KTRICT A KAZE Feature Extraction

2020 ◽  
Vol 11 (2) ◽  
pp. 49-65
Author(s):  
Badal Soni ◽  
Angana Borah ◽  
Pidugu Naga Lakshmi Sowgandhi ◽  
Pramod Sarma ◽  
Ermyas Fekadu Shiferaw
Keyword(s):  
Feature Extraction ◽  
Search Space ◽  
Random Projection ◽  
Semantic Gap ◽  
Query Image ◽  
Retrieval Time ◽  
Similar Images ◽  
Two Phases ◽  
Kaze Feature ◽  
Memory Indexing

To improve the retrieval accuracy in CBIR system means reducing this semantic gap. Reducing semantic is a necessity to build a better, trusted system, since CBIR systems are applied to a lot of fields that require utmost accuracy. Time constraint is also a very important factor since a fast CBIR system leads to a fast completion of different tasks. The aim of the paper is to build a CBIR system that provides high accuracy in lower time complexity and work towards bridging the aforementioned semantic gap. CBIR systems retrieve images that are related to query image (QI) from huge datasets. The traditional CBIR systems include two phases: feature extraction and similarity matching. Here, a technique called KTRICT, a KAZE-feature extraction, tree and random-projection indexing-based CBIR technique, is introduced which incorporates indexing after feature extraction. This reduces the retrieval time by a great extent and also saves memory. Indexing divides a search space into subspaces containing similar images together, thereby decreasing the overall retrieval time.

scholarly journals CBIR Using Features Derived by Deep Learning

2021 ◽  
Vol 2 (3) ◽  
pp. 1-24
Author(s):  
Subhadip Maji ◽  
Smarajit Bose
Keyword(s):  
Deep Learning ◽  
Network Models ◽  
Classification Problem ◽  
Semantic Gap ◽  
Large Database ◽  
High Similarity ◽  
Query Image ◽  
Usual Procedure ◽  
Similar Images ◽  
High Level

In a Content-based Image Retrieval (CBIR) System, the task is to retrieve similar images from a large database given a query image. The usual procedure is to extract some useful features from the query image and retrieve images that have a similar set of features. For this purpose, a suitable similarity measure is chosen, and images with high similarity scores are retrieved. Naturally, the choice of these features play a very important role in the success of this system, and high-level features are required to reduce the “semantic gap.” In this article, we propose to use features derived from pre-trained network models from a deep-learning convolution network trained for a large image classification problem. This approach appears to produce vastly superior results for a variety of databases, and it outperforms many contemporary CBIR systems. We analyse the retrieval time of the method and also propose a pre-clustering of the database based on the above-mentioned features, which yields comparable results in a much shorter time in most of the cases.

scholarly journals An Appraisal of Content-Based Image Retrieval (CBIR) Methods

2019 ◽  
pp. 1-15
Author(s):  
J. O. Olaleke ◽  
A. O. Adetunmbi ◽  
B. A. Ojokoh ◽  
Iroju Olaronke
Keyword(s):  
Feature Extraction ◽  
Image Retrieval ◽  
Digital Libraries ◽  
Large Scale ◽  
Content Based Image Retrieval ◽  
Query Image ◽  
Advantages And Disadvantages ◽  
Feature Extraction And Selection ◽  
Similar Images ◽  
Google Search

