scholarly journals COLOR IMAGE RETRIEVAL BASED ON FUZZY NEURAL NETWORK AND SWARM INTELLIGENCE TECHNIQUES

2022 ◽  
Vol 23 (1) ◽  
pp. 116-128
Author(s):  
Baydaa Khaleel
Keyword(s):  
Neural Network ◽  
Image Retrieval ◽  
Heuristic Algorithms ◽  
Color Image ◽  
Single Layer ◽  
Cuckoo Search ◽  
Query Image ◽  
Linear Discriminant ◽  
Fuzzy Neural ◽  
Image Retrieval System

Image retrieval is an important system for retrieving similar images by searching and browsing in a large database. The image retrieval system can be a reliable tool for people to optimize the use of image accumulation, and finding efficient methods to retrieve images is very important. Recent decades have marked increased research interest in field image retrieval. To retrieve the images, an important set of features is used. In this work, a combination of methods was used to examine all the images and detect images in a database according to a query image. Linear Discriminant Analysis (LDA) was used for feature extraction of the images into the dataset. The images in the database were processed by extracting their important and robust features and storing them in the feature store. Likewise, the strong features were extracted for specific query images. By using some Meta Heuristic algorithms such as Cuckoo Search (CS), Ant Colony Optimization (ACO), and using an artificial neural network such as single-layer Perceptron Neural Network (PNN), similarity was evaluated. It also proposed a new two method by hybridized PNN and CS with fuzzy logic to produce a new method called Fuzzy Single Layer Perceptron Neural Network (FPNN), and Fuzzy Cuckoo Search to examine the similarity between features for query images and features for images in the database. The efficiency of the system methods was evaluated by calculating the precision recall value of the results. The proposed method of FCS outperformed other methods such as (PNN), (ACO), (CS), and (FPNN) in terms of precision and image recall. ABSTRAK: Imej dapatan semula adalah sistem penting bagi mendapatkan imej serupa melalui carian imej dan melayari pangkalan besar data. Sistem dapatan semula imej ini boleh dijadikan alat boleh percaya untuk orang mengoptimum penggunaan pengumpulan imej, dan kaedah pencarian yang berkesan bagi mendapatkan imej adalah sangat penting. Beberapa dekad yang lalu telah menunjukan banyak penyelidikan dalam bidang imej dapatan semula. Bagi mendapatkan imej-imej ini, ciri-ciri set penting telah digunakan. Kajian ini menggunakan beberapa kaedah bagi memeriksa semua imej dan mengesan imej dalam pangkalan data berdasarkan imej carian. Kami menggunakan Analisis Diskriminan Linear (LDA) bagi mengekstrak ciri imej ke dalam set data. Imej-imej dalam pangkalan data diproses dengan mengekstrak ciri-ciri penting dan berkesan daripadanya dan menyimpannya dalam simpanan ciri. Begitu juga, ciri-ciri penting ini diekstrak bagi imej carian tertentu. Persamaan dinilai melalui beberapa algoritma Meta Heuristik seperti Carian Cuckoo (CS), Pengoptimuman Koloni Semut (ACO), dan menggunakan lapisan tunggal rangkaian neural buatan seperti Rangkaian Neural Perseptron (PNN). Dua cadangan baru dengan kombinasi hibrid PNN dan CS bersama logik kabur bagi menghasilkan kaedah baru yang disebut Lapisan Tunggal Kabur Rangkaian Neural Perceptron (FPNN), dan Carian Cuckoo Kabur bagi mengkaji persamaan antara ciri carian imej dan imej pangkalan data. Nilai kecekapan kaedah sistem dinilai dengan mengira ketepatan mengingat pada dapatan hasil. Kaedah FCS yang dicadangkan ini mengatasi kaedah lain seperti (PNN), (ACO), (CS) dan (FPNN) dari segi ketepatan dan ingatan imej.

scholarly journals Image Retrieval System using Residual Neural Network in a Distributed Environment

