An efficient framework for image retrieval using color, texture and edge features

Pavithra, L. K.; Sharmila, T. Sree

doi:10.1016/j.compeleceng.2017.08.030

Cited by 79 publications

(31 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this system, color is extracted using a basic RGB color space model. For the shape analysis, the median filter has been used and finally, Gray level co-occurrence matrix (GLCM) has been employed to extract features related to texture [5]. For similarity calculation, memetic algorithm, which is the combination of Genetic and Great deluge algorithms, has been used.…”

Section: B Related State-of-the-art Workmentioning

confidence: 99%

An Extreme Learning Machine-Relevance Feedback Framework for Enhancing the Accuracy of a Hybrid Image Retrieval System

Shikha¹,

Gitanjali²,

Kumar³

2020

IJIMAI

View full text Add to dashboard Cite

The process of searching, indexing and retrieving images from a massive database is a challenging task and the solution to these problems is an efficient image retrieval system. In this paper, a unique hybrid Content-based image retrieval system is proposed where different attributes of an image like texture, color and shape are extracted by using Gray level co-occurrence matrix (GLCM), color moment and various region props procedure respectively. A hybrid feature matrix or vector (HFV) is formed by an integration of feature vectors belonging to three individual visual attributes. This HFV is given as an input to an Extreme learning machine (ELM) classifier which is based on a solitary hidden layer of neurons and also is a type of feed-forward neural system. ELM performs efficient class prediction of the query image based on the pre-trained data. Lastly, to capture the high level human semantic information, Relevance feedback (RF) is utilized to retrain or reformulate the training of ELM. The advantage of the proposed system is that a combination of an ELM-RF framework leads to an evolution of a modified learning and intelligent classification system. To measure the efficiency of the proposed system, various parameters like Precision, Recall and Accuracy are evaluated. Average precision of 93.05%, 81.03%, 75.8% and 90.14% is obtained respectively on Corel-1K, Corel-5K, Corel-10K and GHIM-10 benchmark datasets. The experimental analysis portrays that the implemented technique outmatches many state-of-the-art related approaches depicting varied hybrid CBIR system.

show abstract

Section: B Related State-of-the-art Workmentioning

confidence: 99%

An Extreme Learning Machine-Relevance Feedback Framework for Enhancing the Accuracy of a Hybrid Image Retrieval System

Shikha¹,

Gitanjali²,

Kumar³

2020

IJIMAI

View full text Add to dashboard Cite

show abstract

“…The similarity is calculated with the use of distance metrics along with appropriate weights for different features. In [10], retrieval systems use color moment, local binary patterns and edge features to obtain similar images by using Manhattan similarity metric.…”

Section: Related Workmentioning

confidence: 99%

Retrieval of Images using Combination of Features as Color, Color Moments and Hu Moments

Raj¹,

Sudhamani²

2019

AIVP

View full text Add to dashboard Cite

In today’s digital era, several of the image retrieval systems focus on retrieving images using features from images themselves such as color, shape and textures and are referred as low-level features. In this proposed work, the features like color with HSV color space, color moments and Hu moments are employed to retrieve similar images. Various experimentations were conducted on Wang’s database images to test the combination of features for higher performance using precision, recall, accuracy and f-score. The results obtained are compared with one another and also with existing works. The retrieval performance is found to be high for proposed system against existing works.

show abstract

“…The important features such as the extraction of images, color features are defined in the RGB and HSV histogram [4]. The color features are extracted from the color moments, color histogram, invariant color histogram [20].…”

Section: Endmentioning

confidence: 99%

Re-Ranking Images Retrieval: Combined Multiple Features Method

P*¹,

JAYAKUMAR²

2019

IJRTE

View full text Add to dashboard Cite

Content-Based Image Retrieval (CBIR) grown rapidly in multimedia field, image retrieval, pattern recognition, etc. CBIR provides an effective way of image search and retrieval from the pool image databases. Learning effective relevance measures plays a critical role in improving the performance of image retrieval systems. In this paper present a Combined multiple features method which is two key parameters (i) Feature extraction, (ii) Similarity metrics for content-based image retrieval method. Feature extraction and similarity metrics important role in Content-Based Image Retrieval. We define hybrid feature extraction and similarity method for finding the most similar images retrieved. Combined features extraction using the various image features. These papers explain some important distance metrics such as Euclidean distance and City block distance. The experiments are performed using the various kinds of databases such as WANG Database, Corel Dataset. The experimental result shows that the proposed method is proved more effective than existing methods.

show abstract

An efficient framework for image retrieval using color, texture and edge features

Cited by 79 publications

References 17 publications

An Extreme Learning Machine-Relevance Feedback Framework for Enhancing the Accuracy of a Hybrid Image Retrieval System

An Extreme Learning Machine-Relevance Feedback Framework for Enhancing the Accuracy of a Hybrid Image Retrieval System

Retrieval of Images using Combination of Features as Color, Color Moments and Hu Moments

Re-Ranking Images Retrieval: Combined Multiple Features Method

Contact Info

Product

Resources

About