scispace - formally typeset

Book ChapterDOI

Artificial Immune Hybrid Photo Album Classifier

01 Jan 2017-pp 475-485

TL;DR: An Artificial Immune Hybrid Photo Album Classifier (AIHPAC) is proposed using the nonlinear biological properties of Human Immune Systems to develop an adaptive and automated personalized photo management system which efficiently manages and organizes personal photos.

AbstractThe personal photo collections are becoming significant in our day today existence. The challenge is to precisely intuit user’s complex and transient interests and to accordingly develop an adaptive and automated personalized photo management system which efficiently manages and organizes personal photos. This is increasingly gaining importance as it will be required to browse, search and retrieve efficiently the relevant information from personal collections which may extend from many years. Significance and relevance for the user also may undergo temporal and crucial shifts which need to be continually logged to generate patterns. The cloud paradigm makes available the basic platform but a system needs to be built wherein a personalized service with ability to capture diversity is guaranteed even when the training data size is small. An Artificial Immune Hybrid Photo Album Classifier (AIHPAC) is proposed using the nonlinear biological properties of Human Immune Systems. The system does event based clustering for an individual with embedded feature selection. The model is self learning and self evolving. The efficacy of the proposed method is efficiently demonstrated by the experimental results.

...read more


Citations
More filters
Book ChapterDOI
01 Jan 2020
TL;DR: This work proposes a novel framework where the small labelled dataset is appropriately augmented using the intelligent learning mechanisms of artificial immune systems to train the proposed model and shows that the generative deep framework utilizing artificial immune system principles provides a highly competitive approach for learning in the semi-supervised environment.
Abstract: Labelled data are not only time consuming but often expensive and difficult to procure as it involves skilful inputs by humans to tag and annotate. Contrary to this unlabelled data is comparatively easier to procure but fewer methods exist to optimally use them. Semi-Supervised Learning overcomes this problem and assists to build better classifiers by using unlabelled data along with sufficient labelled data and may actually yield higher accuracy with considerably less human input effort. But if the labelled data set is inadequate in size then the Semi-Supervised techniques are also stuck. We propose a novel framework where the small labelled dataset is appropriately augmented using the intelligent learning mechanisms of artificial immune systems to train the proposed model. The model retrains with the unlabelled data to fortify the learning mechanism. We show that the generative deep framework utilizing artificial immune system principles provides a highly competitive approach for learning in the semi-supervised environment.

References
More filters
Proceedings ArticleDOI
11 Nov 2001
TL;DR: PhotoMesa is a zoomable image browser that uses a novel treemap algorithm to present large numbers of images grouped by directory, or other available metadata that makes it straightforward to navigate through the space of images, and impossible to get lost.
Abstract: PhotoMesa is a zoomable image browser that uses a novel treemap algorithm to present large numbers of images grouped by directory, or other available metadata. It uses a new interaction technique for zoomable user interfaces designed for novices and family use that makes it straightforward to navigate through the space of images, and impossible to get lost.PhotoMesa groups images using one of two new algorithms that lay out groups of objects in a 2D space-filling manner. Quantum treemaps are designed for laying out images or other objects of indivisible (quantum) size. They are a variation on existing treemap algorithms in that they guarantee that every generated rectangle will have a width and height that are an integral multiple of an input object size. Bubblemaps also fill space with groups of quantum-sized objects, but generate non-rectangular blobs, and utilize space more efficiently.

420 citations

Proceedings ArticleDOI
01 May 1999
TL;DR: FotoFile is an experimental system for multimedia organization and retrieval, based upon the design goal of making multimedia content accessible to non-expert users that blends human and automatic annotation methods.
Abstract: FotoFile is an experimental system for multimedia organization and retrieval, based upon the design goal of making multimedia content accessible to non-expert users. Search and retrieval are done in terms that are natural to the task. The system blends human and automatic annotation methods. It extends textual search, browsing, and retrieval technologies to support multimedia data types.

316 citations

Proceedings ArticleDOI
10 Oct 2004
TL;DR: The contextual metadata that is automatically assembled for a photograph, given time and location, is described, as well as a browser interface that utilizes that metadata.
Abstract: Given time and location information about digital photographs we can automatically generate an abundance of related contextual metadata, using off-the-shelf and Web-based data sources. Among these are the local daylight status and weather conditions at the time and place a photo was taken. This metadata has the potential of serving as memory cues and filters when browsing photo collections, especially as these collections grow into the tens of thousands and span dozens of years.We describe the contextual metadata that we automatically assemble for a photograph, given time and location, as well as a browser interface that utilizes that metadata. We then present the results of a user study and a survey that together expose which categories of contextual metadata are most useful for recalling and finding photographs. We identify among still unavailable metadata categories those that are most promising to develop next.

210 citations

Proceedings ArticleDOI
30 Jul 2000
TL;DR: The PhotoFinder prototype is implemented to enable non-technical users of personal photo collections to search and browse easily, and provides a set of visual Boolean query interfaces coupled with dynamic query and query preview features.
Abstract: Software tools for personal photo collection management are proliferating, but they usually have limited searching and browsing functions. We implemented the PhotoFinder prototype to enable non-technical users of personal photo collections to search and browse easily. PhotoFinder provides a set of visual Boolean query interfaces, coupled with dynamic query and query preview features. It gives users powerful search capabilities. Using a scatter plot thumbnail display and drag-and-drop interface, PhotoFinder is designed to be easy to use for searching and browsing photos.

194 citations

Proceedings ArticleDOI
12 Sep 2009
TL;DR: An automated annotation framework composed by three main components: the context information generator, the semantic concept detector, and the face recognition model that makes the photo collection more structured and searchable.
Abstract: Current researches toward solving personal photo management suffered two problems: (1) lacking of training data, and (2) no consolidated reference for classification. In this paper, we propose an automated annotation framework to address these problems. The framework was composed by three main components: the context information generator, the semantic concept detector, and the face recognition model. By assigning multi-labels for each photo, the framework makes the photo collection more structured and searchable. Our experimental results show that the techniques used in this framework are promising.

17 citations