2020 ◽  
Vol 8 (6) ◽  
pp. 4597-4605
Keyword(s):  
Neural Network ◽  
Image Retrieval ◽  
Retrieval System ◽  
Image Data ◽  
Content Based Image Retrieval ◽  
Features Selection ◽  
Query Image ◽  
Server Side ◽  
Image Retrieval System ◽  
Client Side

Development of Content-Based Image Retrieval systems supports retrieval of similar images based on selected features. Selection of appropriate features for this process is a difficult task. In this regard, deep learning concept helps in choosing appropriate features for retrieval. In this work, Content-Based Image Retrieval system is proposed using Convolution Neural Network known as Residual Neural Network model. The dataset used to build retrieval system is collection of web images 50,000 of 250 categories. The model is trained on 40% of image data and tested on 60% of data. When user submits a query image from the client-side, similar features are extracted by the model on server-side. Later, the features of query image are compared with trained images data and similarity is measured using the metric of Euclidean distance. The retrieved resultant images are displayed on Graphical User Interface. The results are comparatively higher with the existing systems. The proposed work is also compared with Google’s Image retrieval system for random query images and our proposed work has shown a better performance by 14.27%.

scholarly journals Enriching Image Retrieval System through CNN for Sketches and Images

2019 ◽  
Vol 8 (3) ◽  
pp. 1407-1412
Keyword(s):  
Neural Network ◽  
Image Retrieval ◽  
Region Of Interest ◽  
Query Image ◽  
Research Areas ◽  
Finger Counting ◽  
Image Retrieval System ◽  
Retrieval Mechanism ◽  
Processing Techniques ◽  
Current Paradigm

Image retrieval is being a one of the widely research areas in the current paradigm of the software industry. This is mainly due to as a proverb "image can speak many words", which is because of its diversity of the contained objects and their pattern. Many search engines including Google, is providing the option of searching images by giving query image, most of the time this searching is done by the averaging the features of the images which yields considerable low precision. Convolution neural network and Recurrent neural network are widely used mechanisms to handle the image processing techniques in image retrieval. On using of CNN and RNN many systems are yielding the low accuracy because of the features that they are considering. And again, only finger counting systems are dealing with the image retrieval mechanism for the input of the object rather than the whole image. So as a tiny step towards this, this research article proposes a model of image retrieval using the input as image sketch and images using the histogram features and Region of interest based on the position, volume, color and orientation through the interactive CNN model. The image search is performed using the CNN through K means Clustering and Haar wavelets.

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.

Downsizing the Semantic Gap in Contextual Image Retrieval System Using Superintend Gross Silhouette Descriptor

2020 ◽  
Vol 8 (4) ◽  
pp. 1-20
Author(s):  
Girija G. Chiddarwar ◽  
S.Phani Kumar
Keyword(s):  
Image Retrieval ◽  
Correlation Coefficient ◽  
Retrieval System ◽  
Shape Descriptor ◽  
Query Image ◽  
Relationship Strength ◽  
Image Retrieval System ◽  
High Level ◽  
Straight Lines ◽  
The Relationship

Since shape is the most important feature for recognizing objects, it has to be extracted accurately in order to enhance the content based image retrieval system, but challenges prevailed in extracting shape features of an object in an image due to inability of shape descriptor which extracts a limited number of different shapes that are not invariant, alongside the inability to extracting features of overlapping objects, and the shape connotation gap problem between low level and high level features. In order to overcome these problems, this work proposes a Superintend Gross Silhouette Descriptor which uses pixel coordinates on spatial domain of the image for finding the real shape of the object by means of straight lines so it has the ability to detect the overlapped objects as well as the polygonal shapes. After being extracted, features would be trained using a random woodland classifier which classifies the features into a group of classes at maximum convergence for mitigating the shape connotation problem. At the time of retrieval, the features of the query image would be tested with trained features for measuring the similarity by the dynamite correlation coefficient method, which is a measure of the linear correlation so it would render the absolute value of the correlation coefficient which maintains the relationship strength among features.

Sign in / Sign up

Export Citation Format

Share Document