A Crowdsourcing Based Framework for E-Government: Suspect Identification and Investigation

Low-Resolution Face Recognition with Single Sample per Person via Domain Adaptation

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001419560056 ◽

2019 ◽

Vol 33 (05) ◽

pp. 1956005 ◽

Cited By ~ 2

Author(s):

Yongjie Chu ◽

Yong Zhao ◽

Touqeer Ahmad ◽

Lindu Zhao

Keyword(s):

Face Recognition ◽

Domain Adaptation ◽

Face Image ◽

Single Sample ◽

Low Resolution ◽

Target Domain ◽

Discriminative Ability ◽

Surveillance Camera ◽

Single Sample Per Person ◽

Suspect Identification

Numerous low-resolution (LR) face images are captured by a growing number of surveillance cameras nowadays. In some particular applications, such as suspect identification, it is required to recognize an LR face image captured by the surveillance camera using only one high-resolution (HR) profile face image on the ID card. This leads to LR face recognition with single sample per person (SSPP), which is more challenging than conventional LR face recognition or SSPP face recognition. To address this tough problem, we propose a Boosted Coupled Marginal Fisher Analysis (CMFA) approach, which unites domain adaptation and coupled mappings. An auxiliary database containing multiple HR and LR samples is introduced to explore more discriminative information, and locality preserving domain adaption (LPDA) is designed to realize good domain adaptation between SSPP training set (target domain) and auxiliary database (source domain). We perform LPDA on HR and LR images in both domains, then in the domain adaptation space we apply CMFA to learn the discriminative coupled mappings for classification. The learned coupled mappings embed knowledge from the auxiliary dataset, thus their discriminative ability is superior. We extensively evaluate the proposed method on FERET, LFW and SCface database, the promising results demonstrate its effectiveness on LR face recognition with SSPP.

Download Full-text

TB-DOTS PROGRAM;

The Professional Medical Journal ◽

10.29309/tpmj/2008.15.04.2941 ◽

2008 ◽

Vol 15 (04) ◽

pp. 524-532

Author(s):

MUHAMMAD ANWAR SULEHR ◽

AYUB `ALI

Keyword(s):

Urban Areas ◽

Program Design ◽

Health Workers ◽

Cross Sectional Study ◽

Age Group ◽

Sectional Study ◽

Cross Sectional ◽

Direct Supervision ◽

Suspect Identification ◽

Study Setting

Objectives: To assess the performance of Lady Health Workers (LHWs) in collection, storage & distribution of drugs andevaluate their effectiveness regarding TB suspect identification, referral, directly observing the intake of medicine, default identification andhealth education in TB-DOTS program. Design: A cross-sectional study. Setting: In district Toba Tek Singh. Period: From January to Sep2006. Materials & Methods: One hundred and Two LHWs were selected randomly and interviewed using a structured pre-tested questionnaire.Results: Among 102 LHWs, 76.5% were trained in TB-DOTS. Sixty four (62.7%) had qualification matric and above. Collection of the drugswas being performed properly by 87.3%, while 83.4% were storing the anti-TB drugs at proper places. Anti-TB drugs were being distributedto patients daily by 95.1%. Under the direct supervision of LHWs 69.6% of TB patients had completed treatment. In the areas of 58.8% LHWs,TB patients were declared cured after 8 months treatment. Defaulted TB cases were present, in the areas of 19.6% LHWs, while 12.8% of theLHWs had relapsed TB cases in their areas. Most of the LHWs (85.3%) had proper record of medicine and of the patients (84.3%). Conclusion:The experienced and TB-DOTS trained LHWs of urban areas, in the age group of 41-50 years had overall good performance. The LHWs havingqualification matric and above had better performance than the LHWs having middle qualification. TB-DOTS program in district Toba Tek Singhwas working successfully and it should be continued with some improvements and innovations.

Download Full-text