Automatic Face Annotation in Personal Photo Collections Using Context-Based Unsupervised Clustering and Face Information Fusion

Abstract

Abstract-In this paper, a novel face annotation framework is proposed that systematically leverages context information such as situation awareness information with current face recognition (FR) solutions. In particular, unsupervised situation and subject clustering techniques have been developed that are aided by context information. Situation clustering groups together photos that are similar in terms of capture time and visual content, allowing for the reliable use of visual context information during subject clustering. The aim of subject clustering is to merge multiple face images that belong to the same individual. To take advantage of the availability of multiple face images for a particular individual, we propose effective FR methods that are based on face information fusion strategies. The performance of the proposed annotation method has been evaluated using a variety of photo sets. The photo sets were constructed using 1385 photos from the MPEG-7 Visual Core Experiment 3 (VCE-3) data set and approximately 20 000 photos collected from wellknown photo-sharing websites. The reported experimental results show that the proposed face annotation method significantly outperforms traditional face annotation solutions at no additional computational cost, with accuracy gains of up to 25% for particular cases.

Personal image and video organizer with person-based navigation Smart-PIVO system

“…According to Choi et al [4] personal photos commonly categorized and searched through conditions of who, where and when. Even though our approach is limited to 'who' it can supports video.…”

“…It's a major point of the Choi et al, [4] system. Using that kind of methodology is not simply going to help the task of author's development.…”

Fusion of face networks through the surveillance of public spaces to address sociological security recommendations

“…Some of the notable work related to privacy protection mechanism in video surveillance is [14] [15]. Moreover, photo tagging [10], face co-occurrence network [11], and automatic face annotation [16] can enhance the recognition of people of interest both in network. Existing work specially [11] the important of face images for recommending friend list in social network scenario.…”

“…MFCN Graph Construction Input: A threshold: T Output: MFCN Graph: ode ← createNode(f aces[i])10 if f romN ode is not in g.nodeList then11 add f romN ode to g.nodeList12 for j ← i + 1 to totalFaces-1 do13 toN ode ← createNode(f aces[j])14 if toN ode is not in g.nodeList then15 add toN ode to g.nodeList16 if Edge(f romN ode,toN ode) is not in17 g.edgeList then add Edge(f romN ode, toN ode) to 18 g.edgeList with value 1 else 19 increment Edge(f romN ode, 20 toN ode) in g.edgeList by 1 foreach Edge e ∈ g.edgeList do 21 if e.weight < T then 22 remove e from g.edgeList 23remove all the node from g.nodeList which is not 24 in the g.edgeList return g and the different devices that are connected inside the environment. Further, Section 4.2 presents the test results based on the experiment.…”

Drunk Person Screening using Eye Thermal Signatures

“…Iris Identification is a very important noninvasive biometric (1)(2)(3)(4)(5) procedure used so far for security purposes. It has been extensively used in the past, and research results are on the market in robust and high-performance commercial products.…”