Silhouette-Based Gender Recognition in Smart Environments Using Fuzzy Local Binary Patterns and Support Vector Machines

An application for video data analysis based on computer vision and machine learning methods is presented. Novel gender and age classifiers based on adaptive features, local binary patterns and support vector machines are proposed. More than 94% accuracy of viewer's gender recognition is achieved. Our age estimation algorithm provides world-quality results for MORTH database, but focused on real-life audience measurement videodata in which faces can be looks more or less similar to RUS-FD private database. In this case we can reach total mean absolute error score less than 7. All the video processing stages are united into a real-time system of audience analysis. The system allows to extract all the possible information about people from the input video stream, to aggregate and analyze this information in order to measure different statistical parameters. The promising practical application of such algorithms can be human-computer interaction, surveillance monitoring, video content analysis, targeted advertising, biometrics, and entertainment.

The Support Vector Machine (SVM) is an effective classification tool. Though extremely effective, SVMs are not a panacea. SVM training and testing is computationally expensive. Also, tuning the kernel parameters is a complicated procedure. On the other hand, the Nearest Neighbor (KNN) classifier is computationally efficient. In order to achieve the classification efficiency of an SVM and the computational efficiency of a KNN classifier, it has been shown previously that, rather than training a single global SVM, a separate SVM can be trained for the neighbourhood of each query point. In this work, we have extended this Local SVM (LSVM) formulation. Our Local Adaptive SVM (LASVM) formulation trains a local SVM in a modified neighborhood space of a query point. The main contributions of the paper are twofold: First, we present a novel LASVM algorithm to train a local SVM. Second, we discuss in detail the motivations behind the LSVM and LASVM formulations and its possible impacts on tuning the kernel parameters of an SVM. We found that training an SVM in a local adaptive neighborhood can result in significant classification performance gain. Experiments have been conducted on a selection of the UCIML, face, object, and digit databases.

Banana plantation is a commercial agricultural practice of huge significance especially in Asian and African countries. Banana production is affected by natural calamities and plant diseases. But plant diseases present a constant threat to the farmers affecting the quantity and quality of the banana cultivation. From the last decade, the image processing techniques and machine learning algorithms have been broadly used for identification and classification of infections in plants. In this work, texture pattern techniques for identification and classification of diseases in banana plants is introduced. The proposed methodology consists of two primary phases; (a) extraction of texture features from using local binary pattern (LBP); (b) classification of banana plant diseases and healthy banana plant. The texture features using LBP are extracted from an enhanced input image. The extracted features are fed to Support Vector Machine (SVM) and K-nearest neighbor (KNN) for final banana plant disease classification. The proposed technique is tested on the Plant Village dataset for the classification of two different experimental cases (i) Healthy-Black Sigatoka and (ii) Healthy-Cordana leaf spot. The proposed methodology attained an accuracy of 89.1 % and 90.9% for two experimental cases using SVM classifier.

Object detection and gender recognition were two different categories to be classified in a single section is a complicated task and this approach helps in supporting the blind people for an artificial vision. In this paper, our method to the betters vision sensation of blind persons by conversion of visualized data to audio data. Therefore this artificial intelligence model helps in detecting the objects as well as human face recognition with gender classification based on face recognition approach. This model processed with feature extraction and classification models. The feature extraction was comprised with multi scale-invariant feature transform (MSIFT), with feature optimization with support vector machine algorithm then classified using LASSO classifier. For better performance identification, three different classification models were implemented and tested too. Feature selection helps in making tests early to detect the objects and recognizing human actions using image processing approach. This approach can be applied for both offline and online modes. But in this scenario, an offline mode was implemented and was tested with a combination of different databases. For this process of classification ridge regression (RR), elastic net (EN), lasso regression (LR) and LASSO regression were implemented. The final classification results with accuracy are as follows for RR-89.6%, EN-93.5%, LR-93.2% and proposed approach (LRGS) with 98.4% accurate detection rate with prediction name of classes.

Gait energy image (GEI) is considered as an effective gait representation for gait-based human identification. In gait recognition, normally, GEI is computed from one full gait cycle. However in many circumstances, such a full gait cycle might not be available due to occlusion. Thus, the GEI is not complete, giving a rise to degrading gait identification rate. In this paper, we address this issue by proposing a novel method to reconstruct a complete GEI from a few frames of gait cycle. To do so, we propose a deep learning-based approach to transform incomplete GEI to the corresponding complete GEI obtained from a full gait cycle. More precisely, this transformation is done gradually by training several fully convolutional networks independently and then combining these as a uniform model. Experimental results on a large public gait dataset, namely OULP demonstrate the validity of the proposed method for gait identification when dealing with very incomplete gait cycles.

