ANNOR: Efficient image annotation based on combining local and global features

“…The N + measure shows the number of tags with non-zero recalls (i.e. the number of tags correctly assigned by the annotation model at least once) PR = true positive true positive + false positive (14) RC: = true positive true positive + false negative (15)…”

Section: Evaluation Metricsmentioning

confidence: 99%

Architecture to improve the accuracy of automatic image annotation systems

Khatchatoorian

Jamzad

2020

IET Computer Vision

View full text Add to dashboard Cite

Automatic image annotation (AIA) is an image retrieval mechanism to extract relative semantic tags from visual content. So far, the improvement of accuracy in newly developed such methods have been about 1 or 2% in the F1‐score and the architectures seem to have room for improvement. Therefore, the authors designed a more detailed architecture for AIA and suggested new algorithms for its main parts. The proposed architecture has three main parts: feature extraction, learning, and annotation. They designed a novel learning method using machine learning and probability bases. In the annotation part, they suggest a novel method that gains the maximum benefit from the learning part. The combination of the proposed architecture, algorithms, and novel ideas resulted in new accuracy milestones in F1‐score on most commonly used datasets. In their architecture, N+ measure which shows the number of tags with non‐zero recalls showed that they could recall all tags for IAPRTC‐12 and ESP‐Games datasets.

show abstract

“…More recently, (Kuric & Bielikovan, 2015) proposed a method that combined global and local features in the process of automatic image annotation, to retrieve the best results during a search. The combination was more suitable to represent complex scenes and events categories because global and local features provide different kinds of information.…”

Section: Image Annotationmentioning

confidence: 99%

Encapsulation of Image Metadata for Ease of Retrieval and Mobility

Woods

Robert

2019

acs

View full text Add to dashboard Cite

Increasing proliferation of images due to multimedia capabilities of hand-held devices has resulted in loss of source information resulting from inherent mobility. These images are cumbersome to search out once stored away from their original source because they drop their descriptive data. This work, developed a model to encapsulate descriptive metadata into the Exif section of image header for effective retrieval and mobility. The resulting metadata used for retrieval purposes was mobile, searchable and non-obstructive.

show abstract

ANNOR: Efficient image annotation based on combining local and global features

Cited by 16 publications

References 33 publications

Multi‐label automatic image annotation approach based on multiple improvement strategies

Multi‐label automatic image annotation approach based on multiple improvement strategies

Architecture to improve the accuracy of automatic image annotation systems

Encapsulation of Image Metadata for Ease of Retrieval and Mobility

Contact Info

Product

Resources

About