching scheme. Three pairs of multimodal images including optical, LiDAR, and SAR data have been used to evaluate the proposed method. The results show that M-HOPC is robust to nonlinear intensity differences and achieves the superior matching performance compared with other state-of-the-art methods.

scholarly journals SIFT Feature Extraction Algorithm for Image in DCT Domain

2013 ◽  
Vol 347-350 ◽  
pp. 2963-2967 ◽  
Author(s):  
Zhen Wu ◽  
Zhe Xu ◽  
Rui Nian Zhang ◽  
Shao Mei Li
Keyword(s):  
Feature Extraction ◽  
Image Matching ◽  
Coefficient Matrix ◽  
Image Feature ◽  
Image Feature Extraction ◽  
Sift Feature ◽  
Dct Domain ◽  
Extraction Algorithm ◽  
Dct Coefficients ◽  
The Relationship

Image feature extraction is an important technology in image matching and retrieval. For the problem of high computational complexity of spatial domain image feature extraction using the SIFT algorithm, and by studying the relationship between DCT coefficient matrix and image, the paper designed the DCT coefficients reduced matrix of image and proposed the algorithm of SIFT feature extraction in DCT domain reduced image. Experiments showed that with the low loss of accuracy in image matching and retrieval, the method proposed can significantly improve the computational efficiency of feature extraction.

scholarly journals Image Matching via Loopy RNN

2017 ◽  
Author(s):  
Donghao Luo ◽  
Bingbing Ni ◽  
Yichao Yan ◽  
Xiaokang Yang
Keyword(s):  
Image Matching ◽  
Short Term Memory ◽  
Vision System ◽  
Feature Representation ◽  
Image Feature ◽  
Matching Process ◽  
Head Node ◽  
Long Short Term Memory ◽  
Input Gate ◽  
Matching Score

Most existing matching algorithms are one-off algorithms, i.e., they usually measure the distance between the two image feature representation vectors for only one time. In contrast, human's vision system achieves this task, i.e., image matching, by recursively looking at specific/related parts of both images and then making the final judgement. Towards this end, we propose a novel loopy recurrent neural network (Loopy RNN), which is capable of aggregating relationship information of two input images in a progressive/iterative manner and outputting the consolidated matching score in the final iteration. A Loopy RNN features two uniqueness. First, built on conventional long short-term memory (LSTM) nodes, it links the output gate of the tail node to the input gate of the head node, thus it brings up symmetry property required for matching. Second, a monotonous loss designed for the proposed network guarantees increasing confidence during the recursive matching process. Extensive experiments on several image matching benchmarks demonstrate the great potential of the proposed method.

A Image Decomposition Method Based on Euler Mapping for Face Recognition

2014 ◽  
Vol 989-994 ◽  
pp. 4119-4122
Author(s):  
Zhao Kui Li ◽  
Yan Wang
Keyword(s):  
Feature Vector ◽  
State Of The Art ◽  
Image Decomposition ◽  
Feature Representation ◽  
Image Feature ◽  
Z Score ◽  
Linear Discriminant ◽  
Score Method ◽  
Representation Method ◽  
Low Dimensional

This paper presents a robust but simple image feature representation method, called image decomposition based on Euler mapping (IDEM). IDEM firstly captures the orientation information by implementing arctangent operator for each pixel. Then, the orientation image is decomposed into two mapping images by executing Euler mapping. Each mapping image is normalized using the “z-score” method, and all normalized vectors are concatenated into an augmented feature vector. The dimensionality of the augmented feature vector is reduced by linear discriminant analysis to yield a low-dimensional feature vector. Experimental results show that IDEM achieves better results in comparison with state-of-the-art methods.

Image feature extraction algorithm in big data environment

2020 ◽  
Vol 39 (4) ◽  
pp. 5109-5118
Author(s):  
Yubao Zhang
Keyword(s):  
Feature Extraction ◽  
Big Data ◽  
Image Matching ◽  
Image Database ◽  
Scale Space ◽  
Image Feature ◽  
Aerial Image ◽  
Image Feature Extraction ◽  
Matching Algorithm ◽  
Improved Algorithm

The purpose of this article is to explore effective image feature extraction algorithms in the context of big data, and to mine their potential information from complex image data. Based on the BRISK and SIFT algorithms, this paper proposes an image feature extraction and matching algorithm based on BRISK corner points. By combining the SIFT scale space and the BRISK algorithm, a new scale space construction method is proposed. The BRISK algorithm extracts the corner invariant features. Then, by using the improved feature matching method and eliminating the mismatching algorithm, the exact matching of the images is realized. A large number of experimental verifications were performed in the standard test Mikolajczyk image database and aerial image database. The experimental results show that the improved algorithm in this paper is an effective image matching algorithm. The highest accuracy of actual aerial image matching can reach 85.19%, and it can realize the actual aerial image matching that BRISK and SIFT algorithms cannot complete. The improved algorithm in this paper has the advantages of higher matching accuracy and strong robustness.

An Integrated Prediction Method for Identifying Protein-Protein Interactions

2020 ◽  
Vol 17 (4) ◽  
pp. 271-286
Author(s):  
Chang Xu ◽  
Limin Jiang ◽  
Zehua Zhang ◽  
Xuyao Yu ◽  
Renhai Chen ◽  
...  
Keyword(s):  
Protein Interactions ◽  
Feature Vector ◽  
Prediction Method ◽  
Feature Representation ◽  
Protein Interaction Networks ◽  
Learning Approach ◽  
Biological Processes ◽  
Integrated Learning ◽  
Protein Protein Interactions ◽  
Training Process

Background: Protein-Protein Interactions (PPIs) play a key role in various biological processes. Many methods have been developed to predict protein-protein interactions and protein interaction networks. However, many existing applications are limited, because of relying on a large number of homology proteins and interaction marks. Methods: In this paper, we propose a novel integrated learning approach (RF-Ada-DF) with the sequence-based feature representation, for identifying protein-protein interactions. Our method firstly constructs a sequence-based feature vector to represent each pair of proteins, viaMultivariate Mutual Information (MMI) and Normalized Moreau-Broto Autocorrelation (NMBAC). Then, we feed the 638- dimentional features into an integrated learning model for judging interaction pairs and non-interaction pairs. Furthermore, this integrated model embeds Random Forest in AdaBoost framework and turns weak classifiers into a single strong classifier. Meanwhile, we also employ double fault detection in order to suppress over-adaptation during the training process. Results: To evaluate the performance of our method, we conduct several comprehensive tests for PPIs prediction. On the H. pyloridataset, our method achieves 88.16% accuracy and 87.68% sensitivity, the accuracy of our method is increased by 0.57%. On the S. cerevisiaedataset, our method achieves 95.77% accuracy and 93.36% sensitivity, the accuracy of our method is increased by 0.76%. On the Humandataset, our method achieves 98.16% accuracy and 96.80% sensitivity, the accuracy of our method is increased by 0.6%. Experiments show that our method achieves better results than other outstanding methods for sequence-based PPIs prediction. The datasets and codes are available at https://github.com/guofei-tju/RF-Ada-DF.git.

Sign in / Sign up

Export Citation Format

Share Document