The Local Binary Patterns (LBP) feature extraction method is a theoretically and computationally simple and efficient methodology for texture analysis. The LBP operator is used in many applications such as facial expression recognition and face recognition. The original LBP is based on hard thresholding the neighborhood of each pixel, which makes texture representation sensitive to noise. In addition, LBP cannot distinguish between a strong and a weak pattern. In order to enhance the LBP approach, Fuzzy Local Binary Patterns (FLBP) is proposed. In FLBP, any neighborhood does not represented only by one code, but, it is represented by all existing codes with different degrees. In FLBP, any fuzzy Intersection and Union operators may be used. In this study, the following operators are applied and their results are compared together: Dot-Sum, Min-Max and normalized Min-Max. Based on the extensive experiments, the fuzzy Min-Max operators are more useful and can improve the accuracy in the application of Facial Expression Recognition (FER) about 4% (i.e., form 82.98% to 86.88%).

In order to improve the recognition performance and solve the problem of computational complexity caused by the high-dimensional data in human identification, a gait recognition method based on manifold learning is proposed in this paper. Firstly, gait energy image (GEI) of a walking person is abstracted from a gait image sequence. And then discrete wavelet decomposition (DWT) and t-Distributed Stochastic Neighbor Embedding (t-SNE) method is applied to reduce the dimension of high-dimensional GEI data. Finally the support vector machine (SVM) models are trained by the decomposed feature vectors, and the gaits are classified by the trained SVM models at last. Experimental results show that the proposed feature extraction method is efficient in reducing computational complexity and preserving image information.

Gender recognition from facial images has become one of challenging research problem in computer vision, security, verbal-nonverbal communication and human computer interaction applications nowadays. Because facial images include many information such as gender, facial expressions, age, ethnic origin in computer-aided applications, the success rate of the gender recognition depends on quality of facial images. In this paper, it is proposed a new gender recognition method combining Speed Up Robust Features (SURF) based Bags of Visual Words (BoW) and Support Vector Machine (SVM) algorithm unlike previous work. The method is tested on realistic frontal, left and right face images from modern gender recognition FERET dataset with 3560 samples to see efficiency of the proposed method. Experimental results show that the proposed method can obtain better gender recognition performance on FERET database and the accuracy level of on left and right face images is a bit lower than the average accuracy level of frontal ones.

The problem of gender recognition using visual and acoustic cues has recently received significant attention. This paper explores the use of Total Variability (i-vectors) and Inter-Session Variability (ISV) modeling techniques for both unimodal and bimodal gender recognition, and compares them to several state-of-the-art algorithms. The experimental evaluation is conducted on the FERET and LFW databases for face-based gender recognition, on the NISTSRE database for audio-based gender recognition, and on the MOBIO database for audio-visual gender recognition. Results on LFW show that the i-vectors technique outperforms state-of-the-art algorithms, which are based on Support Vector Machines (SVM) applied either on raw pixels, on Local Binary Patterns (LBP) or on Gabor filters, with an accuracy rate of about 95%. Results on NIST-SRE show that the i-vectors system is also superior to state-of-theart GMM-based gender recognition systems, with a relative gain of about 11%. Finally, results on MOBIO show that i-vectors and ISV also take advantage of combining visual and acoustic cues using logistic regression. The resulting bimodal systems achieve accuracy rates of about 98%.

Gait energy image (GEI) is composed of static body silhouette and dynamic frequency information of human gait. To achieve fast and efficient gait recognition, combined with the accurate description of the information of details and directions in image by Curvelet transform, a gait recognition method using GEI and Curvelet (GEIC) is presented. Firstly, to gain the gait energy images, the gait cycle is selected according to the aspect ratio. Secondly, Curvelet energy coefficients of the GEI, which are used as gait feature vector, are extracted by Curvelet transform in different scales and different directions. Finally, the gait recognition is accomplished by the K nearest neighbor (KNN) classifier. The experimental results demonstrate that GEIC performs well on CASIA(B) database, with the average accuracy of 86.83%. Compared with GEI+KPCA, GEI+W(2D)2PCA and GEI+(2D)2PCA, the algorithm GEIC achieves better robustness in the condition of the person wearing or packaging.