Background: Content Based Image Retrieval (CBIR) is an aspect of computer vision and image processing that finds images that are similar to a given query image in a large scale database using the visual contents of images such as colour, texture, shape, and spatial arrangement of regions of interest (ROIs) rather than manually annotated textual keywords. A CBIR system represents an image as a feature vector and measures the similarity between the image and other images in the database for the purpose of retrieving similar images with minimal human intervention. The CBIR system has been deployed in several fields such as fingerprint identification, biodiversity information systems, digital libraries, Architectural and Engineering design, crime prevention, historical research and medicine. There are several steps involved in the development of CBIR systems. Typical examples of these steps include feature extraction and selection, indexing and similarity measurement. Problem: However, each of these steps has its own method. Nevertheless, there is no universally acceptable method for retrieving similar images in CBIR. Aim: Hence, this study examines the diverse methods used in CBIR systems. This is with the aim of revealing the strengths and weakness of each of these methods. Methodology: Literatures that are related to the subject matter were sought in three scientific electronic databases namely CiteseerX, Science Direct and Google scholar. The Google search engine was used to search for documents and WebPages that are appropriate to the study. Results: The result of the study revealed that three main features are usually extracted during CBIR. These features include colour, shape and text. The study also revealed that diverse methods that can be used for extracting each of the features in CBIR. For instance, colour space, colour histogram, colour moments, geometric moment as well as colour correlogram can be used for extracting colour features. The commonly used methods for texture feature extraction include statistical, model-based, and transform-based methods while the edge method, Fourier transform and Zernike methods can be used for extracting shape features. Contributions: The paper highlights the benefits and challenges of diverse methods used in CBIR. This is with the aim of revealing the methods that are more efficient for CBIR. Conclusion: Each of the CBIR methods has their own advantages and disadvantages. However, there is a need for a further work that will validate the reliability and efficiency of each of the method.

scholarly journals An Advanced Relevance Feedback Method to Improve Performance of CBIR using Convolutional Neural Network and Comprehensive Values

2019 ◽  
Vol 9 (2) ◽  
pp. 5427-5438
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Image Retrieval ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Activation Function ◽  
Image Feature ◽  
Similarity Measurement ◽  
Query Image ◽  
Image Production

Content-Based Image Retrieval (CBIR) is extensively used technique for image retrieval from large image databases. However, users are not satisfied with the conventional image retrieval techniques. In addition, the advent of web development and transmission networks, the number of images available to users continues to increase. Therefore, a permanent and considerable digital image production in many areas takes place. Quick access to the similar images of a given query image from this extensive collection of images pose great challenges and require proficient techniques. From query by image to retrieval of relevant images, CBIR has key phases such as feature extraction, similarity measurement, and retrieval of relevant images. However, extracting the features of the images is one of the important steps. Recently Convolutional Neural Network (CNN) shows good results in the field of computer vision due to the ability of feature extraction from the images. Alex Net is a classical Deep CNN for image feature extraction. We have modified the Alex Net Architecture with a few changes and proposed a novel framework to improve its ability for feature extraction and for similarity measurement. The proposal approach optimizes Alex Net in the aspect of pooling layer. In particular, average pooling is replaced by max-avg pooling and the non-linear activation function Maxout is used after every Convolution layer for better feature extraction. This paper introduces CNN for features extraction from images in CBIR system and also presents Euclidean distance along with the Comprehensive Values for better results. The proposed framework goes beyond image retrieval, including the large-scale database. The performance of the proposed work is evaluated using precision. The proposed work show better results than existing works.

A Novel Non-Decreasing Temperature Based Simulated Annealing for Flow Shop Problems

2015 ◽  
Vol 764-765 ◽  
pp. 1390-1394
Author(s):  
Ruey Maw Chen ◽  
Frode Eika Sandnes
Keyword(s):  
Simulated Annealing ◽  
Flow Shop ◽  
State Of The Art ◽  
Computation Time ◽  
Search Space ◽  
Control Mechanisms ◽  
Flow Shop Problem ◽  
Simple Implementation ◽  
Two Phases ◽  
Permutation Schedule

The permutation flow shop problem (PFSP) is an NP-hard permutation sequencing scheduling problem, many meta-heuristics based schemes have been proposed for finding near optimal solutions. A simple insertion simulated annealing (SISA) scheme consisting of two phases is proposed for solving PFSP. First, to reduce the complexity, a simple insertion local search is conducted for constructing the solution. Second, to ensure continuous exploration in the search space, two non-decreasing temperature control mechanisms named Heating SA and Steady SA are introduced in a simulated annealing (SA) procedure. The Heating SA increases the exploration search ability and the Steady SA enhances the exploitation search ability. The most important feature of SISA is its simple implementation and low computation time complexity. Experimental results are compared with other state-of-the-art algorithms and reveal that SISA is able to efficiently yield good permutation schedule.

