A Methodology for Sketch based Image Retrieval based on Score level Fusion

Jhansi, Y.; Reddy, E. Sreenivasa

doi:10.5120/19167-0629

Cited by 3 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jhansi and Reddy [71] applied a score-level fusion model for retrieving sketched-based images. They used the "TU Berlin Sketch" dataset to assess their fusion model.…”

Section: ) Fusion-based Image Retrievalmentioning

confidence: 99%

Manuscripts Image Retrieval Using Deep Learning Incorporating a Variety of Fusion Levels

Khayyat

Elrefaei

2020

IEEE Access

View full text Add to dashboard Cite

The instantaneous search and retrieval of the most relevant images to a specific query image is a desirable application for all digital libraries. The automatic extraction and classification according to the most distinguishable features, is a crucial step to detect the similarities among images successfully. This study introduces a novel approach that utilizes a fusion model for classifying and retrieving historical Arabic manuscripts' images. To accomplish our goal, the images are first classified according to their extracted deep learning visual features utilizing a pre-trained convolutional neural network. Then, the texts written in the manuscripts' images are extracted and pre-processed to classify the images according to their textual features using an optimized bidirectional LSTM deep learning model with attention and batch normalization layers. Finally, both the visual and textual deep learning models are fused at three different fusion-levels named: decision-level, features-level, and score-level. The score-level fusion model resulted in a considerable improvement of each model used individually. Extensive experimentation and evaluation of the proposed fusion method on the collected ancient Arabic manuscripts dataset proved its robustness against other stateof-the-art methods recording 99% classification accuracy and 98% mean accuracy on the top-10 image retrieval.

show abstract

“…Jhansi and Reddy [71] applied a score-level fusion model for retrieving sketched-based images. They used the "TU Berlin Sketch" dataset to assess their fusion model.…”

Section: ) Fusion-based Image Retrievalmentioning

confidence: 99%

Manuscripts Image Retrieval Using Deep Learning Incorporating a Variety of Fusion Levels

Khayyat

Elrefaei

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Score level fusion is the fusion in matching score level. Therefore, it is additionally called matching level fusion (Cui and Yang, 2011;Jhansi and Reddy, 2015). In this research, the score level fusion is used to combined the matching score from fingerprint and face recognition.…”

Section: Score Level Fusionmentioning

confidence: 99%

An Efficient Multimodal Biometric Authentication Integrating Fingerprint and Face Features

Sayeed¹,

Nasir²,

Ong³

2016

American Journal of Applied Sciences

View full text Add to dashboard Cite

Biometrics authentication has been used in many applications such as e-commerce, access control etc. In this research, multimodal biometric authentication in light of score level combination of fingerprint and face is proposed. Face and fingerprint is two of the most popular biometric traits and can complement each other for more reliable user authentication. To verify the effectiveness of the proposed method, FERET, SDUMLA-HMT and FVC2002 databases are used in this research. Furthermore, experimental results showed that the proposed fusion based method for fingerprint and face recognition can improve the performance in terms of Equal Error Rate (EER). Eventually, the experimental result shows that our proposed fusion based technique appears to be promising with 7.01~9.13% of EER based on the different datasets.

show abstract

“…The area of Object Based Image Retrieval is very useful in the area of image retrievals and the main advantage with this mechanism is that based on object effective retrievals from massive datasets are made possible. This object can have any features and can help in an identification of image under studying and thereby helping towards efficient retrievals [1] [2].With these features many applications have been developed and are used in the domains of health care, medical, E-business, etc., [3][4] [5]. Many models are thus subjected to using both parametric model based approaches and non parametric model based approaches.…”

Section: Introductionmentioning

confidence: 99%

A Methodology for Efficient Sketch Based Image Retrievals Based on Correlation Based Matching and Generalized Gamma Mixture Model (GGMM)

Prasad¹,

Prasad²

2020

IJESE

View full text Add to dashboard Cite

The huge developments in touch screen devices and used in Computer vision developed the methodologies for recovering the images based on content. However in certain situations narration is the best suitable way to express and hence in the views of narration sketch based images are thus developed and utilized. These sketch based images are most useful in identifying face in criminal investigations. This paper provides a methodology for retrieving such sketch based images using the correlation based matching and generalized gamma mixture models. Performance is measured using precision and recall.

show abstract

A Methodology for Sketch based Image Retrieval based on Score level Fusion

Cited by 3 publications

References 20 publications

Manuscripts Image Retrieval Using Deep Learning Incorporating a Variety of Fusion Levels

Manuscripts Image Retrieval Using Deep Learning Incorporating a Variety of Fusion Levels

An Efficient Multimodal Biometric Authentication Integrating Fingerprint and Face Features

A Methodology for Efficient Sketch Based Image Retrievals Based on Correlation Based Matching and Generalized Gamma Mixture Model (GGMM)

Contact Info

Product

Resources

About