Garbage is one of the problems that always arise in Indonesia and even in the world. Increasingly, the production of waste is increased along with the increase in population and consumption. Therefore, need a prevention to stop wasting or producing garbage through recycle. This research do garbage recycle classification of cardboard, glass, metal, paper and plastic by using Local Binary Pattern (LBP) texture feature extraction methode and Support Vector Machine (SVM) as classification methode. For examination technic and dataset distribution is using K-Fold Cross Validation methode type Leave One Out (LOO). From examination result had been done were using fold 5 until fold 10. Polynomial kernel get highest accuracy result from every fold used with mean point 87.82%. Based on SVM classification examination result whether linear kernel, polynomial nor gaussian by using fold 5 until fold 10. The best accuracy point for cardboard garbage is 96.01%. For glass garbage, the best accuracy point is 90.62%. Then, metal garbage get the best accuracy point 89.72%. While paper garbage with highest accuracy point 96.01%. And plastic garbage with highest accuracy point 87.64%.

This paper uses a system that can recognize and detect skin diseases such as hives, eczema and psoriasis and provide temporary relief using RGH-HSV Color Space, Local Binary Pattern, Color Histogram and Support Vector Machine (SVM). These algorithms were used to train images for the testing process of the system. For the controlled testing the researchers gathered 30 images for each disease, eczema, hives and psoriasis, from dermnet.com and images from people that have been already diagnosed with the mentioned diseases in both training the prototype and testing the system's accuracy. The system identifying eczema, hives, and psoriasis have the following accuracies respectively, 96.0560%, 95.8041%, and 98.5609%.

Computer-assisted Parkinson’s disease-specific gait pattern recognition has gained more attention in the past decade due to its extensive application. In this research study, vision-based gait feature extraction is obtained from the observed skeleton points to support the real-time Parkinson disease prediction and diagnosis in the smart healthcare environment. So, a novel kernel-based principal component analysis (KPCA) is introduced for establishing respective feature extraction and dimensionality reduction on the patient’s video data. In this research study, a vision-based Parkinson disease identification system (VPDIS) is developed with a feature-weighted minimum distance classifier model to support the clinical assessment of Parkinson’s disease. At the time of experimentation, a steady-state walking style of the patient was captured using the cameras fixed in the smart healthcare environment. Then, the accumulated walking frames from the remote patients were transformed into the required binary silhouettes for the sake of noise minimisation and compression purpose. The resulting experimentation shows that the proposed feature extraction approach has significant improvements on the recognition of target gait patterns from the video-based gait analysis of Parkinson’s and normal patients. Accordingly, the proposed VPDIS using feature-weighted minimum distance classifier model provides better prediction time and classification accuracy against the existing healthcare systems that is developed using support vector machine and ensemble learning classifier models.

Gender classification play a significant role in recognition performance. For the purpose of visual surveillance, gender is considered as an important factor. In this paper a hybrid approach is proposed by fusing Gait Energy Image (GEI) with spatio temporal parameters for the gender classification. The dataset used is CASIA B which comprises of 118 subjects (89 males and 29 females). The proposed method consists of four steps. Gait Energy Image (GEI) is obtained by normalizing and averaging all the silhouette images in one gait cycle for all the subjects. The dimensions of GEI image is reduced by using principal component analysis. 5 spatio temporal parameters namely cadence, speed, height, stride length, stance period are calculated and concatenated with the reduced GEI Image. The reduced feature vector set is trained and tested using support vector machine and artificial neural network. Maximum accuracy achieved is 98.16% which shows the highly competitive results compared to previous methods.

\nIn order to effectively identify the bearing running condition, this paper proposed a new method which combines local mean decomposition (LMD) and support vector machine (SVM) together for ball bearing fault identification. Firstly, the gathered vibration signals were decomposed into a number of product functions (PFs) by LMD, with each PF corresponding to an instantaneous amplitude (IA) signal and instantaneous frequency (IF) signal. Then, introduce the concept of fault characteristic amplitude ratios which can be used to construct fault feature vectors; the extracted characteristic features were input into SVM to train and construct the fault identification model; the bearing running state identification was thereby realized. Cases of normal and fault were analyzed. Experimental results show that the proposed algorithm can diagnose the bearing failures reasonable and efficient.\n