scholarly journals Dynamic switching enables efficient bacterial colonization in flow

2018 ◽  
Vol 115 (21) ◽  
pp. 5438-5443 ◽  
Author(s):  
Anerudh Kannan ◽  
Zhenbin Yang ◽  
Minyoung Kevin Kim ◽  
Howard A. Stone ◽  
Albert Siryaporn
Keyword(s):  
Mammalian Cells ◽  
Spatial Organization ◽  
Dynamic Instability ◽  
Bacterial Colonization ◽  
Cell Types ◽  
Search Space ◽  
Flow Networks ◽  
Surface Attachment ◽  
Dynamic Switching ◽  
Two Phases

Bacteria colonize environments that contain networks of moving fluids, including digestive pathways, blood vasculature in animals, and the xylem and phloem networks in plants. In these flow networks, bacteria form distinct biofilm structures that have an important role in pathogenesis. The physical mechanisms that determine the spatial organization of bacteria in flow are not understood. Here, we show that the bacteriumP. aeruginosacolonizes flow networks using a cyclical process that consists of surface attachment, upstream movement, detachment, movement with the bulk flow, and surface reattachment. This process, which we have termed dynamic switching, distributes bacterial subpopulations upstream and downstream in flow through two phases: movement on surfaces and cellular movement via the bulk. The model equations that describe dynamic switching are identical to those that describe dynamic instability, a process that enables microtubules in eukaryotic cells to search space efficiently to capture chromosomes. Our results show that dynamic switching enables bacteria to explore flow networks efficiently, which maximizes dispersal and colonization and establishes the organizational structure of biofilms. A number of eukaryotic and mammalian cells also exhibit movement in two phases in flow, which suggests that dynamic switching is a modality that enables efficient dispersal for a broad range of cell types.

Automatic Incremental Clustering Using Bat-Grey Wolf Optimizer-Based MapReduce Framework for Effective Management of High-Dimensional Data

2020 ◽  
Vol 11 (4) ◽  
pp. 72-92
Author(s):  
Ch. Vidyadhari ◽  
N. Sandhya ◽  
P. Premchand
Keyword(s):  
Feature Extraction ◽  
Bat Algorithm ◽  
Grey Wolf Optimizer ◽  
Jaccard Coefficient ◽  
Grey Wolf ◽  
Incremental Clustering ◽  
Mapreduce Framework ◽  
Text Documents ◽  
Two Phases ◽  
Point Distance

In this research paper, an incremental clustering approach-enabled MapReduce framework is implemented that include two phases, mapper and reducer phase. In the mapper phase, there are two processes, pre-processing and feature extraction. Once the input data is pre-processed, the feature extraction is done using wordnet features. Then, the features are fed to the reducer phase, where the features are selected using entropy function. Then, the automatic incremental clustering is done using bat-grey wolf optimizer (BAGWO). BAGWO is the integration of bat algorithm (BA) into grey wolf optimization (GWO) for generating various clusters of text documents. Upon the arrival of the incremental data, the mapping of the new data with respect to the centroids is done to obtain the effective cluster. For mapping, kernel-based deep point distance and for centroid update, fuzzy concept is used. The performance of the proposed framework outperformed the existing techniques using rand coefficient, Jaccard coefficient, and clustering accuracy with maximal values 0.921, 0.920, and 0.95, respectively.

