CBIR : Color Feature Extraction using CIELAB Color Space with Compact Color Signature

The immense progress of new technology we have been created an enormous number of digital images by using such devices as a digital camera, scanner, and mobile phones so on. All the images which are taken by the devices to keep in Image Database. For retrieving the desire images which were given in an input image has compared with the large database according to the visual content used by the technique as referred to as the Content Based Image Retrieval (CBIR) system. There are two phases for retrieving images in the CBIR system, as the first one is feature extraction and the second one is similarity size. Thus, the feature extraction consists of every image has produced symbolic content in the form of the function. The visual contents of an image in the CBIR system contain the features which have represented as shape, texture, spatial region and color of the images. In our paper tries to design the images’ color features as in the steps to focus color representation in the k-d tree, CIELAB color space of color signature compression along with categories of Human’s color for Content-based image retrieval and also acquire the results using MATLAB.

Download Full-text

An Novel Framework For Content Based Image Retrieval With Quality Assessment System using Optimal Deep Convolution Neural Network

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.l3428.1081219 ◽

2019 ◽

Vol 8 (12) ◽

pp. 3916-3926

Keyword(s):

Feature Extraction ◽

Image Retrieval ◽

Feature Vector ◽

Structural Similarity ◽

Extraction Process ◽

Input Image ◽

Assessment System ◽

Content Based Image Retrieval ◽

Query Image ◽

Occurrence Matrix

Content based image retrieval (CBIR) models become popular for retrieving images connected to the query image (QI) from massive dataset. Feature extraction process in CBIR plays a vital role as it affects the system’s performance. This paper is focused on the design of deep learning (DL) model for feature extraction based CBIR model. The presented model utilizes a ResNet50 with co-occurrence matrix (RCM) model for CBIR. Here, the ResNet50 model is applied for feature extraction of the QI. Then, the extracted features are placed in the feature repository as a feature vector. The RCM model computes the feature vector for every input image and compares it with the features present in the repository. Then, the images with maximum resemblance will be retrieved from the dataset. In addition, the resemblance between the feature vectors is determined by the use of co-occurrence matrix subtraction process. Besides, structural similarity (SSIM) measure is applied for the validation of the similarity among the images. A comprehensive results analysis takes place by the use of Corel 10K dataset. The experimental outcome indicated the superiority of the RCM model with respect to precision, recall and SSIM.

Download Full-text

A novel content based image retrieval system using K-means/KNN with feature extraction

Computer Science and Information Systems ◽

10.2298/csis120122047c ◽

2012 ◽

Vol 9 (4) ◽

pp. 1645-1661 ◽

Cited By ~ 10

Author(s):

Ray-I Chang ◽

Shu-Yu Lin ◽

Jan-Ming Ho ◽

Chi-Wen Fann ◽

Yu-Chun Wang

Keyword(s):

Feature Extraction ◽

Image Retrieval ◽

Nearest Neighbor ◽

Clustering Algorithms ◽

Content Based Image Retrieval ◽

K Nearest Neighbor ◽

Color Analysis ◽

Image Retrieval System ◽

First Time ◽

System Designs

Image retrieval has been popular for several years. There are different system designs for content based image retrieval (CBIR) system. This paper propose a novel system architecture for CBIR system which combines techniques include content-based image and color analysis, as well as data mining techniques. To our best knowledge, this is the first time to propose segmentation and grid module, feature extraction module, K-means and k-nearest neighbor clustering algorithms and bring in the neighborhood module to build the CBIR system. Concept of neighborhood color analysis module which also recognizes the side of every grids of image is first contributed in this paper. The results show the CBIR systems performs well in the training and it also indicates there contains many interested issue to be optimized in the query stage of image retrieval.

Download Full-text

Content based Image Retrieval System using Local Feature Extraction Techniques

International Journal of Computer Applications ◽

10.5120/ijca2021921549 ◽

2021 ◽

Vol 183 (20) ◽

pp. 16-20

Author(s):

Abhishek Madduri

Keyword(s):

Feature Extraction ◽

Image Retrieval ◽

Retrieval System ◽

Local Feature ◽

Content Based Image Retrieval ◽

Extraction Techniques ◽

Image Retrieval System ◽

Local Feature Extraction

Download Full-text

Content Based Image Retrieval using Collaborative Color, Texture and Shape Features

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.b8014.019320 ◽

2020 ◽

Vol 9 (3) ◽

pp. 1466-1469

Keyword(s):

Feature Extraction ◽

Image Retrieval ◽

Texture Feature ◽

Content Based Image Retrieval ◽

Support Vector ◽

Feature Extraction Method ◽

Attribute Extraction ◽

The Individual ◽

Selection Of ◽

Color Texture

Selection of feature extraction method is incredibly recondite task in Content Based Image Retrieval (CBIR). In this paper, CBIR is implemented using collaboration of color; texture and shape attribute to improve the feature discriminating property. The implementation is divided in to three steps such as preprocessing, features extraction, classification. We have proposed color histogram features for color feature extraction, Local Binary Pattern (LBP) for texture feature extraction, and Histogram of oriented gradients (HOG) for shape attribute extraction. For the classification support vector machine classifier is applied. Experimental results show that combination of all three features outperforms the individual feature or combination of two feature extraction techniques

Download Full-text