Holistic Feature Extraction for Automatic Image Annotation

2011 ◽  
Author(s):  
Supheakmungkol Sarin ◽  
Michael Fahrmair ◽  
Matthias Wagner ◽  
Wataru Kameyama
Keyword(s):  
Feature Extraction ◽  
Image Annotation ◽  
Automatic Image Annotation

A Probabilistic SVM Approach to Annotation of Calcification Mammograms

2012 ◽  
pp. 208-222
Author(s):  
Chia-Hung Wei ◽  
Sherry Y. Chen
Keyword(s):  
Feature Extraction ◽  
Image Classification ◽  
Image Annotation ◽  
Medical Images ◽  
Extraction Methods ◽  
Experimental Results ◽  
Automatic Image Annotation ◽  
Accuracy Rate ◽  
Present Feature ◽  
Average Accuracy

Due to the increasing use of digital medical images, a need exists to develop an approach for automatic image annotation, which provides textual labels for images. Thus added labels can be used to access images using textual queries. Automatic image annotation can be separated into two individual tasks: feature extraction and image classification. In this paper, the authors present feature extraction methods for calcification mammograms. The resultant features, based on BI-RADS standards, make annotated image contents represent the correct medical meaning and tag correspondent terms. Furthermore, this paper also proposes a probabilistic SVM approach to image classification. Finally, the experimental results indicate that the probabilistic SVM approach to image annotation can achieve 79.5% in the average accuracy rate.

scholarly journals ASALTAG : Automatic Image Annotation Through Salient Object Detection and Improved k-Nearest Neighbor Feature Matching

2018 ◽  
Vol 2 (1) ◽  
pp. 6
Author(s):  
Theresia Hendrawati ◽  
Duman Care Khrisne
Keyword(s):  
Feature Extraction ◽  
Object Detection ◽  
Nearest Neighbor ◽  
Distance Measure ◽  
Image Annotation ◽  
Salient Object Detection ◽  
Salient Object ◽  
Automatic Image Annotation ◽  
K Nearest Neighbor ◽  
Hu Moments

Image databases are becoming very large nowadays, and there is an increasing need for automatic image annotation, for assiting on finding the desired specific image. In this paper, we present a new approach of automatic image annotation using salient object detection and improved k-Nearest Neigbor classifier named ASALTAG. ASALTAG is consist of three major part, the segmentation using Minimum Barirer Salienct Region Segmentation, feature extraction using Block Truncation Algorithm, Gray Level Co-occurrence Matrix and Hu’ Moments, the last part is classification using improved k-Nearest Neigbor. As the result we get maximum accuracy of 79.56% with k=5, better than earlier research. It is because the saliency object detection we do before the feature extraction proccess give us more focused object in image to annotate. Normalization of the feature vector and the distance measure that we use in ASALTAG also improve the kNN classifier accuracy for labeling image.

Multi-class particle swarm model selection for automatic image annotation

2012 ◽  
Vol 39 (12) ◽  
pp. 11011-11021 ◽  
Author(s):  
Hugo Jair Escalante ◽  
Manuel Montes ◽  
L. Enrique Sucar
Keyword(s):  
Model Selection ◽  
Image Annotation ◽  
Particle Swarm ◽  
Automatic Image Annotation ◽  
Selection For

scholarly journals Automatic image annotation based on deep learning models: a systematic review and future challenges

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Myasar Mundher Adnan ◽  
Mohd Shafry Mohd Rahim ◽  
Amjad Rehman ◽  
Zahid Mehmood ◽  
Tanzila Saba ◽  
...  
Keyword(s):  
Systematic Review ◽  
Deep Learning ◽  
Image Annotation ◽  
Automatic Image Annotation ◽  
Learning Models ◽  
Future Challenges
Sign in / Sign up

Export Citation Format

Share Document