An effective hyperspectral image retrieval method using integrated spectral and textural features

Sensor Review ◽  
2015 ◽  
Vol 35 (3) ◽  
pp. 274-281 ◽  
Author(s):  
Zhenfeng Shao ◽  
Weixun Zhou ◽  
Qimin Cheng ◽  
Chunyuan Diao ◽  
Lei Zhang
Keyword(s):  
Design Methodology ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Textural Features ◽  
Washington Dc ◽  
Query Image ◽  
Retrieval Method ◽  
Content Type ◽  
Similar Images

Purpose – The purpose of this paper is to improve the retrieval results of hyperspectral image by integrating both spectral and textural features. For this purpose, an improved multiscale opponent representation for hyperspectral texture is proposed to represent the spatial information of the hyperspectral scene. Design/methodology/approach – In the presented approach, end-member signatures are extracted as spectral features by means of the widely used end-member induction algorithm N-FINDR, and the improved multiscale opponent representation is extracted from the first three principal components of the hyperspectral data based on Gabor filters. Then, the combination similarity between query image and other images in the database is calculated, and the first k more similar images are returned in descending order of the combination similarity. Findings – Some experiments are calculated using the airborne hyperspectral data of Washington DC Mall. According to the experimental results, the proposed method improves the retrieval results, especially for image categories that have regular textural structures. Originality/value – The paper presents an effective retrieval method for hyperspectral images.

scholarly journals Template Based Pose and Illumination Invariant Face Recognition

2020 ◽  
Vol 8 (5) ◽  
pp. 3220-3229
Keyword(s):  
Face Recognition ◽  
Gabor Wavelet ◽  
Mathematical Methods ◽  
Query Image ◽  
Illumination Invariant ◽  
Face Images ◽  
The Face ◽  
Similar Images ◽  
Proper Face ◽  
The Impact

This article presents a method “Template based pose and illumination invariant face recognition”. We know that pose and Illumination are important variants where we cannot find proper face images for a given query image. As per the literature, previous methods are also not accurately calculating the pose and Illumination variants of a person face image. So we concentrated on pose and Illumination. Our System firstly calculates the face inclination or the pose of the head of a person with various mathematical methods. Then Our System removes the Illumination from the image using a Gabor phase based illumination invariant extraction strategy. In this strategy, the system normalizes changing light on face images, which can decrease the impact of fluctuating Illumination somewhat. Furthermore, a lot of 2D genuine Gabor wavelet with various orientations is utilized for image change, and numerous Gabor coefficients are consolidated into one entire in thinking about spectrum and phase. Finally, the light invariant is acquired by separating the phase feature from the consolidated coefficients. Then after that, the obtained Pose and illumination invariant images are convolved with Gabor filters to obtain Gabor images. Then templates will be extracted from these Gabor images and one template average is generated. Then similarity measure will be performed between query image template average and database images template averages. Finally the most similar images will be displayed to the user. Exploratory results on PubFig database, Yale B and CMU PIE face databases show that our technique got a critical improvement over other related strategies for face recognition under enormous pose and light variation conditions.

scholarly journals A Content Based Approach to Medical X-Ray Image Retrieval using Texture Features

2014 ◽  
Vol 12 (7) ◽  
pp. 3742-3748 ◽  
Author(s):  
Sumathi Ganesan ◽  
T.S. Subashini
Keyword(s):  
Image Retrieval ◽  
Imaging Techniques ◽  
Texture Features ◽  
X Rays ◽  
Query Image ◽  
City Block ◽  
X Ray ◽  
Important Research Topic ◽  
Similar Images ◽  
The City

Of late, the amount of digital X-ray images that are produced in hospitals is increasing incredibly fast. Efficient storing, processing and retrieving of X-ray images have thus become an important research topic. With the exponential need that arises in the search for the clinically relevant and visually similar medical images over a vast database, the arena of digital imaging techniques is forced to provide a potential and path-breaking methodology in the midst of technical advancements so as to give the best match in accordance to the user’s query image. CBIR helps doctors to compare X-rays of their current patients with images from similar cases and they could also use these images as queries to find the similar entries in the X-ray database. This paper focuses on six different classes of X-ray images, viz. chest, skull, foot, spine, pelvic and palm for efficient image retrieval. Initially the various X-rays are automatically classified into the six-different classes using BPNN and SVM as classifiers and GLCM co-efficient as features for classification. Indexing is done to make the retrieval fast and retrieval of similar images is based on the city block distance.  

Sign in / Sign up

Export Citation Format

Share Document