Categorization of Images Using Autoencoder Hashing and Training of Intra Bin Classifiers for Image Classification and Annotation.
Automatic annotation of images is considered to be an important research problem in image retrieval. Traditional methods are computationally complex and fail to annotate correctly when the number of image classes is large and related. This paper proposes a novel approach, an autoencoder hashing, to...
| Publicado en: | Journal of Medical Systems Vol. 42; no. 7; pp. 1 - 2 |
|---|---|
| Autores principales: | , , |
| Formato: | algorithm equations & formulas pictorial research tables/charts Journal Article |
| Publicado: |
Springer Nature
Jul2018
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=130627138&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 130627138 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 01485598 4N0 jtl: Journal of Medical Systems issn: 01485598 maglogo: N pubinfo: dt: Jul2018 vid: 42 iid: 7 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 130627138 130627138 130627138 10.1007/s10916-018-0986-6 130627138 ppf: 1 ppct: 1 formats: fmt: @attributes: type: P tig: atl: Categorization of Images Using Autoencoder Hashing and Training of Intra Bin Classifiers for Image Classification and Annotation. aug: au: Mercy Rajaselvi Beaulah, P. Manjula, D. Sugumaran, Vijayan affil: Department of Computer science & Engineering, Easwari Engineering College, Chennai, India sug: subj: Diagnostic Imaging Classification Autoencoder Experimental Studies Information Technology Health Information Management Descriptive Statistics Data Analysis Software Precision Validity Information Retrieval Funding Source ab: Automatic annotation of images is considered to be an important research problem in image retrieval. Traditional methods are computationally complex and fail to annotate correctly when the number of image classes is large and related. This paper proposes a novel approach, an autoencoder hashing, to categorize images of large-scale image classes. The intra bin classifiers are trained to classify the query image, and the tag weight and tag frequency are computed to achieve a more effective annotation of the query image. The proposed approach has been compared with other existing approaches in the literature using performance measures, such as precision, accuracy, mean average precision (MAP), and F1 score. The experimental results indicate that our proposed approach outperforms the existing approaches. pubtype: Academic Journal doctype: algorithm equations & formulas pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|