• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3962-3980
• /
• 2019

To deal with single sample face recognition, this paper presents a patch based semi-supervised linear regression (PSLR) algorithm, which draws facial variation information from unlabeled samples. Each facial image is divided into overlapped patches, and a regression model with mapping matrix will be constructed on each patch. Then, we adjust these matrices by mapping unlabeled patches to $[1,1,{\cdots},1]^T$. The solutions of all the mapping matrices are integrated into an overall objective function, which uses ${\ell}_{2,1}$-norm minimization constraints to improve discrimination ability of mapping matrices and reduce the impact of noise. After mapping matrices are computed, we adopt majority-voting strategy to classify the probe samples. To further learn the discrimination information between probe samples and obtain more robust mapping matrices, we also propose a multistage PSLR (MPSLR) algorithm, which iteratively updates the training dataset by adding those reliably labeled probe samples into it. The effectiveness of our approaches is evaluated using three public facial databases. Experimental results prove that our approaches are robust to illumination, expression and occlusion.

• Korean Journal of Veterinary Research
• /
• v.38 no.4
• /
• pp.898-908
• /
• 1998

The aim of this experiments were to assess the time-interval change of motional characteristics in frozen-thawed semen of Korean native cattle (KNC) by using computer aided semen analysis (CASA) technology. Twenty-six KNC frozen semen straws were obtained from Korean KNC improvement department, livestock improvement main division, national livestock cooperatives federation in Korea. Specimens were allowed to thaw at $37^{\circ}C$ for 30 sec in water bath. Semen analysis was performed on semen image analysis system (SIAS, Medical supply, Korea) adjusted to the gate settings and used the semen droplet ($5{\mu}l$) placed on Makler counting chamber (Sefi medical instrument, Israel) prewarmed at $37^{\circ}C$. The same person used the same micropipette to fill the Makler counting chamber. A total of 150 or more of sperms were analysed in each specimen by a single trained person by scanning at least 5 to 10 fields. The measurement parameters in SIAS were as follows ; frame rate = 30 frames per sec, image capture = 1 sec, minimum motile speed = $10{\mu}m/s$, maximum countable sperm number = 400. Statistical analysis was done by Student t-test with use of the Sigma plot program on a IBM personal computer. The dancemean(DNM) and hyperactivated sperm(HYP) of frozen-thawed KNC semen kinematics were significantly decreased(p < 0.05) after 10 min of incubation at $37^{\circ}C$ water bath. But, wobble(WOB) of same sample semen was significantly increased(p < 0.05) after 10 min of incubation and significantly decrease(p < 0.05) after 60 min of same incubation. And, after 30 mim of incubation, significantly differences were found most of motion kinematics, motifity(MOT), curvilinear velocity(VCL), straight line velocity(VSL), average path velocity(VAP), amplitude of lateral head displacement(ALH), beat cross frequency(BCF), mean angular displacement(MAD), dance(DNC), on same sample semen. The DNM of KNC semen sample was variable kinematics after 30 min of incubation. Also, the linearity(LIN) and straightness(STR) was significantly decreased(p < 0.05) from 60 min of incubation. In conclusion, the AI within 30 min after thawing of frozen semen can be an effective method for obtaining high fertility rate in KNC reproductive program.